Fix unload of bundled emb

Choose standalone embedding (in /embeddings folder) first

.eslintignore

@@ -0,0 +1,4 @@
+extensions
+extensions-disabled
+repositories
+venv

.eslintrc.js

@@ -0,0 +1,98 @@
+/* global module */
+module.exports = {
+    env: {
+        browser: true,
+        es2021: true,
+    },
+    extends: "eslint:recommended",
+    parserOptions: {
+        ecmaVersion: "latest",
+    },
+    rules: {
+        "arrow-spacing": "error",
+        "block-spacing": "error",
+        "brace-style": "error",
+        "comma-dangle": ["error", "only-multiline"],
+        "comma-spacing": "error",
+        "comma-style": ["error", "last"],
+        "curly": ["error", "multi-line", "consistent"],
+        "eol-last": "error",
+        "func-call-spacing": "error",
+        "function-call-argument-newline": ["error", "consistent"],
+        "function-paren-newline": ["error", "consistent"],
+        "indent": ["error", 4],
+        "key-spacing": "error",
+        "keyword-spacing": "error",
+        "linebreak-style": ["error", "unix"],
+        "no-extra-semi": "error",
+        "no-mixed-spaces-and-tabs": "error",
+        "no-multi-spaces": "error",
+        "no-redeclare": ["error", {builtinGlobals: false}],
+        "no-trailing-spaces": "error",
+        "no-unused-vars": "off",
+        "no-whitespace-before-property": "error",
+        "object-curly-newline": ["error", {consistent: true, multiline: true}],
+        "object-curly-spacing": ["error", "never"],
+        "operator-linebreak": ["error", "after"],
+        "quote-props": ["error", "consistent-as-needed"],
+        "semi": ["error", "always"],
+        "semi-spacing": "error",
+        "semi-style": ["error", "last"],
+        "space-before-blocks": "error",
+        "space-before-function-paren": ["error", "never"],
+        "space-in-parens": ["error", "never"],
+        "space-infix-ops": "error",
+        "space-unary-ops": "error",
+        "switch-colon-spacing": "error",
+        "template-curly-spacing": ["error", "never"],
+        "unicode-bom": "error",
+    },
+    globals: {
+        //script.js
+        gradioApp: "readonly",
+        executeCallbacks: "readonly",
+        onAfterUiUpdate: "readonly",
+        onOptionsChanged: "readonly",
+        onUiLoaded: "readonly",
+        onUiUpdate: "readonly",
+        uiCurrentTab: "writable",
+        uiElementInSight: "readonly",
+        uiElementIsVisible: "readonly",
+        //ui.js
+        opts: "writable",
+        all_gallery_buttons: "readonly",
+        selected_gallery_button: "readonly",
+        selected_gallery_index: "readonly",
+        switch_to_txt2img: "readonly",
+        switch_to_img2img_tab: "readonly",
+        switch_to_img2img: "readonly",
+        switch_to_sketch: "readonly",
+        switch_to_inpaint: "readonly",
+        switch_to_inpaint_sketch: "readonly",
+        switch_to_extras: "readonly",
+        get_tab_index: "readonly",
+        create_submit_args: "readonly",
+        restart_reload: "readonly",
+        updateInput: "readonly",
+        onEdit: "readonly",
+        //extraNetworks.js
+        requestGet: "readonly",
+        popup: "readonly",
+        // from python
+        localization: "readonly",
+        // progrssbar.js
+        randomId: "readonly",
+        requestProgress: "readonly",
+        // imageviewer.js
+        modalPrevImage: "readonly",
+        modalNextImage: "readonly",
+        // token-counters.js
+        setupTokenCounters: "readonly",
+        // localStorage.js
+        localSet: "readonly",
+        localGet: "readonly",
+        localRemove: "readonly",
+        // resizeHandle.js
+        setupResizeHandle: "writable"
+    }
+};

.git-blame-ignore-revs

@@ -0,0 +1,2 @@
+# Apply ESlint
+9c54b78d9dde5601e916f308d9a9d6953ec39430

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -26,7 +26,7 @@ body:
     id: steps
     attributes:
       label: Steps to reproduce the problem
-      description: Please provide us with precise step by step information on how to reproduce the bug
+      description: Please provide us with precise step by step instructions on how to reproduce the bug
       value: |
         1. Go to .... 
         2. Press ....
@@ -37,28 +37,16 @@ body:
     id: what-should
     attributes:
       label: What should have happened?
-      description: tell what you think the normal behavior should be
+      description: Tell us what you think the normal behavior should be
     validations:
       required: true
-  - type: input
-    id: commit
+  - type: textarea
+    id: sysinfo
     attributes:
-      label: Commit where the problem happens
-      description: Which commit are you running ? (Do not write *Latest version/repo/commit*, as this means nothing and will have changed by the time we read your issue. Rather, copy the **Commit hash** shown in the cmd/terminal when you launch the UI)
+      label: Sysinfo
+      description: System info file, generated by WebUI. You can generate it in settings, on the Sysinfo page. Drag the file into the field to upload it. If you submit your report without including the sysinfo file, the report will be closed. If needed, review the report to make sure it includes no personal information you don't want to share. If you can't start WebUI, you can use --dump-sysinfo commandline argument to generate the file.
     validations:
       required: true
-  - type: dropdown
-    id: platforms
-    attributes:
-      label: What platforms do you use to access UI ?
-      multiple: true
-      options:
-        - Windows
-        - Linux
-        - MacOS
-        - iOS
-        - Android
-        - Other/Cloud
   - type: dropdown
     id: browsers
     attributes:
@@ -70,14 +58,17 @@ body:
         - Brave
         - Apple Safari
         - Microsoft Edge
+        - Other
   - type: textarea
-    id: cmdargs
+    id: logs
     attributes:
-      label: Command Line Arguments
-      description: Are you using any launching parameters/command line arguments (modified webui-user.py) ? If yes, please write them below
+      label: Console logs
+      description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after your bug happened. If it's very long, provide a link to pastebin or similar service.
       render: Shell
+    validations:
+      required: true
   - type: textarea
     id: misc
     attributes:
-      label: Additional information, context and logs
-      description: Please provide us with any relevant additional info, context or log output.
+      label: Additional information
+      description: Please provide us with any relevant additional info or context.

.github/pull_request_template.md

@@ -1,28 +1,15 @@
-# Please read the [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) before submitting a pull request!
+## Description
 
-If you have a large change, pay special attention to this paragraph:
+* a simple description of what you're trying to accomplish
+* a summary of changes in code
+* which issues it fixes, if any
 
-> Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.
+## Screenshots/videos:
 
-Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.
 
-**Describe what this pull request is trying to achieve.**
+## Checklist:
 
-A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.
-
-**Additional notes and description of your changes**
-
-More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.
-
-**Environment this was tested in**
-
-List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.
- - OS: [e.g. Windows, Linux]
- - Browser: [e.g. chrome, safari]
- - Graphics card: [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]
-
-**Screenshots or videos of your changes**
-
-If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.
-
-This is **required** for anything that touches the user interface.
+- [ ] I have read [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
+- [ ] I have performed a self-review of my own code
+- [ ] My code follows the [style guidelines](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing#code-style)
+- [ ] My code passes [tests](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Tests)

.github/workflows/on_pull_request.yaml

@@ -1,39 +1,38 @@
-# See https://github.com/actions/starter-workflows/blob/1067f16ad8a1eac328834e4b0ae24f7d206f810d/ci/pylint.yml for original reference file
-name: Run Linting/Formatting on Pull Requests
+name: Linter
 
 on:
   - push
   - pull_request
-  # See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#onpull_requestpull_request_targetbranchesbranches-ignore for syntax docs
-  # if you want to filter out branches, delete the `- pull_request` and uncomment these lines :
-  # pull_request:  
-  #  branches:
-  #    - master
-  #  branches-ignore:
-  #    - development
 
 jobs:
-  lint:
+  lint-python:
+    name: ruff
     runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
         uses: actions/checkout@v3
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+      - uses: actions/setup-python@v4
         with:
-          python-version: 3.10.6
-          cache: pip
-          cache-dependency-path: |
-            **/requirements*txt
-      - name: Install PyLint
-        run: | 
-          python -m pip install --upgrade pip
-          pip install pylint
-      # This lets PyLint check to see if it can resolve imports
-      - name: Install dependencies
-        run: |
-          export COMMANDLINE_ARGS="--skip-torch-cuda-test --exit"
-          python launch.py
-      - name: Analysing the code with pylint
-        run: |
-          pylint $(git ls-files '*.py')
+          python-version: 3.11
+          # NB: there's no cache: pip here since we're not installing anything
+          #     from the requirements.txt file(s) in the repository; it's faster
+          #     not to have GHA download an (at the time of writing) 4 GB cache
+          #     of PyTorch and other dependencies.
+      - name: Install Ruff
+        run: pip install ruff==0.0.272
+      - name: Run Ruff
+        run: ruff .
+  lint-js:
+    name: eslint
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+      - name: Install Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: 18
+      - run: npm i --ci
+      - run: npm run lint

.github/workflows/run_tests.yaml

@@ -1,4 +1,4 @@
-name: Run basic features tests on CPU with empty SD model
+name: Tests
 
 on:
   - push
@@ -6,7 +6,9 @@ on:
 
 jobs:
   test:
+    name: tests on CPU with empty model
     runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
         uses: actions/checkout@v3
@@ -17,13 +19,55 @@ jobs:
           cache: pip
           cache-dependency-path: |
             **/requirements*txt
+            launch.py
+      - name: Install test dependencies
+        run: pip install wait-for-it -r requirements-test.txt
+        env:
+          PIP_DISABLE_PIP_VERSION_CHECK: "1"
+          PIP_PROGRESS_BAR: "off"
+      - name: Setup environment
+        run: python launch.py --skip-torch-cuda-test --exit
+        env:
+          PIP_DISABLE_PIP_VERSION_CHECK: "1"
+          PIP_PROGRESS_BAR: "off"
+          TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
+          WEBUI_LAUNCH_LIVE_OUTPUT: "1"
+          PYTHONUNBUFFERED: "1"
+      - name: Start test server
+        run: >
+          python -m coverage run
+          --data-file=.coverage.server
+          launch.py
+          --skip-prepare-environment
+          --skip-torch-cuda-test
+          --test-server
+          --do-not-download-clip
+          --no-half
+          --disable-opt-split-attention
+          --use-cpu all
+          --api-server-stop
+          2>&1 | tee output.txt &
       - name: Run tests
-        run: python launch.py --tests --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test
-      - name: Upload main app stdout-stderr
+        run: |
+          wait-for-it --service 127.0.0.1:7860 -t 600
+          python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
+      - name: Kill test server
+        if: always()
+        run: curl -vv -XPOST http://127.0.0.1:7860/sdapi/v1/server-stop && sleep 10
+      - name: Show coverage
+        run: |
+          python -m coverage combine .coverage*
+          python -m coverage report -i
+          python -m coverage html -i
+      - name: Upload main app output
         uses: actions/upload-artifact@v3
         if: always()
         with:
-          name: stdout-stderr
-          path: |
-            test/stdout.txt
-            test/stderr.txt
+          name: output
+          path: output.txt
+      - name: Upload coverage HTML
+        uses: actions/upload-artifact@v3
+        if: always()
+        with:
+          name: htmlcov
+          path: htmlcov

.github/workflows/warns_merge_master.yml

@@ -0,0 +1,19 @@
+name: Pull requests can't target master branch
+
+"on":
+  pull_request:
+    types:
+      - opened
+      - synchronize
+      - reopened
+    branches:
+      - master
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Warning marge into master
+        run: |
+          echo -e "::warning::This pull request directly merge into \"master\" branch, normally development happens on \"dev\" branch."
+          exit 1

.gitignore

@@ -32,4 +32,8 @@ notification.mp3
 /extensions
 /test/stdout.txt
 /test/stderr.txt
-/cache.json
+/cache.json*
+/config_states/
+/node_modules
+/package-lock.json
+/.coverage*

CHANGELOG.md

@@ -0,0 +1,507 @@
+## 1.6.0
+
+### Features:
+ * refiner support [#12371](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12371)
+ * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards
+ * add style editor dialog
+ * hires fix: add an option to use a different checkpoint for second pass ([#12181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12181))
+ * option to keep multiple loaded models in memory ([#12227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12227))
+ * new samplers: Restart, DPM++ 2M SDE Exponential, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential ([#12300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12300), [#12519](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12519), [#12542](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12542))
+ * rework DDIM, PLMS, UniPC to use CFG denoiser same as in k-diffusion samplers:
+   * makes all of them work with img2img
+   * makes prompt composition posssible (AND)
+   * makes them available for SDXL
+ * always show extra networks tabs in the UI ([#11808](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11808))
+ * use less RAM when creating models ([#11958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11958), [#12599](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12599))
+ * textual inversion inference support for SDXL
+ * extra networks UI: show metadata for SD checkpoints
+ * checkpoint merger: add metadata support 
+ * prompt editing and attention: add support for whitespace after the number ([ red : green : 0.5 ]) (seed breaking change) ([#12177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12177))
+ * VAE: allow selecting own VAE for each checkpoint (in user metadata editor)
+ * VAE: add selected VAE to infotext
+ * options in main UI: add own separate setting for txt2img and img2img, correctly read values from pasted infotext, add setting for column count ([#12551](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12551))
+ * add resize handle to txt2img and img2img tabs, allowing to change the amount of horizontable space given to generation parameters and resulting image gallery ([#12687](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12687), [#12723](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12723))
+ * change default behavior for batching cond/uncond -- now it's on by default, and is disabled by an UI setting (Optimizatios -> Batch cond/uncond) - if you are on lowvram/medvram and are getting OOM exceptions, you will need to enable it
+ * show current position in queue and make it so that requests are processed in the order of arrival ([#12707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12707))
+ * add `--medvram-sdxl` flag that only enables `--medvram` for SDXL models
+ * prompt editing timeline has separate range for first pass and hires-fix pass (seed breaking change) ([#12457](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12457))
+
+### Minor:
+ * img2img batch: RAM savings, VRAM savings, .tif, .tiff in img2img batch ([#12120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12120), [#12514](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12514), [#12515](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12515))
+ * postprocessing/extras: RAM savings ([#12479](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12479))
+ * XYZ: in the axis labels, remove pathnames from model filenames
+ * XYZ: support hires sampler ([#12298](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12298))
+ * XYZ: new option: use text inputs instead of dropdowns ([#12491](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12491))
+ * add gradio version warning
+ * sort list of VAE checkpoints ([#12297](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12297))
+ * use transparent white for mask in inpainting, along with an option to select the color ([#12326](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12326))
+ * move some settings to their own section: img2img, VAE
+ * add checkbox to show/hide dirs for extra networks
+ * Add TAESD(or more) options for all the VAE encode/decode operation ([#12311](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12311))
+ * gradio theme cache, new gradio themes, along with explanation that the user can input his own values ([#12346](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12346), [#12355](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12355))
+ * sampler fixes/tweaks: s_tmax, s_churn, s_noise, s_tmax ([#12354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12354), [#12356](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12356), [#12357](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12357), [#12358](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12358), [#12375](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12375), [#12521](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12521))
+ * update README.md with correct instructions for Linux installation ([#12352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12352))
+ * option to not save incomplete images, on by default ([#12338](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12338))
+ * enable cond cache by default
+ * git autofix for repos that are corrupted ([#12230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12230))
+ * allow to open images in new browser tab by middle mouse button ([#12379](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12379))
+ * automatically open webui in browser when running "locally" ([#12254](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12254))
+ * put commonly used samplers on top, make DPM++ 2M Karras the default choice
+ * zoom and pan: option to auto-expand a wide image, improved integration ([#12413](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12413), [#12727](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12727))
+ * option to cache Lora networks in memory
+ * rework hires fix UI to use accordion
+ * face restoration and tiling moved to settings - use "Options in main UI" setting if you want them back
+ * change quicksettings items to have variable width
+ * Lora: add Norm module, add support for bias ([#12503](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12503))
+ * Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console
+ * support search and display of hashes for all extra network items ([#12510](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12510))
+ * add extra noise param for img2img operations ([#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564))
+ * support for Lora with bias ([#12584](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12584))
+ * make interrupt quicker ([#12634](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12634))
+ * configurable gallery height ([#12648](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12648))
+ * make results column sticky ([#12645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12645))
+ * more hash filename patterns ([#12639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12639))
+ * make image viewer actually fit the whole page ([#12635](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12635))
+ * make progress bar work independently from live preview display which results in it being updated a lot more often
+ * forbid Full live preview method for medvram and add a setting to undo the forbidding
+ * make it possible to localize tooltips and placeholders
+ * add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))
+ * Restore faces and Tiling generation parameters have been moved to settings out of main UI
+   * if you want to put them back into main UI, use `Options in main UI` setting on the UI page.
+
+### Extensions and API:
+ * gradio 3.41.2
+ * also bump versions for packages: transformers, GitPython, accelerate, scikit-image, timm, tomesd
+ * support tooltip kwarg for gradio elements: gr.Textbox(label='hello', tooltip='world')
+ * properly clear the total console progressbar when using txt2img and img2img from API
+ * add cmd_arg --disable-extra-extensions and --disable-all-extensions ([#12294](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12294))
+ * shared.py and webui.py split into many files
+ * add --loglevel commandline argument for logging
+ * add a custom UI element that combines accordion and checkbox
+ * avoid importing gradio in tests because it spams warnings
+ * put infotext label for setting into OptionInfo definition rather than in a separate list
+ * make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` ([#12470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12470))
+ * option to make scripts UI without gr.Group
+ * add a way for scripts to register a callback for before/after just a single component's creation
+ * use dataclass for StableDiffusionProcessing
+ * store patches for Lora in a specialized module instead of inside torch
+ * support http/https URLs in API ([#12663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12663), [#12698](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12698))
+ * add extra noise callback ([#12616](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12616))
+ * dump current stack traces when exiting with SIGINT
+ * add type annotations for extra fields of shared.sd_model
+
+### Bug Fixes:
+ * Don't crash if out of local storage quota for javascriot localStorage
+ * XYZ plot do not fail if an exception occurs
+ * fix missing TI hash in infotext if generation uses both negative and positive TI ([#12269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12269))
+ * localization fixes ([#12307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12307))
+ * fix sdxl model invalid configuration after the hijack
+ * correctly toggle extras checkbox for infotext paste ([#12304](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12304))
+ * open raw sysinfo link in new page ([#12318](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12318))
+ * prompt parser: Account for empty field in alternating words syntax ([#12319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12319))
+ * add tab and carriage return to invalid filename chars ([#12327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12327))
+ * fix api only Lora not working ([#12387](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12387))
+ * fix options in main UI misbehaving when there's just one element
+ * make it possible to use a sampler from infotext even if it's hidden in the dropdown
+ * fix styles missing from the prompt in infotext when making a grid of batch of multiplie images
+ * prevent bogus progress output in console when calculating hires fix dimensions
+ * fix --use-textbox-seed
+ * fix broken `Lora/Networks: use old method` option ([#12466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12466))
+ * properly return `None` for VAE hash when using `--no-hashing` ([#12463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12463))
+ * MPS/macOS fixes and optimizations ([#12526](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12526))
+ * add second_order to samplers that mistakenly didn't have it
+ * when refreshing cards in extra networks UI, do not discard user's custom resolution
+ * fix processing error that happens if batch_size is not a multiple of how many prompts/negative prompts there are ([#12509](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12509))
+ * fix inpaint upload for alpha masks ([#12588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12588))
+ * fix exception when image sizes are not integers ([#12586](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12586))
+ * fix incorrect TAESD Latent scale ([#12596](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12596))
+ * auto add data-dir to gradio-allowed-path ([#12603](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12603))
+ * fix exception if extensuions dir is missing ([#12607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12607))
+ * fix issues with api model-refresh and vae-refresh ([#12638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12638))
+ * fix img2img background color for transparent images option not being used ([#12633](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12633))
+ * attempt to resolve NaN issue with unstable VAEs in fp32 mk2 ([#12630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12630))
+ * implement missing undo hijack for SDXL
+ * fix xyz swap axes ([#12684](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12684))
+ * fix errors in backup/restore tab if any of config files are broken ([#12689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12689))
+ * fix SD VAE switch error after model reuse ([#12685](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12685))
+ * fix trying to create images too large for the chosen format ([#12667](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12667))
+ * create Gradio temp directory if necessary ([#12717](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12717))
+ * prevent possible cache loss if exiting as it's being written by using an atomic operation to replace the cache with the new version
+ * set devices.dtype_unet correctly
+ * run RealESRGAN on GPU for non-CUDA devices ([#12737](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * prevent extra network buttons being obscured by description for very small card sizes ([#12745](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12745))
+ * fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt
+ * fix defaults settings page breaking when any of main UI tabs are hidden
+ * fix incorrect save/display of new values in Defaults page in settings
+ * fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working
+ * fix an error that prevents VAE being reloaded after an option change if a VAE near the checkpoint exists ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
+ * fix style editing dialog breaking if it's opened in both img2img and txt2img tabs
+ * fix a bug allowing users to bypass gradio and API authentication (reported by vysecurity) 
+ * fix notification not playing when built-in webui tab is inactive ([#12834](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12834))
+ * honor `--skip-install` for extension installers ([#12832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832))
+ * don't print blank stdout in extension installers ([#12833](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))
+ * do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))
+ * get progressbar to display correctly in extensions tab
+
+
+## 1.5.2
+
+### Bug Fixes:
+ * fix memory leak when generation fails
+ * update doggettx cross attention optimization to not use an unreasonable amount of memory in some edge cases -- suggestion by MorkTheOrk
+
+
+## 1.5.1
+
+### Minor:
+ * support parsing text encoder blocks in some new LoRAs
+ * delete scale checker script due to user demand
+
+### Extensions and API:
+ * add postprocess_batch_list script callback
+
+### Bug Fixes:
+ * fix TI training for SD1
+ * fix reload altclip model error
+ * prepend the pythonpath instead of overriding it
+ * fix typo in SD_WEBUI_RESTARTING
+ * if txt2img/img2img raises an exception, finally call state.end()
+ * fix composable diffusion weight parsing
+ * restyle Startup profile for black users
+ * fix webui not launching with --nowebui
+ * catch exception for non git extensions
+ * fix some options missing from /sdapi/v1/options
+ * fix for extension update status always saying "unknown"
+ * fix display of extra network cards that have `<>` in the name
+ * update lora extension to work with python 3.8
+
+
+## 1.5.0
+
+### Features:
+ * SD XL support
+ * user metadata system for custom networks
+ * extended Lora metadata editor: set activation text, default weight, view tags, training info
+ * Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)
+ * show github stars for extenstions
+ * img2img batch mode can read extra stuff from png info
+ * img2img batch works with subdirectories
+ * hotkeys to move prompt elements: alt+left/right
+ * restyle time taken/VRAM display
+ * add textual inversion hashes to infotext
+ * optimization: cache git extension repo information
+ * move generate button next to the generated picture for mobile clients
+ * hide cards for networks of incompatible Stable Diffusion version in Lora extra networks interface
+ * skip installing packages with pip if they all are already installed - startup speedup of about 2 seconds
+
+### Minor:
+ * checkbox to check/uncheck all extensions in the Installed tab
+ * add gradio user to infotext and to filename patterns
+ * allow gif for extra network previews
+ * add options to change colors in grid
+ * use natural sort for items in extra networks
+ * Mac: use empty_cache() from torch 2 to clear VRAM
+ * added automatic support for installing the right libraries for Navi3 (AMD)
+ * add option SWIN_torch_compile to accelerate SwinIR upscale
+ * suppress printing TI embedding info at start to console by default
+ * speedup extra networks listing
+ * added `[none]` filename token.
+ * removed thumbs extra networks view mode (use settings tab to change width/height/scale to get thumbs)
+ * add always_discard_next_to_last_sigma option to XYZ plot
+ * automatically switch to 32-bit float VAE if the generated picture has NaNs without the need for `--no-half-vae` commandline flag.
+ 
+### Extensions and API:
+ * api endpoints: /sdapi/v1/server-kill, /sdapi/v1/server-restart, /sdapi/v1/server-stop
+ * allow Script to have custom metaclass
+ * add model exists status check /sdapi/v1/options
+ * rename --add-stop-route to --api-server-stop
+ * add `before_hr` script callback
+ * add callback `after_extra_networks_activate`
+ * disable rich exception output in console for API by default, use WEBUI_RICH_EXCEPTIONS env var to enable
+ * return http 404 when thumb file not found
+ * allow replacing extensions index with environment variable
+ 
+### Bug Fixes:
+ * fix for catch errors when retrieving extension index #11290
+ * fix very slow loading speed of .safetensors files when reading from network drives
+ * API cache cleanup
+ * fix UnicodeEncodeError when writing to file CLIP Interrogator batch mode
+ * fix warning of 'has_mps' deprecated from PyTorch
+ * fix problem with extra network saving images as previews losing generation info
+ * fix throwing exception when trying to resize image with I;16 mode
+ * fix for #11534: canvas zoom and pan extension hijacking shortcut keys
+ * fixed launch script to be runnable from any directory
+ * don't add "Seed Resize: -1x-1" to API image metadata
+ * correctly remove end parenthesis with ctrl+up/down
+ * fixing --subpath on newer gradio version
+ * fix: check fill size none zero when resize  (fixes #11425)
+ * use submit and blur for quick settings textbox
+ * save img2img batch with images.save_image()
+ * prevent running preload.py for disabled extensions
+ * fix: previously, model name was added together with directory name to infotext and to [model_name] filename pattern; directory name is now not included
+
+
+## 1.4.1
+
+### Bug Fixes:
+ * add queue lock for refresh-checkpoints
+
+## 1.4.0
+
+### Features:
+ * zoom controls for inpainting
+ * run basic torch calculation at startup in parallel to reduce the performance impact of first generation
+ * option to pad prompt/neg prompt to be same length
+ * remove taming_transformers dependency
+ * custom k-diffusion scheduler settings
+ * add an option to show selected settings in main txt2img/img2img UI
+ * sysinfo tab in settings
+ * infer styles from prompts when pasting params into the UI
+ * an option to control the behavior of the above
+
+### Minor:
+ * bump Gradio to 3.32.0
+ * bump xformers to 0.0.20
+ * Add option to disable token counters
+ * tooltip fixes & optimizations
+ * make it possible to configure filename for the zip download
+ * `[vae_filename]` pattern for filenames
+ * Revert discarding penultimate sigma for DPM-Solver++(2M) SDE
+ * change UI reorder setting to multiselect
+ * read version info form CHANGELOG.md if git version info is not available
+ * link footer API to Wiki when API is not active
+ * persistent conds cache (opt-in optimization)
+ 
+### Extensions:
+ * After installing extensions, webui properly restarts the process rather than reloads the UI 
+ * Added VAE listing to web API. Via: /sdapi/v1/sd-vae
+ * custom unet support
+ * Add onAfterUiUpdate callback
+ * refactor EmbeddingDatabase.register_embedding() to allow unregistering
+ * add before_process callback for scripts
+ * add ability for alwayson scripts to specify section and let user reorder those sections
+ 
+### Bug Fixes:
+ * Fix dragging text to prompt
+ * fix incorrect quoting for infotext values with colon in them
+ * fix "hires. fix" prompt sharing same labels with txt2img_prompt
+ * Fix s_min_uncond default type int
+ * Fix for #10643 (Inpainting mask sometimes not working)
+ * fix bad styling for thumbs view in extra networks #10639
+ * fix for empty list of optimizations #10605
+ * small fixes to prepare_tcmalloc for Debian/Ubuntu compatibility
+ * fix --ui-debug-mode exit
+ * patch GitPython to not use leaky persistent processes
+ * fix duplicate Cross attention optimization after UI reload
+ * torch.cuda.is_available() check for SdOptimizationXformers
+ * fix hires fix using wrong conds in second pass if using Loras.
+ * handle exception when parsing generation parameters from png info
+ * fix upcast attention dtype error
+ * forcing Torch Version to 1.13.1 for RX 5000 series GPUs
+ * split mask blur into X and Y components, patch Outpainting MK2 accordingly
+ * don't die when a LoRA is a broken symlink
+ * allow activation of Generate Forever during generation
+
+
+## 1.3.2
+
+### Bug Fixes:
+ * fix files served out of tmp directory even if they are saved to disk
+ * fix postprocessing overwriting parameters
+
+## 1.3.1
+
+### Features:
+ * revert default cross attention optimization to Doggettx
+
+### Bug Fixes:
+ * fix bug: LoRA don't apply on dropdown list sd_lora
+ * fix png info always added even if setting is not enabled
+ * fix some fields not applying in xyz plot
+ * fix "hires. fix" prompt sharing same labels with txt2img_prompt
+ * fix lora hashes not being added properly to infotex if there is only one lora
+ * fix --use-cpu failing to work properly at startup
+ * make --disable-opt-split-attention command line option work again
+
+## 1.3.0
+
+### Features:
+ * add UI to edit defaults
+ * token merging (via dbolya/tomesd)
+ * settings tab rework: add a lot of additional explanations and links
+ * load extensions' Git metadata in parallel to loading the main program to save a ton of time during startup
+ * update extensions table: show branch, show date in separate column, and show version from tags if available
+ * TAESD - another option for cheap live previews
+ * allow choosing sampler and prompts for second pass of hires fix - hidden by default, enabled in settings
+ * calculate hashes for Lora
+ * add lora hashes to infotext
+ * when pasting infotext, use infotext's lora hashes to find local loras for `<lora:xxx:1>` entries whose hashes match loras the user has
+ * select cross attention optimization from UI
+
+### Minor:
+ * bump Gradio to 3.31.0
+ * bump PyTorch to 2.0.1 for macOS and Linux AMD
+ * allow setting defaults for elements in extensions' tabs
+ * allow selecting file type for live previews
+ * show "Loading..." for extra networks when displaying for the first time
+ * suppress ENSD infotext for samplers that don't use it
+ * clientside optimizations
+ * add options to show/hide hidden files and dirs in extra networks, and to not list models/files in hidden directories
+ * allow whitespace in styles.csv
+ * add option to reorder tabs
+ * move some functionality (swap resolution and set seed to -1) to client
+ * option to specify editor height for img2img
+ * button to copy image resolution into img2img width/height sliders
+ * switch from pyngrok to ngrok-py
+ * lazy-load images in extra networks UI
+ * set "Navigate image viewer with gamepad" option to false by default, by request
+ * change upscalers to download models into user-specified directory (from commandline args) rather than the default models/<...>
+ * allow hiding buttons in ui-config.json
+
+### Extensions:
+ * add /sdapi/v1/script-info api
+ * use Ruff to lint Python code
+ * use ESlint to lint Javascript code
+ * add/modify CFG callbacks for Self-Attention Guidance extension
+ * add command and endpoint for graceful server stopping
+ * add some locals (prompts/seeds/etc) from processing function into the Processing class as fields
+ * rework quoting for infotext items that have commas in them to use JSON (should be backwards compatible except for cases where it didn't work previously)
+ * add /sdapi/v1/refresh-loras api checkpoint post request
+ * tests overhaul
+
+### Bug Fixes:
+ * fix an issue preventing the program from starting if the user specifies a bad Gradio theme
+ * fix broken prompts from file script
+ * fix symlink scanning for extra networks
+ * fix --data-dir ignored when launching via webui-user.bat COMMANDLINE_ARGS
+ * allow web UI to be ran fully offline
+ * fix inability to run with --freeze-settings
+ * fix inability to merge checkpoint without adding metadata
+ * fix extra networks' save preview image not adding infotext for jpeg/webm
+ * remove blinking effect from text in hires fix and scale resolution preview
+ * make links to `http://<...>.git` extensions work in the extension tab
+ * fix bug with webui hanging at startup due to hanging git process
+
+
+## 1.2.1
+
+### Features:
+ * add an option to always refer to LoRA by filenames
+
+### Bug Fixes:
+ * never refer to LoRA by an alias if multiple LoRAs have same alias or the alias is called none
+ * fix upscalers disappearing after the user reloads UI
+ * allow bf16 in safe unpickler (resolves problems with loading some LoRAs)
+ * allow web UI to be ran fully offline
+ * fix localizations not working
+ * fix error for LoRAs: `'LatentDiffusion' object has no attribute 'lora_layer_mapping'`
+
+## 1.2.0
+
+### Features:
+ * do not wait for Stable Diffusion model to load at startup
+ * add filename patterns: `[denoising]`
+ * directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for
+ * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metdata of the file, if present, instead of filename (both can be used to activate LoRA)
+ * LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
+ * LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)
+ * LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)
+ * add version to infotext, footer and console output when starting
+ * add links to wiki for filename pattern settings
+ * add extended info for quicksettings setting and use multiselect input instead of a text field
+
+### Minor:
+ * bump Gradio to 3.29.0
+ * bump PyTorch to 2.0.1
+ * `--subpath` option for gradio for use with reverse proxy
+ * Linux/macOS: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
+ * do not apply localizations if there are none (possible frontend optimization)
+ * add extra `None` option for VAE in XYZ plot
+ * print error to console when batch processing in img2img fails
+ * create HTML for extra network pages only on demand
+ * allow directories starting with `.` to still list their models for LoRA, checkpoints, etc
+ * put infotext options into their own category in settings tab
+ * do not show licenses page when user selects Show all pages in settings
+
+### Extensions:
+ * tooltip localization support
+ * add API method to get LoRA models with prompt
+
+### Bug Fixes:
+ * re-add `/docs` endpoint
+ * fix gamepad navigation
+ * make the lightbox fullscreen image function properly
+ * fix squished thumbnails in extras tab
+ * keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)
+ * fix webui showing the same image if you configure the generation to always save results into same file
+ * fix bug with upscalers not working properly
+ * fix MPS on PyTorch 2.0.1, Intel Macs
+ * make it so that custom context menu from contextMenu.js only disappears after user's click, ignoring non-user click events
+ * prevent Reload UI button/link from reloading the page when it's not yet ready
+ * fix prompts from file script failing to read contents from a drag/drop file
+
+
+## 1.1.1
+### Bug Fixes:
+ * fix an error that prevents running webui on PyTorch<2.0 without --disable-safe-unpickle
+
+## 1.1.0
+### Features:
+ * switch to PyTorch 2.0.0 (except for AMD GPUs)
+ * visual improvements to custom code scripts
+ * add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`
+ * add support for saving init images in img2img, and record their hashes in infotext for reproducability
+ * automatically select current word when adjusting weight with ctrl+up/down
+ * add dropdowns for X/Y/Z plot
+ * add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs
+ * support Gradio's theme API
+ * use TCMalloc on Linux by default; possible fix for memory leaks
+ * add optimization option to remove negative conditioning at low sigma values #9177
+ * embed model merge metadata in .safetensors file
+ * extension settings backup/restore feature #9169
+ * add "resize by" and "resize to" tabs to img2img
+ * add option "keep original size" to textual inversion images preprocess
+ * image viewer scrolling via analog stick
+ * button to restore the progress from session lost / tab reload
+
+### Minor:
+ * bump Gradio to 3.28.1
+ * change "scale to" to sliders in Extras tab
+ * add labels to tool buttons to make it possible to hide them
+ * add tiled inference support for ScuNET
+ * add branch support for extension installation
+ * change Linux installation script to install into current directory rather than `/home/username`
+ * sort textual inversion embeddings by name (case-insensitive)
+ * allow styles.csv to be symlinked or mounted in docker
+ * remove the "do not add watermark to images" option
+ * make selected tab configurable with UI config
+ * make the extra networks UI fixed height and scrollable
+ * add `disable_tls_verify` arg for use with self-signed certs
+
+### Extensions:
+ * add reload callback
+ * add `is_hr_pass` field for processing
+
+### Bug Fixes:
+ * fix broken batch image processing on 'Extras/Batch Process' tab
+ * add "None" option to extra networks dropdowns
+ * fix FileExistsError for CLIP Interrogator
+ * fix /sdapi/v1/txt2img endpoint not working on Linux #9319
+ * fix disappearing live previews and progressbar during slow tasks
+ * fix fullscreen image view not working properly in some cases
+ * prevent alwayson_scripts args param resizing script_arg list when they are inserted in it
+ * fix prompt schedule for second order samplers
+ * fix image mask/composite for weird resolutions #9628
+ * use correct images for previews when using AND (see #9491)
+ * one broken image in img2img batch won't stop all processing
+ * fix image orientation bug in train/preprocess
+ * fix Ngrok recreating tunnels every reload
+ * fix `--realesrgan-models-path` and `--ldsr-models-path` not working
+ * fix `--skip-install` not working
+ * use SAMPLE file format in Outpainting Mk2 & Poorman
+ * do not fail all LoRAs if some have failed to load when making a picture
+
+## 1.0.0
+  * everything

CITATION.cff

@@ -0,0 +1,7 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - given-names: AUTOMATIC1111
+title: "Stable Diffusion Web UI"
+date-released: 2022-08-22
+url: "https://github.com/AUTOMATIC1111/stable-diffusion-webui"

README.md

@@ -13,11 +13,11 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Prompt Matrix
 - Stable Diffusion Upscale
 - Attention, specify parts of text that the model should pay more attention to
-    - a man in a ((tuxedo)) - will pay more attention to tuxedo
-    - a man in a (tuxedo:1.21) - alternative syntax
-    - select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user)
+    - a man in a `((tuxedo))` - will pay more attention to tuxedo
+    - a man in a `(tuxedo:1.21)` - alternative syntax
+    - select text and press `Ctrl+Up` or `Ctrl+Down` (or `Command+Up` or `Command+Down` if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
 - Loopback, run img2img processing multiple times
-- X/Y plot, a way to draw a 2 dimensional plot of images with different parameters
+- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
 - Textual Inversion
     - have as many embeddings as you want and use any names you like for them
     - use multiple embeddings with different numbers of vectors per token
@@ -46,7 +46,7 @@ A browser interface based on Gradio library for Stable Diffusion.
      - drag and drop an image/text-parameters to promptbox
 - Read Generation Parameters Button, loads parameters in promptbox to UI
 - Settings page
-- Running arbitrary python code from UI (must run with --allow-code to enable)
+- Running arbitrary python code from UI (must run with `--allow-code` to enable)
 - Mouseover hints for most UI elements
 - Possible to change defaults/mix/max/step values for UI elements via text config
 - Tiling support, a checkbox to create images that can be tiled like textures
@@ -69,7 +69,7 @@ A browser interface based on Gradio library for Stable Diffusion.
      - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
 - No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
 - DeepDanbooru integration, creates danbooru style tags for anime prompts
-- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
+- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add `--xformers` to commandline args)
 - via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
 - Generate forever option
 - Training tab
@@ -78,50 +78,58 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Clip skip
 - Hypernetworks
 - Loras (same as Hypernetworks but more pretty)
-- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt. 
+- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt 
 - Can select to load a different VAE from settings screen
 - Estimated completion time in progress bar
 - API
-- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
+- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML
 - via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
 - [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
 - [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
 - Now without any bad letters!
 - Load checkpoints in safetensors format
-- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
+- Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
 - Now with a license!
 - Reorder elements in the UI from settings screen
-- 
 
 ## Installation and Running
-Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
+Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:
+- [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
+- [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
+- [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
 
 Alternatively, use online services (like Google Colab):
 
 - [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
 
+### Installation on Windows 10/11 with NVidia-GPUs using release package
+1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract its contents.
+2. Run `update.bat`.
+3. Run `run.bat`.
+> For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs)
+
 ### Automatic Installation on Windows
-1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
+1. Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch), checking "Add Python to PATH".
 2. Install [git](https://git-scm.com/download/win).
 3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
-4. Place stable diffusion checkpoint (`model.ckpt`) in the `models/Stable-diffusion` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
-5. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
+4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
 
 ### Automatic Installation on Linux
 1. Install the dependencies:
 ```bash
 # Debian-based:
-sudo apt install wget git python3 python3-venv
+sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
 # Red Hat-based:
 sudo dnf install wget git python3
 # Arch-based:
 sudo pacman -S wget git python3
 ```
-2. To install in `/home/$(whoami)/stable-diffusion-webui/`, run:
+2. Navigate to the directory you would like the webui to be installed and execute the following command:
 ```bash
-bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)
+wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
 ```
-
+3. Run `webui.sh`.
+4. Check `webui-user.sh` for options.
 ### Installation on Apple Silicon
 
 Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
@@ -130,8 +138,11 @@ Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-w
 Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
 
 ## Documentation
+
 The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
 
+For the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) [crawlable wiki](https://github-wiki-see.page/m/AUTOMATIC1111/stable-diffusion-webui/wiki).
+
 ## Credits
 Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
 
@@ -155,6 +166,12 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
 - xformers - https://github.com/facebookresearch/xformers
 - DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
+- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
+- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
 - Security advice - RyotaK
+- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
+- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
+- LyCORIS - KohakuBlueleaf
+- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

configs/instruct-pix2pix.yaml

@@ -0,0 +1,98 @@
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+model:
+  base_learning_rate: 1.0e-04
+  target: modules.models.diffusion.ddpm_edit.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: edited
+    cond_stage_key: edit
+    # image_size: 64
+    # image_size: 32
+    image_size: 16
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 0 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 8
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 128
+    num_workers: 1
+    wrap: false
+    validation:
+      target: edit_dataset.EditDataset
+      params:
+        path: data/clip-filtered-dataset
+        cache_dir:  data/
+        cache_name: data_10k
+        split: val
+        min_text_sim: 0.2
+        min_image_sim: 0.75
+        min_direction_sim: 0.2
+        max_samples_per_prompt: 1
+        min_resize_res: 512
+        max_resize_res: 512
+        crop_res: 512
+        output_as_edit: False
+        real_input: True

configs/v1-inpainting-inference.yaml

@@ -1,8 +1,7 @@
 model:
-  base_learning_rate: 1.0e-4
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
   params:
-    parameterization: "v"
     linear_start: 0.00085
     linear_end: 0.0120
     num_timesteps_cond: 1
@@ -12,29 +11,36 @@ model:
     cond_stage_key: "txt"
     image_size: 64
     channels: 4
-    cond_stage_trainable: false
-    conditioning_key: crossattn
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid   # important
     monitor: val/loss_simple_ema
     scale_factor: 0.18215
-    use_ema: False # we set this to false because this is an inference only config
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
 
     unet_config:
       target: ldm.modules.diffusionmodules.openaimodel.UNetModel
       params:
-        use_checkpoint: True
-        use_fp16: True
         image_size: 32 # unused
-        in_channels: 4
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
         out_channels: 4
         model_channels: 320
         attention_resolutions: [ 4, 2, 1 ]
         num_res_blocks: 2
         channel_mult: [ 1, 2, 4, 4 ]
-        num_head_channels: 64 # need to fix for flash-attn
+        num_heads: 8
         use_spatial_transformer: True
-        use_linear_in_transformer: True
         transformer_depth: 1
-        context_dim: 1024
+        context_dim: 768
+        use_checkpoint: True
         legacy: False
 
     first_stage_config:
@@ -43,7 +49,6 @@ model:
         embed_dim: 4
         monitor: val/rec_loss
         ddconfig:
-          #attn_type: "vanilla-xformers"
           double_z: true
           z_channels: 4
           resolution: 256
@@ -62,7 +67,4 @@ model:
           target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
-      params:
-        freeze: True
-        layer: "penultimate"
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

environment-wsl2.yaml

@@ -4,8 +4,8 @@ channels:
   - defaults
 dependencies:
   - python=3.10
-  - pip=22.2.2
-  - cudatoolkit=11.3
-  - pytorch=1.12.1
-  - torchvision=0.13.1
-  - numpy=1.23.1
+  - pip=23.0
+  - cudatoolkit=11.8
+  - pytorch=2.0
+  - torchvision=0.15
+  - numpy=1.23

extensions-builtin/LDSR/ldsr_model_arch.py

@@ -12,7 +12,7 @@ import safetensors.torch
 
 from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.util import instantiate_from_config, ismap
-from modules import shared, sd_hijack
+from modules import shared, sd_hijack, devices
 
 cached_ldsr_model: torch.nn.Module = None
 
@@ -88,7 +88,7 @@ class LDSR:
 
         x_t = None
         logs = None
-        for n in range(n_runs):
+        for _ in range(n_runs):
             if custom_shape is not None:
                 x_t = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device)
                 x_t = repeat(x_t, '1 c h w -> b c h w', b=custom_shape[0])
@@ -110,11 +110,9 @@ class LDSR:
         diffusion_steps = int(steps)
         eta = 1.0
 
-        down_sample_method = 'Lanczos'
 
         gc.collect()
-        if torch.cuda.is_available:
-            torch.cuda.empty_cache()
+        devices.torch_gc()
 
         im_og = image
         width_og, height_og = im_og.size
@@ -151,14 +149,13 @@ class LDSR:
 
         del model
         gc.collect()
-        if torch.cuda.is_available:
-            torch.cuda.empty_cache()
+        devices.torch_gc()
 
         return a
 
 
 def get_cond(selected_path):
-    example = dict()
+    example = {}
     up_f = 4
     c = selected_path.convert('RGB')
     c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0)
@@ -196,7 +193,7 @@ def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_s
 @torch.no_grad()
 def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize_x0=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None,
                               corrector_kwargs=None, x_T=None, ddim_use_x0_pred=False):
-    log = dict()
+    log = {}
 
     z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key,
                                         return_first_stage_outputs=True,
@@ -244,7 +241,7 @@ def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize
         x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True)
         log["sample_noquant"] = x_sample_noquant
         log["sample_diff"] = torch.abs(x_sample_noquant - x_sample)
-    except:
+    except Exception:
         pass
 
     log["sample"] = x_sample

extensions-builtin/LDSR/scripts/ldsr_model.py

@@ -1,13 +1,11 @@
 import os
-import sys
-import traceback
-
-from basicsr.utils.download_util import load_file_from_url
 
+from modules.modelloader import load_file_from_url
 from modules.upscaler import Upscaler, UpscalerData
 from ldsr_model_arch import LDSR
-from modules import shared, script_callbacks
-import sd_hijack_autoencoder, sd_hijack_ddpm_v1
+from modules import shared, script_callbacks, errors
+import sd_hijack_autoencoder  # noqa: F401
+import sd_hijack_ddpm_v1  # noqa: F401
 
 
 class UpscalerLDSR(Upscaler):
@@ -25,35 +23,36 @@ class UpscalerLDSR(Upscaler):
         yaml_path = os.path.join(self.model_path, "project.yaml")
         old_model_path = os.path.join(self.model_path, "model.pth")
         new_model_path = os.path.join(self.model_path, "model.ckpt")
-        safetensors_model_path = os.path.join(self.model_path, "model.safetensors")
+
+        local_model_paths = self.find_models(ext_filter=[".ckpt", ".safetensors"])
+        local_ckpt_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.ckpt")]), None)
+        local_safetensors_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.safetensors")]), None)
+        local_yaml_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("project.yaml")]), None)
+
         if os.path.exists(yaml_path):
             statinfo = os.stat(yaml_path)
             if statinfo.st_size >= 10485760:
                 print("Removing invalid LDSR YAML file.")
                 os.remove(yaml_path)
+
         if os.path.exists(old_model_path):
             print("Renaming model from model.pth to model.ckpt")
             os.rename(old_model_path, new_model_path)
-        if os.path.exists(safetensors_model_path):
-            model = safetensors_model_path
-        else:
-            model = load_file_from_url(url=self.model_url, model_dir=self.model_path,
-                                       file_name="model.ckpt", progress=True)
-        yaml = load_file_from_url(url=self.yaml_url, model_dir=self.model_path,
-                                  file_name="project.yaml", progress=True)
 
-        try:
+        if local_safetensors_path is not None and os.path.exists(local_safetensors_path):
+            model = local_safetensors_path
+        else:
+            model = local_ckpt_path or load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name="model.ckpt")
+
+        yaml = local_yaml_path or load_file_from_url(self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml")
+
         return LDSR(model, yaml)
 
-        except Exception:
-            print("Error importing LDSR:", file=sys.stderr)
-            print(traceback.format_exc(), file=sys.stderr)
-        return None
-
     def do_upscale(self, img, path):
+        try:
             ldsr = self.load_model(path)
-        if ldsr is None:
-            print("NO LDSR!")
+        except Exception:
+            errors.report(f"Failed loading LDSR model {path}", exc_info=True)
             return img
         ddim_steps = shared.opts.ldsr_steps
         return ldsr.super_resolution(img, ddim_steps, self.scale)

extensions-builtin/LDSR/sd_hijack_autoencoder.py

@@ -1,16 +1,21 @@
 # The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo
 # The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo
 # As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder
-
+import numpy as np
 import torch
 import pytorch_lightning as pl
 import torch.nn.functional as F
 from contextlib import contextmanager
-from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
+
+from torch.optim.lr_scheduler import LambdaLR
+
+from ldm.modules.ema import LitEma
+from vqvae_quantize import VectorQuantizer2 as VectorQuantizer
 from ldm.modules.diffusionmodules.model import Encoder, Decoder
 from ldm.util import instantiate_from_config
 
 import ldm.models.autoencoder
+from packaging import version
 
 class VQModel(pl.LightningModule):
     def __init__(self,
@@ -19,7 +24,7 @@ class VQModel(pl.LightningModule):
                  n_embed,
                  embed_dim,
                  ckpt_path=None,
-                 ignore_keys=[],
+                 ignore_keys=None,
                  image_key="image",
                  colorize_nlabels=None,
                  monitor=None,
@@ -57,7 +62,7 @@ class VQModel(pl.LightningModule):
             print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
 
         if ckpt_path is not None:
-            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [])
         self.scheduler_config = scheduler_config
         self.lr_g_factor = lr_g_factor
 
@@ -76,18 +81,19 @@ class VQModel(pl.LightningModule):
                 if context is not None:
                     print(f"{context}: Restored training weights")
 
-    def init_from_ckpt(self, path, ignore_keys=list()):
+    def init_from_ckpt(self, path, ignore_keys=None):
         sd = torch.load(path, map_location="cpu")["state_dict"]
         keys = list(sd.keys())
         for k in keys:
-            for ik in ignore_keys:
+            for ik in ignore_keys or []:
                 if k.startswith(ik):
                     print("Deleting key {} from state_dict.".format(k))
                     del sd[k]
         missing, unexpected = self.load_state_dict(sd, strict=False)
         print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
-        if len(missing) > 0:
+        if missing:
             print(f"Missing Keys: {missing}")
+        if unexpected:
             print(f"Unexpected Keys: {unexpected}")
 
     def on_train_batch_end(self, *args, **kwargs):
@@ -165,7 +171,7 @@ class VQModel(pl.LightningModule):
     def validation_step(self, batch, batch_idx):
         log_dict = self._validation_step(batch, batch_idx)
         with self.ema_scope():
-            log_dict_ema = self._validation_step(batch, batch_idx, suffix="_ema")
+            self._validation_step(batch, batch_idx, suffix="_ema")
         return log_dict
 
     def _validation_step(self, batch, batch_idx, suffix=""):
@@ -232,7 +238,7 @@ class VQModel(pl.LightningModule):
         return self.decoder.conv_out.weight
 
     def log_images(self, batch, only_inputs=False, plot_ema=False, **kwargs):
-        log = dict()
+        log = {}
         x = self.get_input(batch, self.image_key)
         x = x.to(self.device)
         if only_inputs:
@@ -249,7 +255,8 @@ class VQModel(pl.LightningModule):
         if plot_ema:
             with self.ema_scope():
                 xrec_ema, _ = self(x)
-                if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema)
+                if x.shape[1] > 3:
+                    xrec_ema = self.to_rgb(xrec_ema)
                 log["reconstructions_ema"] = xrec_ema
         return log
 
@@ -264,7 +271,7 @@ class VQModel(pl.LightningModule):
 
 class VQModelInterface(VQModel):
     def __init__(self, embed_dim, *args, **kwargs):
-        super().__init__(embed_dim=embed_dim, *args, **kwargs)
+        super().__init__(*args, embed_dim=embed_dim, **kwargs)
         self.embed_dim = embed_dim
 
     def encode(self, x):
@@ -282,5 +289,5 @@ class VQModelInterface(VQModel):
         dec = self.decoder(quant)
         return dec
 
-setattr(ldm.models.autoencoder, "VQModel", VQModel)
-setattr(ldm.models.autoencoder, "VQModelInterface", VQModelInterface)
+ldm.models.autoencoder.VQModel = VQModel
+ldm.models.autoencoder.VQModelInterface = VQModelInterface

extensions-builtin/LDSR/sd_hijack_ddpm_v1.py

@@ -48,7 +48,7 @@ class DDPMV1(pl.LightningModule):
                  beta_schedule="linear",
                  loss_type="l2",
                  ckpt_path=None,
-                 ignore_keys=[],
+                 ignore_keys=None,
                  load_only_unet=False,
                  monitor="val/loss",
                  use_ema=True,
@@ -100,7 +100,7 @@ class DDPMV1(pl.LightningModule):
         if monitor is not None:
             self.monitor = monitor
         if ckpt_path is not None:
-            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet)
 
         self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
                                linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
@@ -182,22 +182,22 @@ class DDPMV1(pl.LightningModule):
                 if context is not None:
                     print(f"{context}: Restored training weights")
 
-    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+    def init_from_ckpt(self, path, ignore_keys=None, only_model=False):
         sd = torch.load(path, map_location="cpu")
         if "state_dict" in list(sd.keys()):
             sd = sd["state_dict"]
         keys = list(sd.keys())
         for k in keys:
-            for ik in ignore_keys:
+            for ik in ignore_keys or []:
                 if k.startswith(ik):
                     print("Deleting key {} from state_dict.".format(k))
                     del sd[k]
         missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
             sd, strict=False)
         print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
-        if len(missing) > 0:
+        if missing:
             print(f"Missing Keys: {missing}")
-        if len(unexpected) > 0:
+        if unexpected:
             print(f"Unexpected Keys: {unexpected}")
 
     def q_mean_variance(self, x_start, t):
@@ -375,7 +375,7 @@ class DDPMV1(pl.LightningModule):
 
     @torch.no_grad()
     def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
-        log = dict()
+        log = {}
         x = self.get_input(batch, self.first_stage_key)
         N = min(x.shape[0], N)
         n_row = min(x.shape[0], n_row)
@@ -383,7 +383,7 @@ class DDPMV1(pl.LightningModule):
         log["inputs"] = x
 
         # get diffusion row
-        diffusion_row = list()
+        diffusion_row = []
         x_start = x[:n_row]
 
         for t in range(self.num_timesteps):
@@ -444,13 +444,13 @@ class LatentDiffusionV1(DDPMV1):
             conditioning_key = None
         ckpt_path = kwargs.pop("ckpt_path", None)
         ignore_keys = kwargs.pop("ignore_keys", [])
-        super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
+        super().__init__(*args, conditioning_key=conditioning_key, **kwargs)
         self.concat_mode = concat_mode
         self.cond_stage_trainable = cond_stage_trainable
         self.cond_stage_key = cond_stage_key
         try:
             self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
-        except:
+        except Exception:
             self.num_downs = 0
         if not scale_by_std:
             self.scale_factor = scale_factor
@@ -877,16 +877,6 @@ class LatentDiffusionV1(DDPMV1):
                 c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
         return self.p_losses(x, c, t, *args, **kwargs)
 
-    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
-        def rescale_bbox(bbox):
-            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
-            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
-            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
-            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
-            return x0, y0, w, h
-
-        return [rescale_bbox(b) for b in bboxes]
-
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
@@ -1126,7 +1116,7 @@ class LatentDiffusionV1(DDPMV1):
         if cond is not None:
             if isinstance(cond, dict):
                 cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
-                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
 
@@ -1157,8 +1147,10 @@ class LatentDiffusionV1(DDPMV1):
 
             if i % log_every_t == 0 or i == timesteps - 1:
                 intermediates.append(x0_partial)
-            if callback: callback(i)
-            if img_callback: img_callback(img, i)
+            if callback:
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
         return img, intermediates
 
     @torch.no_grad()
@@ -1205,8 +1197,10 @@ class LatentDiffusionV1(DDPMV1):
 
             if i % log_every_t == 0 or i == timesteps - 1:
                 intermediates.append(img)
-            if callback: callback(i)
-            if img_callback: img_callback(img, i)
+            if callback:
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
 
         if return_intermediates:
             return img, intermediates
@@ -1221,7 +1215,7 @@ class LatentDiffusionV1(DDPMV1):
         if cond is not None:
             if isinstance(cond, dict):
                 cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
-                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
         return self.p_sample_loop(cond,
@@ -1253,7 +1247,7 @@ class LatentDiffusionV1(DDPMV1):
 
         use_ddim = ddim_steps is not None
 
-        log = dict()
+        log = {}
         z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
                                            return_first_stage_outputs=True,
                                            force_c_encode=True,
@@ -1280,7 +1274,7 @@ class LatentDiffusionV1(DDPMV1):
 
         if plot_diffusion_rows:
             # get diffusion row
-            diffusion_row = list()
+            diffusion_row = []
             z_start = z[:n_row]
             for t in range(self.num_timesteps):
                 if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
@@ -1322,7 +1316,7 @@ class LatentDiffusionV1(DDPMV1):
 
             if inpaint:
                 # make a simple center square
-                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                h, w = z.shape[2], z.shape[3]
                 mask = torch.ones(N, h, w).to(self.device)
                 # zeros will be filled in
                 mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
@@ -1424,10 +1418,10 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1):
     # TODO: move all layout-specific hacks to this class
     def __init__(self, cond_stage_key, *args, **kwargs):
         assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
-        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+        super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs)
 
     def log_images(self, batch, N=8, *args, **kwargs):
-        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+        logs = super().log_images(*args, batch=batch, N=N, **kwargs)
 
         key = 'train' if self.training else 'validation'
         dset = self.trainer.datamodule.datasets[key]
@@ -1443,7 +1437,7 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1):
         logs['bbox_image'] = cond_img
         return logs
 
-setattr(ldm.models.diffusion.ddpm, "DDPMV1", DDPMV1)
-setattr(ldm.models.diffusion.ddpm, "LatentDiffusionV1", LatentDiffusionV1)
-setattr(ldm.models.diffusion.ddpm, "DiffusionWrapperV1", DiffusionWrapperV1)
-setattr(ldm.models.diffusion.ddpm, "Layout2ImgDiffusionV1", Layout2ImgDiffusionV1)
+ldm.models.diffusion.ddpm.DDPMV1 = DDPMV1
+ldm.models.diffusion.ddpm.LatentDiffusionV1 = LatentDiffusionV1
+ldm.models.diffusion.ddpm.DiffusionWrapperV1 = DiffusionWrapperV1
+ldm.models.diffusion.ddpm.Layout2ImgDiffusionV1 = Layout2ImgDiffusionV1

extensions-builtin/LDSR/vqvae_quantize.py

@@ -0,0 +1,147 @@
+# Vendored from https://raw.githubusercontent.com/CompVis/taming-transformers/24268930bf1dce879235a7fddd0b2355b84d7ea6/taming/modules/vqvae/quantize.py,
+# where the license is as follows:
+#
+# Copyright (c) 2020 Patrick Esser and Robin Rombach and Björn Ommer
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE
+# OR OTHER DEALINGS IN THE SOFTWARE./
+
+import torch
+import torch.nn as nn
+import numpy as np
+from einops import rearrange
+
+
+class VectorQuantizer2(nn.Module):
+    """
+    Improved version over VectorQuantizer, can be used as a drop-in replacement. Mostly
+    avoids costly matrix multiplications and allows for post-hoc remapping of indices.
+    """
+
+    # NOTE: due to a bug the beta term was applied to the wrong term. for
+    # backwards compatibility we use the buggy version by default, but you can
+    # specify legacy=False to fix it.
+    def __init__(self, n_e, e_dim, beta, remap=None, unknown_index="random",
+                 sane_index_shape=False, legacy=True):
+        super().__init__()
+        self.n_e = n_e
+        self.e_dim = e_dim
+        self.beta = beta
+        self.legacy = legacy
+
+        self.embedding = nn.Embedding(self.n_e, self.e_dim)
+        self.embedding.weight.data.uniform_(-1.0 / self.n_e, 1.0 / self.n_e)
+
+        self.remap = remap
+        if self.remap is not None:
+            self.register_buffer("used", torch.tensor(np.load(self.remap)))
+            self.re_embed = self.used.shape[0]
+            self.unknown_index = unknown_index  # "random" or "extra" or integer
+            if self.unknown_index == "extra":
+                self.unknown_index = self.re_embed
+                self.re_embed = self.re_embed + 1
+            print(f"Remapping {self.n_e} indices to {self.re_embed} indices. "
+                  f"Using {self.unknown_index} for unknown indices.")
+        else:
+            self.re_embed = n_e
+
+        self.sane_index_shape = sane_index_shape
+
+    def remap_to_used(self, inds):
+        ishape = inds.shape
+        assert len(ishape) > 1
+        inds = inds.reshape(ishape[0], -1)
+        used = self.used.to(inds)
+        match = (inds[:, :, None] == used[None, None, ...]).long()
+        new = match.argmax(-1)
+        unknown = match.sum(2) < 1
+        if self.unknown_index == "random":
+            new[unknown] = torch.randint(0, self.re_embed, size=new[unknown].shape).to(device=new.device)
+        else:
+            new[unknown] = self.unknown_index
+        return new.reshape(ishape)
+
+    def unmap_to_all(self, inds):
+        ishape = inds.shape
+        assert len(ishape) > 1
+        inds = inds.reshape(ishape[0], -1)
+        used = self.used.to(inds)
+        if self.re_embed > self.used.shape[0]:  # extra token
+            inds[inds >= self.used.shape[0]] = 0  # simply set to zero
+        back = torch.gather(used[None, :][inds.shape[0] * [0], :], 1, inds)
+        return back.reshape(ishape)
+
+    def forward(self, z, temp=None, rescale_logits=False, return_logits=False):
+        assert temp is None or temp == 1.0, "Only for interface compatible with Gumbel"
+        assert rescale_logits is False, "Only for interface compatible with Gumbel"
+        assert return_logits is False, "Only for interface compatible with Gumbel"
+        # reshape z -> (batch, height, width, channel) and flatten
+        z = rearrange(z, 'b c h w -> b h w c').contiguous()
+        z_flattened = z.view(-1, self.e_dim)
+        # distances from z to embeddings e_j (z - e)^2 = z^2 + e^2 - 2 e * z
+
+        d = torch.sum(z_flattened ** 2, dim=1, keepdim=True) + \
+            torch.sum(self.embedding.weight ** 2, dim=1) - 2 * \
+            torch.einsum('bd,dn->bn', z_flattened, rearrange(self.embedding.weight, 'n d -> d n'))
+
+        min_encoding_indices = torch.argmin(d, dim=1)
+        z_q = self.embedding(min_encoding_indices).view(z.shape)
+        perplexity = None
+        min_encodings = None
+
+        # compute loss for embedding
+        if not self.legacy:
+            loss = self.beta * torch.mean((z_q.detach() - z) ** 2) + \
+                   torch.mean((z_q - z.detach()) ** 2)
+        else:
+            loss = torch.mean((z_q.detach() - z) ** 2) + self.beta * \
+                   torch.mean((z_q - z.detach()) ** 2)
+
+        # preserve gradients
+        z_q = z + (z_q - z).detach()
+
+        # reshape back to match original input shape
+        z_q = rearrange(z_q, 'b h w c -> b c h w').contiguous()
+
+        if self.remap is not None:
+            min_encoding_indices = min_encoding_indices.reshape(z.shape[0], -1)  # add batch axis
+            min_encoding_indices = self.remap_to_used(min_encoding_indices)
+            min_encoding_indices = min_encoding_indices.reshape(-1, 1)  # flatten
+
+        if self.sane_index_shape:
+            min_encoding_indices = min_encoding_indices.reshape(
+                z_q.shape[0], z_q.shape[2], z_q.shape[3])
+
+        return z_q, loss, (perplexity, min_encodings, min_encoding_indices)
+
+    def get_codebook_entry(self, indices, shape):
+        # shape specifying (batch, height, width, channel)
+        if self.remap is not None:
+            indices = indices.reshape(shape[0], -1)  # add batch axis
+            indices = self.unmap_to_all(indices)
+            indices = indices.reshape(-1)  # flatten again
+
+        # get quantized latent vectors
+        z_q = self.embedding(indices)
+
+        if shape is not None:
+            z_q = z_q.view(shape)
+            # reshape back to match original input shape
+            z_q = z_q.permute(0, 3, 1, 2).contiguous()
+
+        return z_q

extensions-builtin/Lora/extra_networks_lora.py

@@ -1,20 +1,67 @@
-from modules import extra_networks
-import lora
+from modules import extra_networks, shared
+import networks
+
 
 class ExtraNetworkLora(extra_networks.ExtraNetwork):
     def __init__(self):
         super().__init__('lora')
 
+        self.errors = {}
+        """mapping of network names to the number of errors the network had during operation"""
+
     def activate(self, p, params_list):
+        additional = shared.opts.sd_lora
+
+        self.errors.clear()
+
+        if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
+            p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
+            params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
+
         names = []
-        multipliers = []
+        te_multipliers = []
+        unet_multipliers = []
+        dyn_dims = []
         for params in params_list:
-            assert len(params.items) > 0
+            assert params.items
 
-            names.append(params.items[0])
-            multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
+            names.append(params.positional[0])
 
-        lora.load_loras(names, multipliers)
+            te_multiplier = float(params.positional[1]) if len(params.positional) > 1 else 1.0
+            te_multiplier = float(params.named.get("te", te_multiplier))
+
+            unet_multiplier = float(params.positional[2]) if len(params.positional) > 2 else te_multiplier
+            unet_multiplier = float(params.named.get("unet", unet_multiplier))
+
+            dyn_dim = int(params.positional[3]) if len(params.positional) > 3 else None
+            dyn_dim = int(params.named["dyn"]) if "dyn" in params.named else dyn_dim
+
+            te_multipliers.append(te_multiplier)
+            unet_multipliers.append(unet_multiplier)
+            dyn_dims.append(dyn_dim)
+
+        networks.load_networks(names, te_multipliers, unet_multipliers, dyn_dims)
+
+        if shared.opts.lora_add_hashes_to_infotext:
+            network_hashes = []
+            for item in networks.loaded_networks:
+                shorthash = item.network_on_disk.shorthash
+                if not shorthash:
+                    continue
+
+                alias = item.mentioned_name
+                if not alias:
+                    continue
+
+                alias = alias.replace(":", "").replace(",", "")
+
+                network_hashes.append(f"{alias}: {shorthash}")
+
+            if network_hashes:
+                p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
 
     def deactivate(self, p):
-        pass
+        if self.errors:
+            p.comment("Networks with errors: " + ", ".join(f"{k} ({v})" for k, v in self.errors.items()))
+
+            self.errors.clear()

extensions-builtin/Lora/lora.py

@@ -1,204 +1,9 @@
-import glob
-import os
-import re
-import torch
+import networks
 
-from modules import shared, devices, sd_models
+list_available_loras = networks.list_available_networks
 
-re_digits = re.compile(r"\d+")
-re_unet_down_blocks = re.compile(r"lora_unet_down_blocks_(\d+)_attentions_(\d+)_(.+)")
-re_unet_mid_blocks = re.compile(r"lora_unet_mid_block_attentions_(\d+)_(.+)")
-re_unet_up_blocks = re.compile(r"lora_unet_up_blocks_(\d+)_attentions_(\d+)_(.+)")
-re_text_block = re.compile(r"lora_te_text_model_encoder_layers_(\d+)_(.+)")
-
-
-def convert_diffusers_name_to_compvis(key):
-    def match(match_list, regex):
-        r = re.match(regex, key)
-        if not r:
-            return False
-
-        match_list.clear()
-        match_list.extend([int(x) if re.match(re_digits, x) else x for x in r.groups()])
-        return True
-
-    m = []
-
-    if match(m, re_unet_down_blocks):
-        return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[1]}_1_{m[2]}"
-
-    if match(m, re_unet_mid_blocks):
-        return f"diffusion_model_middle_block_1_{m[1]}"
-
-    if match(m, re_unet_up_blocks):
-        return f"diffusion_model_output_blocks_{m[0] * 3 + m[1]}_1_{m[2]}"
-
-    if match(m, re_text_block):
-        return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
-
-    return key
-
-
-class LoraOnDisk:
-    def __init__(self, name, filename):
-        self.name = name
-        self.filename = filename
-
-
-class LoraModule:
-    def __init__(self, name):
-        self.name = name
-        self.multiplier = 1.0
-        self.modules = {}
-        self.mtime = None
-
-
-class LoraUpDownModule:
-    def __init__(self):
-        self.up = None
-        self.down = None
-        self.alpha = None
-
-
-def assign_lora_names_to_compvis_modules(sd_model):
-    lora_layer_mapping = {}
-
-    for name, module in shared.sd_model.cond_stage_model.wrapped.named_modules():
-        lora_name = name.replace(".", "_")
-        lora_layer_mapping[lora_name] = module
-        module.lora_layer_name = lora_name
-
-    for name, module in shared.sd_model.model.named_modules():
-        lora_name = name.replace(".", "_")
-        lora_layer_mapping[lora_name] = module
-        module.lora_layer_name = lora_name
-
-    sd_model.lora_layer_mapping = lora_layer_mapping
-
-
-def load_lora(name, filename):
-    lora = LoraModule(name)
-    lora.mtime = os.path.getmtime(filename)
-
-    sd = sd_models.read_state_dict(filename)
-
-    keys_failed_to_match = []
-
-    for key_diffusers, weight in sd.items():
-        fullkey = convert_diffusers_name_to_compvis(key_diffusers)
-        key, lora_key = fullkey.split(".", 1)
-
-        sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
-        if sd_module is None:
-            keys_failed_to_match.append(key_diffusers)
-            continue
-
-        lora_module = lora.modules.get(key, None)
-        if lora_module is None:
-            lora_module = LoraUpDownModule()
-            lora.modules[key] = lora_module
-
-        if lora_key == "alpha":
-            lora_module.alpha = weight.item()
-            continue
-
-        if type(sd_module) == torch.nn.Linear:
-            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
-        elif type(sd_module) == torch.nn.Conv2d:
-            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
-        else:
-            assert False, f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}'
-
-        with torch.no_grad():
-            module.weight.copy_(weight)
-
-        module.to(device=devices.device, dtype=devices.dtype)
-
-        if lora_key == "lora_up.weight":
-            lora_module.up = module
-        elif lora_key == "lora_down.weight":
-            lora_module.down = module
-        else:
-            assert False, f'Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha'
-
-    if len(keys_failed_to_match) > 0:
-        print(f"Failed to match keys when loading Lora {filename}: {keys_failed_to_match}")
-
-    return lora
-
-
-def load_loras(names, multipliers=None):
-    already_loaded = {}
-
-    for lora in loaded_loras:
-        if lora.name in names:
-            already_loaded[lora.name] = lora
-
-    loaded_loras.clear()
-
-    loras_on_disk = [available_loras.get(name, None) for name in names]
-    if any([x is None for x in loras_on_disk]):
-        list_available_loras()
-
-        loras_on_disk = [available_loras.get(name, None) for name in names]
-
-    for i, name in enumerate(names):
-        lora = already_loaded.get(name, None)
-
-        lora_on_disk = loras_on_disk[i]
-        if lora_on_disk is not None:
-            if lora is None or os.path.getmtime(lora_on_disk.filename) > lora.mtime:
-                lora = load_lora(name, lora_on_disk.filename)
-
-        if lora is None:
-            print(f"Couldn't find Lora with name {name}")
-            continue
-
-        lora.multiplier = multipliers[i] if multipliers else 1.0
-        loaded_loras.append(lora)
-
-
-def lora_forward(module, input, res):
-    if len(loaded_loras) == 0:
-        return res
-
-    lora_layer_name = getattr(module, 'lora_layer_name', None)
-    for lora in loaded_loras:
-        module = lora.modules.get(lora_layer_name, None)
-        if module is not None:
-            res = res + module.up(module.down(input)) * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
-
-    return res
-
-
-def lora_Linear_forward(self, input):
-    return lora_forward(self, input, torch.nn.Linear_forward_before_lora(self, input))
-
-
-def lora_Conv2d_forward(self, input):
-    return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora(self, input))
-
-
-def list_available_loras():
-    available_loras.clear()
-
-    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
-
-    candidates = \
-        glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.pt'), recursive=True) + \
-        glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.safetensors'), recursive=True) + \
-        glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.ckpt'), recursive=True)
-
-    for filename in sorted(candidates):
-        if os.path.isdir(filename):
-            continue
-
-        name = os.path.splitext(os.path.basename(filename))[0]
-
-        available_loras[name] = LoraOnDisk(name, filename)
-
-
-available_loras = {}
-loaded_loras = []
-
-list_available_loras()
+available_loras = networks.available_networks
+available_lora_aliases = networks.available_network_aliases
+available_lora_hash_lookup = networks.available_network_hash_lookup
+forbidden_lora_aliases = networks.forbidden_network_aliases
+loaded_loras = networks.loaded_networks

extensions-builtin/Lora/lora_logger.py

@@ -0,0 +1,33 @@
+import sys
+import copy
+import logging
+
+
+class ColoredFormatter(logging.Formatter):
+    COLORS = {
+        "DEBUG": "\033[0;36m",  # CYAN
+        "INFO": "\033[0;32m",  # GREEN
+        "WARNING": "\033[0;33m",  # YELLOW
+        "ERROR": "\033[0;31m",  # RED
+        "CRITICAL": "\033[0;37;41m",  # WHITE ON RED
+        "RESET": "\033[0m",  # RESET COLOR
+    }
+
+    def format(self, record):
+        colored_record = copy.copy(record)
+        levelname = colored_record.levelname
+        seq = self.COLORS.get(levelname, self.COLORS["RESET"])
+        colored_record.levelname = f"{seq}{levelname}{self.COLORS['RESET']}"
+        return super().format(colored_record)
+
+
+logger = logging.getLogger("lora")
+logger.propagate = False
+
+
+if not logger.handlers:
+    handler = logging.StreamHandler(sys.stdout)
+    handler.setFormatter(
+        ColoredFormatter("[%(name)s]-%(levelname)s: %(message)s")
+    )
+    logger.addHandler(handler)

extensions-builtin/Lora/lora_patches.py

@@ -0,0 +1,31 @@
+import torch
+
+import networks
+from modules import patches
+
+
+class LoraPatches:
+    def __init__(self):
+        self.Linear_forward = patches.patch(__name__, torch.nn.Linear, 'forward', networks.network_Linear_forward)
+        self.Linear_load_state_dict = patches.patch(__name__, torch.nn.Linear, '_load_from_state_dict', networks.network_Linear_load_state_dict)
+        self.Conv2d_forward = patches.patch(__name__, torch.nn.Conv2d, 'forward', networks.network_Conv2d_forward)
+        self.Conv2d_load_state_dict = patches.patch(__name__, torch.nn.Conv2d, '_load_from_state_dict', networks.network_Conv2d_load_state_dict)
+        self.GroupNorm_forward = patches.patch(__name__, torch.nn.GroupNorm, 'forward', networks.network_GroupNorm_forward)
+        self.GroupNorm_load_state_dict = patches.patch(__name__, torch.nn.GroupNorm, '_load_from_state_dict', networks.network_GroupNorm_load_state_dict)
+        self.LayerNorm_forward = patches.patch(__name__, torch.nn.LayerNorm, 'forward', networks.network_LayerNorm_forward)
+        self.LayerNorm_load_state_dict = patches.patch(__name__, torch.nn.LayerNorm, '_load_from_state_dict', networks.network_LayerNorm_load_state_dict)
+        self.MultiheadAttention_forward = patches.patch(__name__, torch.nn.MultiheadAttention, 'forward', networks.network_MultiheadAttention_forward)
+        self.MultiheadAttention_load_state_dict = patches.patch(__name__, torch.nn.MultiheadAttention, '_load_from_state_dict', networks.network_MultiheadAttention_load_state_dict)
+
+    def undo(self):
+        self.Linear_forward = patches.undo(__name__, torch.nn.Linear, 'forward')
+        self.Linear_load_state_dict = patches.undo(__name__, torch.nn.Linear, '_load_from_state_dict')
+        self.Conv2d_forward = patches.undo(__name__, torch.nn.Conv2d, 'forward')
+        self.Conv2d_load_state_dict = patches.undo(__name__, torch.nn.Conv2d, '_load_from_state_dict')
+        self.GroupNorm_forward = patches.undo(__name__, torch.nn.GroupNorm, 'forward')
+        self.GroupNorm_load_state_dict = patches.undo(__name__, torch.nn.GroupNorm, '_load_from_state_dict')
+        self.LayerNorm_forward = patches.undo(__name__, torch.nn.LayerNorm, 'forward')
+        self.LayerNorm_load_state_dict = patches.undo(__name__, torch.nn.LayerNorm, '_load_from_state_dict')
+        self.MultiheadAttention_forward = patches.undo(__name__, torch.nn.MultiheadAttention, 'forward')
+        self.MultiheadAttention_load_state_dict = patches.undo(__name__, torch.nn.MultiheadAttention, '_load_from_state_dict')
+

extensions-builtin/Lora/lyco_helpers.py

@@ -0,0 +1,21 @@
+import torch
+
+
+def make_weight_cp(t, wa, wb):
+    temp = torch.einsum('i j k l, j r -> i r k l', t, wb)
+    return torch.einsum('i j k l, i r -> r j k l', temp, wa)
+
+
+def rebuild_conventional(up, down, shape, dyn_dim=None):
+    up = up.reshape(up.size(0), -1)
+    down = down.reshape(down.size(0), -1)
+    if dyn_dim is not None:
+        up = up[:, :dyn_dim]
+        down = down[:dyn_dim, :]
+    return (up @ down).reshape(shape)
+
+
+def rebuild_cp_decomposition(up, down, mid):
+    up = up.reshape(up.size(0), -1)
+    down = down.reshape(down.size(0), -1)
+    return torch.einsum('n m k l, i n, m j -> i j k l', mid, up, down)

extensions-builtin/Lora/network.py

@@ -0,0 +1,159 @@
+from __future__ import annotations
+import os
+from collections import namedtuple
+import enum
+
+from modules import sd_models, cache, errors, hashes, shared
+
+NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
+
+metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
+
+
+class SdVersion(enum.Enum):
+    Unknown = 1
+    SD1 = 2
+    SD2 = 3
+    SDXL = 4
+
+
+class NetworkOnDisk:
+    def __init__(self, name, filename):
+        self.name = name
+        self.filename = filename
+        self.metadata = {}
+        self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
+
+        def read_metadata():
+            metadata = sd_models.read_metadata_from_safetensors(filename)
+            metadata.pop('ssmd_cover_images', None)  # those are cover images, and they are too big to display in UI as text
+
+            return metadata
+
+        if self.is_safetensors:
+            try:
+                self.metadata = cache.cached_data_for_file('safetensors-metadata', "lora/" + self.name, filename, read_metadata)
+            except Exception as e:
+                errors.display(e, f"reading lora {filename}")
+
+        if self.metadata:
+            m = {}
+            for k, v in sorted(self.metadata.items(), key=lambda x: metadata_tags_order.get(x[0], 999)):
+                m[k] = v
+
+            self.metadata = m
+
+        self.alias = self.metadata.get('ss_output_name', self.name)
+
+        self.hash = None
+        self.shorthash = None
+        self.set_hash(
+            self.metadata.get('sshs_model_hash') or
+            hashes.sha256_from_cache(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or
+            ''
+        )
+
+        self.sd_version = self.detect_version()
+
+    def detect_version(self):
+        if str(self.metadata.get('ss_base_model_version', "")).startswith("sdxl_"):
+            return SdVersion.SDXL
+        elif str(self.metadata.get('ss_v2', "")) == "True":
+            return SdVersion.SD2
+        elif len(self.metadata):
+            return SdVersion.SD1
+
+        return SdVersion.Unknown
+
+    def set_hash(self, v):
+        self.hash = v
+        self.shorthash = self.hash[0:12]
+
+        if self.shorthash:
+            import networks
+            networks.available_network_hash_lookup[self.shorthash] = self
+
+    def read_hash(self):
+        if not self.hash:
+            self.set_hash(hashes.sha256(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or '')
+
+    def get_alias(self):
+        import networks
+        if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in networks.forbidden_network_aliases:
+            return self.name
+        else:
+            return self.alias
+
+
+class Network:  # LoraModule
+    def __init__(self, name, network_on_disk: NetworkOnDisk):
+        self.name = name
+        self.network_on_disk = network_on_disk
+        self.te_multiplier = 1.0
+        self.unet_multiplier = 1.0
+        self.dyn_dim = None
+        self.modules = {}
+        self.bundle_embeddings = {}
+        self.mtime = None
+
+        self.mentioned_name = None
+        """the text that was used to add the network to prompt - can be either name or an alias"""
+
+
+class ModuleType:
+    def create_module(self, net: Network, weights: NetworkWeights) -> Network | None:
+        return None
+
+
+class NetworkModule:
+    def __init__(self, net: Network, weights: NetworkWeights):
+        self.network = net
+        self.network_key = weights.network_key
+        self.sd_key = weights.sd_key
+        self.sd_module = weights.sd_module
+
+        if hasattr(self.sd_module, 'weight'):
+            self.shape = self.sd_module.weight.shape
+
+        self.dim = None
+        self.bias = weights.w.get("bias")
+        self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
+        self.scale = weights.w["scale"].item() if "scale" in weights.w else None
+
+    def multiplier(self):
+        if 'transformer' in self.sd_key[:20]:
+            return self.network.te_multiplier
+        else:
+            return self.network.unet_multiplier
+
+    def calc_scale(self):
+        if self.scale is not None:
+            return self.scale
+        if self.dim is not None and self.alpha is not None:
+            return self.alpha / self.dim
+
+        return 1.0
+
+    def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
+        if self.bias is not None:
+            updown = updown.reshape(self.bias.shape)
+            updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown = updown.reshape(output_shape)
+
+        if len(output_shape) == 4:
+            updown = updown.reshape(output_shape)
+
+        if orig_weight.size().numel() == updown.size().numel():
+            updown = updown.reshape(orig_weight.shape)
+
+        if ex_bias is not None:
+            ex_bias = ex_bias * self.multiplier()
+
+        return updown * self.calc_scale() * self.multiplier(), ex_bias
+
+    def calc_updown(self, target):
+        raise NotImplementedError()
+
+    def forward(self, x, y):
+        raise NotImplementedError()
+

extensions-builtin/Lora/network_full.py

@@ -0,0 +1,27 @@
+import network
+
+
+class ModuleTypeFull(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["diff"]):
+            return NetworkModuleFull(net, weights)
+
+        return None
+
+
+class NetworkModuleFull(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.weight = weights.w.get("diff")
+        self.ex_bias = weights.w.get("diff_b")
+
+    def calc_updown(self, orig_weight):
+        output_shape = self.weight.shape
+        updown = self.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+        if self.ex_bias is not None:
+            ex_bias = self.ex_bias.to(orig_weight.device, dtype=orig_weight.dtype)
+        else:
+            ex_bias = None
+
+        return self.finalize_updown(updown, orig_weight, output_shape, ex_bias)

extensions-builtin/Lora/network_hada.py

@@ -0,0 +1,55 @@
+import lyco_helpers
+import network
+
+
+class ModuleTypeHada(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["hada_w1_a", "hada_w1_b", "hada_w2_a", "hada_w2_b"]):
+            return NetworkModuleHada(net, weights)
+
+        return None
+
+
+class NetworkModuleHada(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        if hasattr(self.sd_module, 'weight'):
+            self.shape = self.sd_module.weight.shape
+
+        self.w1a = weights.w["hada_w1_a"]
+        self.w1b = weights.w["hada_w1_b"]
+        self.dim = self.w1b.shape[0]
+        self.w2a = weights.w["hada_w2_a"]
+        self.w2b = weights.w["hada_w2_b"]
+
+        self.t1 = weights.w.get("hada_t1")
+        self.t2 = weights.w.get("hada_t2")
+
+    def calc_updown(self, orig_weight):
+        w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
+        w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+        w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
+        w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+
+        output_shape = [w1a.size(0), w1b.size(1)]
+
+        if self.t1 is not None:
+            output_shape = [w1a.size(1), w1b.size(1)]
+            t1 = self.t1.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown1 = lyco_helpers.make_weight_cp(t1, w1a, w1b)
+            output_shape += t1.shape[2:]
+        else:
+            if len(w1b.shape) == 4:
+                output_shape += w1b.shape[2:]
+            updown1 = lyco_helpers.rebuild_conventional(w1a, w1b, output_shape)
+
+        if self.t2 is not None:
+            t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
+        else:
+            updown2 = lyco_helpers.rebuild_conventional(w2a, w2b, output_shape)
+
+        updown = updown1 * updown2
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_ia3.py

@@ -0,0 +1,30 @@
+import network
+
+
+class ModuleTypeIa3(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["weight"]):
+            return NetworkModuleIa3(net, weights)
+
+        return None
+
+
+class NetworkModuleIa3(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.w = weights.w["weight"]
+        self.on_input = weights.w["on_input"].item()
+
+    def calc_updown(self, orig_weight):
+        w = self.w.to(orig_weight.device, dtype=orig_weight.dtype)
+
+        output_shape = [w.size(0), orig_weight.size(1)]
+        if self.on_input:
+            output_shape.reverse()
+        else:
+            w = w.reshape(-1, 1)
+
+        updown = orig_weight * w
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_lokr.py

@@ -0,0 +1,64 @@
+import torch
+
+import lyco_helpers
+import network
+
+
+class ModuleTypeLokr(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        has_1 = "lokr_w1" in weights.w or ("lokr_w1_a" in weights.w and "lokr_w1_b" in weights.w)
+        has_2 = "lokr_w2" in weights.w or ("lokr_w2_a" in weights.w and "lokr_w2_b" in weights.w)
+        if has_1 and has_2:
+            return NetworkModuleLokr(net, weights)
+
+        return None
+
+
+def make_kron(orig_shape, w1, w2):
+    if len(w2.shape) == 4:
+        w1 = w1.unsqueeze(2).unsqueeze(2)
+    w2 = w2.contiguous()
+    return torch.kron(w1, w2).reshape(orig_shape)
+
+
+class NetworkModuleLokr(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.w1 = weights.w.get("lokr_w1")
+        self.w1a = weights.w.get("lokr_w1_a")
+        self.w1b = weights.w.get("lokr_w1_b")
+        self.dim = self.w1b.shape[0] if self.w1b is not None else self.dim
+        self.w2 = weights.w.get("lokr_w2")
+        self.w2a = weights.w.get("lokr_w2_a")
+        self.w2b = weights.w.get("lokr_w2_b")
+        self.dim = self.w2b.shape[0] if self.w2b is not None else self.dim
+        self.t2 = weights.w.get("lokr_t2")
+
+    def calc_updown(self, orig_weight):
+        if self.w1 is not None:
+            w1 = self.w1.to(orig_weight.device, dtype=orig_weight.dtype)
+        else:
+            w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1 = w1a @ w1b
+
+        if self.w2 is not None:
+            w2 = self.w2.to(orig_weight.device, dtype=orig_weight.dtype)
+        elif self.t2 is None:
+            w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2 = w2a @ w2b
+        else:
+            t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
+
+        output_shape = [w1.size(0) * w2.size(0), w1.size(1) * w2.size(1)]
+        if len(orig_weight.shape) == 4:
+            output_shape = orig_weight.shape
+
+        updown = make_kron(output_shape, w1, w2)
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_lora.py

@@ -0,0 +1,86 @@
+import torch
+
+import lyco_helpers
+import network
+from modules import devices
+
+
+class ModuleTypeLora(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
+            return NetworkModuleLora(net, weights)
+
+        return None
+
+
+class NetworkModuleLora(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.up_model = self.create_module(weights.w, "lora_up.weight")
+        self.down_model = self.create_module(weights.w, "lora_down.weight")
+        self.mid_model = self.create_module(weights.w, "lora_mid.weight", none_ok=True)
+
+        self.dim = weights.w["lora_down.weight"].shape[0]
+
+    def create_module(self, weights, key, none_ok=False):
+        weight = weights.get(key)
+
+        if weight is None and none_ok:
+            return None
+
+        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention]
+        is_conv = type(self.sd_module) in [torch.nn.Conv2d]
+
+        if is_linear:
+            weight = weight.reshape(weight.shape[0], -1)
+            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
+        elif is_conv and key == "lora_down.weight" or key == "dyn_up":
+            if len(weight.shape) == 2:
+                weight = weight.reshape(weight.shape[0], -1, 1, 1)
+
+            if weight.shape[2] != 1 or weight.shape[3] != 1:
+                module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
+            else:
+                module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
+        elif is_conv and key == "lora_mid.weight":
+            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
+        elif is_conv and key == "lora_up.weight" or key == "dyn_down":
+            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
+        else:
+            raise AssertionError(f'Lora layer {self.network_key} matched a layer with unsupported type: {type(self.sd_module).__name__}')
+
+        with torch.no_grad():
+            if weight.shape != module.weight.shape:
+                weight = weight.reshape(module.weight.shape)
+            module.weight.copy_(weight)
+
+        module.to(device=devices.cpu, dtype=devices.dtype)
+        module.weight.requires_grad_(False)
+
+        return module
+
+    def calc_updown(self, orig_weight):
+        up = self.up_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+        down = self.down_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+
+        output_shape = [up.size(0), down.size(1)]
+        if self.mid_model is not None:
+            # cp-decomposition
+            mid = self.mid_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown = lyco_helpers.rebuild_cp_decomposition(up, down, mid)
+            output_shape += mid.shape[2:]
+        else:
+            if len(down.shape) == 4:
+                output_shape += down.shape[2:]
+            updown = lyco_helpers.rebuild_conventional(up, down, output_shape, self.network.dyn_dim)
+
+        return self.finalize_updown(updown, orig_weight, output_shape)
+
+    def forward(self, x, y):
+        self.up_model.to(device=devices.device)
+        self.down_model.to(device=devices.device)
+
+        return y + self.up_model(self.down_model(x)) * self.multiplier() * self.calc_scale()
+
+

extensions-builtin/Lora/network_norm.py

@@ -0,0 +1,28 @@
+import network
+
+
+class ModuleTypeNorm(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["w_norm", "b_norm"]):
+            return NetworkModuleNorm(net, weights)
+
+        return None
+
+
+class NetworkModuleNorm(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.w_norm = weights.w.get("w_norm")
+        self.b_norm = weights.w.get("b_norm")
+
+    def calc_updown(self, orig_weight):
+        output_shape = self.w_norm.shape
+        updown = self.w_norm.to(orig_weight.device, dtype=orig_weight.dtype)
+
+        if self.b_norm is not None:
+            ex_bias = self.b_norm.to(orig_weight.device, dtype=orig_weight.dtype)
+        else:
+            ex_bias = None
+
+        return self.finalize_updown(updown, orig_weight, output_shape, ex_bias)

extensions-builtin/Lora/networks.py

@@ -0,0 +1,641 @@
+import logging
+import os
+import re
+
+import lora_patches
+import network
+import network_lora
+import network_hada
+import network_ia3
+import network_lokr
+import network_full
+import network_norm
+
+import torch
+from typing import Union
+
+from modules import shared, devices, sd_models, errors, scripts, sd_hijack
+from modules.textual_inversion.textual_inversion import Embedding
+
+from lora_logger import logger
+
+module_types = [
+    network_lora.ModuleTypeLora(),
+    network_hada.ModuleTypeHada(),
+    network_ia3.ModuleTypeIa3(),
+    network_lokr.ModuleTypeLokr(),
+    network_full.ModuleTypeFull(),
+    network_norm.ModuleTypeNorm(),
+]
+
+
+re_digits = re.compile(r"\d+")
+re_x_proj = re.compile(r"(.*)_([qkv]_proj)$")
+re_compiled = {}
+
+suffix_conversion = {
+    "attentions": {},
+    "resnets": {
+        "conv1": "in_layers_2",
+        "conv2": "out_layers_3",
+        "norm1": "in_layers_0",
+        "norm2": "out_layers_0",
+        "time_emb_proj": "emb_layers_1",
+        "conv_shortcut": "skip_connection",
+    }
+}
+
+
+def convert_diffusers_name_to_compvis(key, is_sd2):
+    def match(match_list, regex_text):
+        regex = re_compiled.get(regex_text)
+        if regex is None:
+            regex = re.compile(regex_text)
+            re_compiled[regex_text] = regex
+
+        r = re.match(regex, key)
+        if not r:
+            return False
+
+        match_list.clear()
+        match_list.extend([int(x) if re.match(re_digits, x) else x for x in r.groups()])
+        return True
+
+    m = []
+
+    if match(m, r"lora_unet_conv_in(.*)"):
+        return f'diffusion_model_input_blocks_0_0{m[0]}'
+
+    if match(m, r"lora_unet_conv_out(.*)"):
+        return f'diffusion_model_out_2{m[0]}'
+
+    if match(m, r"lora_unet_time_embedding_linear_(\d+)(.*)"):
+        return f"diffusion_model_time_embed_{m[0] * 2 - 2}{m[1]}"
+
+    if match(m, r"lora_unet_down_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
+        suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
+        return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
+
+    if match(m, r"lora_unet_mid_block_(attentions|resnets)_(\d+)_(.+)"):
+        suffix = suffix_conversion.get(m[0], {}).get(m[2], m[2])
+        return f"diffusion_model_middle_block_{1 if m[0] == 'attentions' else m[1] * 2}_{suffix}"
+
+    if match(m, r"lora_unet_up_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
+        suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
+        return f"diffusion_model_output_blocks_{m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
+
+    if match(m, r"lora_unet_down_blocks_(\d+)_downsamplers_0_conv"):
+        return f"diffusion_model_input_blocks_{3 + m[0] * 3}_0_op"
+
+    if match(m, r"lora_unet_up_blocks_(\d+)_upsamplers_0_conv"):
+        return f"diffusion_model_output_blocks_{2 + m[0] * 3}_{2 if m[0]>0 else 1}_conv"
+
+    if match(m, r"lora_te_text_model_encoder_layers_(\d+)_(.+)"):
+        if is_sd2:
+            if 'mlp_fc1' in m[1]:
+                return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
+            elif 'mlp_fc2' in m[1]:
+                return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
+            else:
+                return f"model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
+
+        return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
+
+    if match(m, r"lora_te2_text_model_encoder_layers_(\d+)_(.+)"):
+        if 'mlp_fc1' in m[1]:
+            return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
+        elif 'mlp_fc2' in m[1]:
+            return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
+        else:
+            return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
+
+    return key
+
+
+def assign_network_names_to_compvis_modules(sd_model):
+    network_layer_mapping = {}
+
+    if shared.sd_model.is_sdxl:
+        for i, embedder in enumerate(shared.sd_model.conditioner.embedders):
+            if not hasattr(embedder, 'wrapped'):
+                continue
+
+            for name, module in embedder.wrapped.named_modules():
+                network_name = f'{i}_{name.replace(".", "_")}'
+                network_layer_mapping[network_name] = module
+                module.network_layer_name = network_name
+    else:
+        for name, module in shared.sd_model.cond_stage_model.wrapped.named_modules():
+            network_name = name.replace(".", "_")
+            network_layer_mapping[network_name] = module
+            module.network_layer_name = network_name
+
+    for name, module in shared.sd_model.model.named_modules():
+        network_name = name.replace(".", "_")
+        network_layer_mapping[network_name] = module
+        module.network_layer_name = network_name
+
+    sd_model.network_layer_mapping = network_layer_mapping
+
+
+def load_network(name, network_on_disk):
+    net = network.Network(name, network_on_disk)
+    net.mtime = os.path.getmtime(network_on_disk.filename)
+
+    sd = sd_models.read_state_dict(network_on_disk.filename)
+
+    # this should not be needed but is here as an emergency fix for an unknown error people are experiencing in 1.2.0
+    if not hasattr(shared.sd_model, 'network_layer_mapping'):
+        assign_network_names_to_compvis_modules(shared.sd_model)
+
+    keys_failed_to_match = {}
+    is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
+
+    matched_networks = {}
+    bundle_embeddings = {}
+
+    for key_network, weight in sd.items():
+        key_network_without_network_parts, network_part = key_network.split(".", 1)
+        if key_network_without_network_parts == "bundle_emb":
+            emb_name, vec_name = network_part.split(".", 1)
+            emb_dict = bundle_embeddings.get(emb_name, {})
+            if vec_name.split('.')[0] == 'string_to_param':
+                _, k2 = vec_name.split('.', 1)
+                emb_dict['string_to_param'] = {k2: weight}
+            else:
+                emb_dict[vec_name] = weight
+            bundle_embeddings[emb_name] = emb_dict
+
+        key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
+        sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+        if sd_module is None:
+            m = re_x_proj.match(key)
+            if m:
+                sd_module = shared.sd_model.network_layer_mapping.get(m.group(1), None)
+
+        # SDXL loras seem to already have correct compvis keys, so only need to replace "lora_unet" with "diffusion_model"
+        if sd_module is None and "lora_unet" in key_network_without_network_parts:
+            key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
+            sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+        elif sd_module is None and "lora_te1_text_model" in key_network_without_network_parts:
+            key = key_network_without_network_parts.replace("lora_te1_text_model", "0_transformer_text_model")
+            sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+            # some SD1 Loras also have correct compvis keys
+            if sd_module is None:
+                key = key_network_without_network_parts.replace("lora_te1_text_model", "transformer_text_model")
+                sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+        if sd_module is None:
+            keys_failed_to_match[key_network] = key
+            continue
+
+        if key not in matched_networks:
+            matched_networks[key] = network.NetworkWeights(network_key=key_network, sd_key=key, w={}, sd_module=sd_module)
+
+        matched_networks[key].w[network_part] = weight
+
+    for key, weights in matched_networks.items():
+        net_module = None
+        for nettype in module_types:
+            net_module = nettype.create_module(net, weights)
+            if net_module is not None:
+                break
+
+        if net_module is None:
+            raise AssertionError(f"Could not find a module type (out of {', '.join([x.__class__.__name__ for x in module_types])}) that would accept those keys: {', '.join(weights.w)}")
+
+        net.modules[key] = net_module
+
+    embeddings = {}
+    for emb_name, data in bundle_embeddings.items():
+        # textual inversion embeddings
+        if 'string_to_param' in data:
+            param_dict = data['string_to_param']
+            param_dict = getattr(param_dict, '_parameters', param_dict)  # fix for torch 1.12.1 loading saved file from torch 1.11
+            assert len(param_dict) == 1, 'embedding file has multiple terms in it'
+            emb = next(iter(param_dict.items()))[1]
+            vec = emb.detach().to(devices.device, dtype=torch.float32)
+            shape = vec.shape[-1]
+            vectors = vec.shape[0]
+        elif type(data) == dict and 'clip_g' in data and 'clip_l' in data:  # SDXL embedding
+            vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()}
+            shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1]
+            vectors = data['clip_g'].shape[0]
+        elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts
+            assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
+
+            emb = next(iter(data.values()))
+            if len(emb.shape) == 1:
+                emb = emb.unsqueeze(0)
+            vec = emb.detach().to(devices.device, dtype=torch.float32)
+            shape = vec.shape[-1]
+            vectors = vec.shape[0]
+        else:
+            raise Exception(f"Couldn't identify {emb_name} in lora: {name} as neither textual inversion embedding nor diffuser concept.")
+
+        embedding = Embedding(vec, emb_name)
+        embedding.vectors = vectors
+        embedding.shape = shape
+        embedding.loaded = None
+        embeddings[emb_name] = embedding
+
+    net.bundle_embeddings = embeddings
+
+    if keys_failed_to_match:
+        logging.debug(f"Network {network_on_disk.filename} didn't match keys: {keys_failed_to_match}")
+
+    return net
+
+
+def purge_networks_from_memory():
+    while len(networks_in_memory) > shared.opts.lora_in_memory_limit and len(networks_in_memory) > 0:
+        name = next(iter(networks_in_memory))
+        networks_in_memory.pop(name, None)
+
+    devices.torch_gc()
+
+
+def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=None):
+    emb_db = sd_hijack.model_hijack.embedding_db
+    already_loaded = {}
+
+    for net in loaded_networks:
+        if net.name in names:
+            already_loaded[net.name] = net
+        for emb_name, embedding in net.bundle_embeddings.items():
+            if embedding.loaded:
+                embedding.loaded = None
+                emb_db.register_embedding_by_name(None, shared.sd_model, emb_name)
+
+    loaded_networks.clear()
+
+    networks_on_disk = [available_network_aliases.get(name, None) for name in names]
+    if any(x is None for x in networks_on_disk):
+        list_available_networks()
+
+        networks_on_disk = [available_network_aliases.get(name, None) for name in names]
+
+    failed_to_load_networks = []
+
+    for i, (network_on_disk, name) in enumerate(zip(networks_on_disk, names)):
+        net = already_loaded.get(name, None)
+
+        if network_on_disk is not None:
+            if net is None:
+                net = networks_in_memory.get(name)
+
+            if net is None or os.path.getmtime(network_on_disk.filename) > net.mtime:
+                try:
+                    net = load_network(name, network_on_disk)
+
+                    networks_in_memory.pop(name, None)
+                    networks_in_memory[name] = net
+                except Exception as e:
+                    errors.display(e, f"loading network {network_on_disk.filename}")
+                    continue
+
+            net.mentioned_name = name
+
+            network_on_disk.read_hash()
+
+        if net is None:
+            failed_to_load_networks.append(name)
+            logging.info(f"Couldn't find network with name {name}")
+            continue
+
+        net.te_multiplier = te_multipliers[i] if te_multipliers else 1.0
+        net.unet_multiplier = unet_multipliers[i] if unet_multipliers else 1.0
+        net.dyn_dim = dyn_dims[i] if dyn_dims else 1.0
+        loaded_networks.append(net)
+
+        for emb_name, embedding in net.bundle_embeddings.items():
+            if embedding.loaded is None and emb_name in emb_db.word_embeddings:
+                logger.warning(
+                    f'Skip bundle embedding: "{emb_name}"'
+                    ' as it was already loaded from embeddings folder'
+                )
+                continue
+
+            embedding.loaded = False
+            if emb_db.expected_shape == -1 or emb_db.expected_shape == embedding.shape:
+                embedding.loaded = True
+                emb_db.register_embedding(embedding, shared.sd_model)
+            else:
+                emb_db.skipped_embeddings[name] = embedding
+
+    if failed_to_load_networks:
+        sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
+
+    purge_networks_from_memory()
+
+
+def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
+    weights_backup = getattr(self, "network_weights_backup", None)
+    bias_backup = getattr(self, "network_bias_backup", None)
+
+    if weights_backup is None and bias_backup is None:
+        return
+
+    if weights_backup is not None:
+        if isinstance(self, torch.nn.MultiheadAttention):
+            self.in_proj_weight.copy_(weights_backup[0])
+            self.out_proj.weight.copy_(weights_backup[1])
+        else:
+            self.weight.copy_(weights_backup)
+
+    if bias_backup is not None:
+        if isinstance(self, torch.nn.MultiheadAttention):
+            self.out_proj.bias.copy_(bias_backup)
+        else:
+            self.bias.copy_(bias_backup)
+    else:
+        if isinstance(self, torch.nn.MultiheadAttention):
+            self.out_proj.bias = None
+        else:
+            self.bias = None
+
+
+def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
+    """
+    Applies the currently selected set of networks to the weights of torch layer self.
+    If weights already have this particular set of networks applied, does nothing.
+    If not, restores orginal weights from backup and alters weights according to networks.
+    """
+
+    network_layer_name = getattr(self, 'network_layer_name', None)
+    if network_layer_name is None:
+        return
+
+    current_names = getattr(self, "network_current_names", ())
+    wanted_names = tuple((x.name, x.te_multiplier, x.unet_multiplier, x.dyn_dim) for x in loaded_networks)
+
+    weights_backup = getattr(self, "network_weights_backup", None)
+    if weights_backup is None and wanted_names != ():
+        if current_names != ():
+            raise RuntimeError("no backup weights found and current weights are not unchanged")
+
+        if isinstance(self, torch.nn.MultiheadAttention):
+            weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
+        else:
+            weights_backup = self.weight.to(devices.cpu, copy=True)
+
+        self.network_weights_backup = weights_backup
+
+    bias_backup = getattr(self, "network_bias_backup", None)
+    if bias_backup is None:
+        if isinstance(self, torch.nn.MultiheadAttention) and self.out_proj.bias is not None:
+            bias_backup = self.out_proj.bias.to(devices.cpu, copy=True)
+        elif getattr(self, 'bias', None) is not None:
+            bias_backup = self.bias.to(devices.cpu, copy=True)
+        else:
+            bias_backup = None
+        self.network_bias_backup = bias_backup
+
+    if current_names != wanted_names:
+        network_restore_weights_from_backup(self)
+
+        for net in loaded_networks:
+            module = net.modules.get(network_layer_name, None)
+            if module is not None and hasattr(self, 'weight'):
+                try:
+                    with torch.no_grad():
+                        updown, ex_bias = module.calc_updown(self.weight)
+
+                        if len(self.weight.shape) == 4 and self.weight.shape[1] == 9:
+                            # inpainting model. zero pad updown to make channel[1]  4 to 9
+                            updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
+
+                        self.weight += updown
+                        if ex_bias is not None and hasattr(self, 'bias'):
+                            if self.bias is None:
+                                self.bias = torch.nn.Parameter(ex_bias)
+                            else:
+                                self.bias += ex_bias
+                except RuntimeError as e:
+                    logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+                    extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+                continue
+
+            module_q = net.modules.get(network_layer_name + "_q_proj", None)
+            module_k = net.modules.get(network_layer_name + "_k_proj", None)
+            module_v = net.modules.get(network_layer_name + "_v_proj", None)
+            module_out = net.modules.get(network_layer_name + "_out_proj", None)
+
+            if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
+                try:
+                    with torch.no_grad():
+                        updown_q, _ = module_q.calc_updown(self.in_proj_weight)
+                        updown_k, _ = module_k.calc_updown(self.in_proj_weight)
+                        updown_v, _ = module_v.calc_updown(self.in_proj_weight)
+                        updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
+                        updown_out, ex_bias = module_out.calc_updown(self.out_proj.weight)
+
+                        self.in_proj_weight += updown_qkv
+                        self.out_proj.weight += updown_out
+                    if ex_bias is not None:
+                        if self.out_proj.bias is None:
+                            self.out_proj.bias = torch.nn.Parameter(ex_bias)
+                        else:
+                            self.out_proj.bias += ex_bias
+
+                except RuntimeError as e:
+                    logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+                    extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+                continue
+
+            if module is None:
+                continue
+
+            logging.debug(f"Network {net.name} layer {network_layer_name}: couldn't find supported operation")
+            extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+        self.network_current_names = wanted_names
+
+
+def network_forward(module, input, original_forward):
+    """
+    Old way of applying Lora by executing operations during layer's forward.
+    Stacking many loras this way results in big performance degradation.
+    """
+
+    if len(loaded_networks) == 0:
+        return original_forward(module, input)
+
+    input = devices.cond_cast_unet(input)
+
+    network_restore_weights_from_backup(module)
+    network_reset_cached_weight(module)
+
+    y = original_forward(module, input)
+
+    network_layer_name = getattr(module, 'network_layer_name', None)
+    for lora in loaded_networks:
+        module = lora.modules.get(network_layer_name, None)
+        if module is None:
+            continue
+
+        y = module.forward(input, y)
+
+    return y
+
+
+def network_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
+    self.network_current_names = ()
+    self.network_weights_backup = None
+    self.network_bias_backup = None
+
+
+def network_Linear_forward(self, input):
+    if shared.opts.lora_functional:
+        return network_forward(self, input, originals.Linear_forward)
+
+    network_apply_weights(self)
+
+    return originals.Linear_forward(self, input)
+
+
+def network_Linear_load_state_dict(self, *args, **kwargs):
+    network_reset_cached_weight(self)
+
+    return originals.Linear_load_state_dict(self, *args, **kwargs)
+
+
+def network_Conv2d_forward(self, input):
+    if shared.opts.lora_functional:
+        return network_forward(self, input, originals.Conv2d_forward)
+
+    network_apply_weights(self)
+
+    return originals.Conv2d_forward(self, input)
+
+
+def network_Conv2d_load_state_dict(self, *args, **kwargs):
+    network_reset_cached_weight(self)
+
+    return originals.Conv2d_load_state_dict(self, *args, **kwargs)
+
+
+def network_GroupNorm_forward(self, input):
+    if shared.opts.lora_functional:
+        return network_forward(self, input, originals.GroupNorm_forward)
+
+    network_apply_weights(self)
+
+    return originals.GroupNorm_forward(self, input)
+
+
+def network_GroupNorm_load_state_dict(self, *args, **kwargs):
+    network_reset_cached_weight(self)
+
+    return originals.GroupNorm_load_state_dict(self, *args, **kwargs)
+
+
+def network_LayerNorm_forward(self, input):
+    if shared.opts.lora_functional:
+        return network_forward(self, input, originals.LayerNorm_forward)
+
+    network_apply_weights(self)
+
+    return originals.LayerNorm_forward(self, input)
+
+
+def network_LayerNorm_load_state_dict(self, *args, **kwargs):
+    network_reset_cached_weight(self)
+
+    return originals.LayerNorm_load_state_dict(self, *args, **kwargs)
+
+
+def network_MultiheadAttention_forward(self, *args, **kwargs):
+    network_apply_weights(self)
+
+    return originals.MultiheadAttention_forward(self, *args, **kwargs)
+
+
+def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
+    network_reset_cached_weight(self)
+
+    return originals.MultiheadAttention_load_state_dict(self, *args, **kwargs)
+
+
+def list_available_networks():
+    available_networks.clear()
+    available_network_aliases.clear()
+    forbidden_network_aliases.clear()
+    available_network_hash_lookup.clear()
+    forbidden_network_aliases.update({"none": 1, "Addams": 1})
+
+    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
+
+    candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
+    candidates += list(shared.walk_files(shared.cmd_opts.lyco_dir_backcompat, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
+    for filename in candidates:
+        if os.path.isdir(filename):
+            continue
+
+        name = os.path.splitext(os.path.basename(filename))[0]
+        try:
+            entry = network.NetworkOnDisk(name, filename)
+        except OSError:  # should catch FileNotFoundError and PermissionError etc.
+            errors.report(f"Failed to load network {name} from {filename}", exc_info=True)
+            continue
+
+        available_networks[name] = entry
+
+        if entry.alias in available_network_aliases:
+            forbidden_network_aliases[entry.alias.lower()] = 1
+
+        available_network_aliases[name] = entry
+        available_network_aliases[entry.alias] = entry
+
+
+re_network_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)")
+
+
+def infotext_pasted(infotext, params):
+    if "AddNet Module 1" in [x[1] for x in scripts.scripts_txt2img.infotext_fields]:
+        return  # if the other extension is active, it will handle those fields, no need to do anything
+
+    added = []
+
+    for k in params:
+        if not k.startswith("AddNet Model "):
+            continue
+
+        num = k[13:]
+
+        if params.get("AddNet Module " + num) != "LoRA":
+            continue
+
+        name = params.get("AddNet Model " + num)
+        if name is None:
+            continue
+
+        m = re_network_name.match(name)
+        if m:
+            name = m.group(1)
+
+        multiplier = params.get("AddNet Weight A " + num, "1.0")
+
+        added.append(f"<lora:{name}:{multiplier}>")
+
+    if added:
+        params["Prompt"] += "\n" + "".join(added)
+
+
+originals: lora_patches.LoraPatches = None
+
+extra_network_lora = None
+
+available_networks = {}
+available_network_aliases = {}
+loaded_networks = []
+loaded_bundle_embeddings = {}
+networks_in_memory = {}
+available_network_hash_lookup = {}
+forbidden_network_aliases = {}
+
+list_available_networks()

extensions-builtin/Lora/preload.py

@@ -4,3 +4,4 @@ from modules import paths
 
 def preload(parser):
     parser.add_argument("--lora-dir", type=str, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
+    parser.add_argument("--lyco-dir-backcompat", type=str, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))

extensions-builtin/Lora/scripts/lora_script.py

@@ -1,30 +1,99 @@
-import torch
+import re
 
-import lora
+import gradio as gr
+from fastapi import FastAPI
+
+import network
+import networks
+import lora  # noqa:F401
+import lora_patches
 import extra_networks_lora
 import ui_extra_networks_lora
-from modules import script_callbacks, ui_extra_networks, extra_networks
+from modules import script_callbacks, ui_extra_networks, extra_networks, shared
 
 
 def unload():
-    torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora
-    torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_lora
+    networks.originals.undo()
 
 
 def before_ui():
     ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
-    extra_networks.register_extra_network(extra_networks_lora.ExtraNetworkLora())
+
+    networks.extra_network_lora = extra_networks_lora.ExtraNetworkLora()
+    extra_networks.register_extra_network(networks.extra_network_lora)
+    extra_networks.register_extra_network_alias(networks.extra_network_lora, "lyco")
 
 
-if not hasattr(torch.nn, 'Linear_forward_before_lora'):
-    torch.nn.Linear_forward_before_lora = torch.nn.Linear.forward
+networks.originals = lora_patches.LoraPatches()
 
-if not hasattr(torch.nn, 'Conv2d_forward_before_lora'):
-    torch.nn.Conv2d_forward_before_lora = torch.nn.Conv2d.forward
-
-torch.nn.Linear.forward = lora.lora_Linear_forward
-torch.nn.Conv2d.forward = lora.lora_Conv2d_forward
-
-script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules)
+script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
 script_callbacks.on_script_unloaded(unload)
 script_callbacks.on_before_ui(before_ui)
+script_callbacks.on_infotext_pasted(networks.infotext_pasted)
+
+
+shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), {
+    "sd_lora": shared.OptionInfo("None", "Add network to prompt", gr.Dropdown, lambda: {"choices": ["None", *networks.available_networks]}, refresh=networks.list_available_networks),
+    "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to Lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
+    "lora_add_hashes_to_infotext": shared.OptionInfo(True, "Add Lora hashes to infotext"),
+    "lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
+    "lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
+    "lora_in_memory_limit": shared.OptionInfo(0, "Number of Lora networks to keep cached in memory", gr.Number, {"precision": 0}),
+}))
+
+
+shared.options_templates.update(shared.options_section(('compatibility', "Compatibility"), {
+    "lora_functional": shared.OptionInfo(False, "Lora/Networks: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
+}))
+
+
+def create_lora_json(obj: network.NetworkOnDisk):
+    return {
+        "name": obj.name,
+        "alias": obj.alias,
+        "path": obj.filename,
+        "metadata": obj.metadata,
+    }
+
+
+def api_networks(_: gr.Blocks, app: FastAPI):
+    @app.get("/sdapi/v1/loras")
+    async def get_loras():
+        return [create_lora_json(obj) for obj in networks.available_networks.values()]
+
+    @app.post("/sdapi/v1/refresh-loras")
+    async def refresh_loras():
+        return networks.list_available_networks()
+
+
+script_callbacks.on_app_started(api_networks)
+
+re_lora = re.compile("<lora:([^:]+):")
+
+
+def infotext_pasted(infotext, d):
+    hashes = d.get("Lora hashes")
+    if not hashes:
+        return
+
+    hashes = [x.strip().split(':', 1) for x in hashes.split(",")]
+    hashes = {x[0].strip().replace(",", ""): x[1].strip() for x in hashes}
+
+    def network_replacement(m):
+        alias = m.group(1)
+        shorthash = hashes.get(alias)
+        if shorthash is None:
+            return m.group(0)
+
+        network_on_disk = networks.available_network_hash_lookup.get(shorthash)
+        if network_on_disk is None:
+            return m.group(0)
+
+        return f'<lora:{network_on_disk.get_alias()}:'
+
+    d["Prompt"] = re.sub(re_lora, network_replacement, d["Prompt"])
+
+
+script_callbacks.on_infotext_pasted(infotext_pasted)
+
+shared.opts.onchange("lora_in_memory_limit", networks.purge_networks_from_memory)

extensions-builtin/Lora/ui_edit_user_metadata.py

@@ -0,0 +1,217 @@
+import datetime
+import html
+import random
+
+import gradio as gr
+import re
+
+from modules import ui_extra_networks_user_metadata
+
+
+def is_non_comma_tagset(tags):
+    average_tag_length = sum(len(x) for x in tags.keys()) / len(tags)
+
+    return average_tag_length >= 16
+
+
+re_word = re.compile(r"[-_\w']+")
+re_comma = re.compile(r" *, *")
+
+
+def build_tags(metadata):
+    tags = {}
+
+    for _, tags_dict in metadata.get("ss_tag_frequency", {}).items():
+        for tag, tag_count in tags_dict.items():
+            tag = tag.strip()
+            tags[tag] = tags.get(tag, 0) + int(tag_count)
+
+    if tags and is_non_comma_tagset(tags):
+        new_tags = {}
+
+        for text, text_count in tags.items():
+            for word in re.findall(re_word, text):
+                if len(word) < 3:
+                    continue
+
+                new_tags[word] = new_tags.get(word, 0) + text_count
+
+        tags = new_tags
+
+    ordered_tags = sorted(tags.keys(), key=tags.get, reverse=True)
+
+    return [(tag, tags[tag]) for tag in ordered_tags]
+
+
+class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor):
+    def __init__(self, ui, tabname, page):
+        super().__init__(ui, tabname, page)
+
+        self.select_sd_version = None
+
+        self.taginfo = None
+        self.edit_activation_text = None
+        self.slider_preferred_weight = None
+        self.edit_notes = None
+
+    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, notes):
+        user_metadata = self.get_user_metadata(name)
+        user_metadata["description"] = desc
+        user_metadata["sd version"] = sd_version
+        user_metadata["activation text"] = activation_text
+        user_metadata["preferred weight"] = preferred_weight
+        user_metadata["notes"] = notes
+
+        self.write_user_metadata(name, user_metadata)
+
+    def get_metadata_table(self, name):
+        table = super().get_metadata_table(name)
+        item = self.page.items.get(name, {})
+        metadata = item.get("metadata") or {}
+
+        keys = {
+            'ss_output_name': "Output name:",
+            'ss_sd_model_name': "Model:",
+            'ss_clip_skip': "Clip skip:",
+            'ss_network_module': "Kohya module:",
+        }
+
+        for key, label in keys.items():
+            value = metadata.get(key, None)
+            if value is not None and str(value) != "None":
+                table.append((label, html.escape(value)))
+
+        ss_training_started_at = metadata.get('ss_training_started_at')
+        if ss_training_started_at:
+            table.append(("Date trained:", datetime.datetime.utcfromtimestamp(float(ss_training_started_at)).strftime('%Y-%m-%d %H:%M')))
+
+        ss_bucket_info = metadata.get("ss_bucket_info")
+        if ss_bucket_info and "buckets" in ss_bucket_info:
+            resolutions = {}
+            for _, bucket in ss_bucket_info["buckets"].items():
+                resolution = bucket["resolution"]
+                resolution = f'{resolution[1]}x{resolution[0]}'
+
+                resolutions[resolution] = resolutions.get(resolution, 0) + int(bucket["count"])
+
+            resolutions_list = sorted(resolutions.keys(), key=resolutions.get, reverse=True)
+            resolutions_text = html.escape(", ".join(resolutions_list[0:4]))
+            if len(resolutions) > 4:
+                resolutions_text += ", ..."
+                resolutions_text = f"<span title='{html.escape(', '.join(resolutions_list))}'>{resolutions_text}</span>"
+
+            table.append(('Resolutions:' if len(resolutions_list) > 1 else 'Resolution:', resolutions_text))
+
+        image_count = 0
+        for _, params in metadata.get("ss_dataset_dirs", {}).items():
+            image_count += int(params.get("img_count", 0))
+
+        if image_count:
+            table.append(("Dataset size:", image_count))
+
+        return table
+
+    def put_values_into_components(self, name):
+        user_metadata = self.get_user_metadata(name)
+        values = super().put_values_into_components(name)
+
+        item = self.page.items.get(name, {})
+        metadata = item.get("metadata") or {}
+
+        tags = build_tags(metadata)
+        gradio_tags = [(tag, str(count)) for tag, count in tags[0:24]]
+
+        return [
+            *values[0:5],
+            item.get("sd_version", "Unknown"),
+            gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
+            user_metadata.get('activation text', ''),
+            float(user_metadata.get('preferred weight', 0.0)),
+            gr.update(visible=True if tags else False),
+            gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
+        ]
+
+    def generate_random_prompt(self, name):
+        item = self.page.items.get(name, {})
+        metadata = item.get("metadata") or {}
+        tags = build_tags(metadata)
+
+        return self.generate_random_prompt_from_tags(tags)
+
+    def generate_random_prompt_from_tags(self, tags):
+        max_count = None
+        res = []
+        for tag, count in tags:
+            if not max_count:
+                max_count = count
+
+            v = random.random() * max_count
+            if count > v:
+                res.append(tag)
+
+        return ", ".join(sorted(res))
+
+    def create_extra_default_items_in_left_column(self):
+
+        # this would be a lot better as gr.Radio but I can't make it work
+        self.select_sd_version = gr.Dropdown(['SD1', 'SD2', 'SDXL', 'Unknown'], value='Unknown', label='Stable Diffusion version', interactive=True)
+
+    def create_editor(self):
+        self.create_default_editor_elems()
+
+        self.taginfo = gr.HighlightedText(label="Training dataset tags")
+        self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
+        self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
+
+        with gr.Row() as row_random_prompt:
+            with gr.Column(scale=8):
+                random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
+
+            with gr.Column(scale=1, min_width=120):
+                generate_random_prompt = gr.Button('Generate', size="lg", scale=1)
+
+        self.edit_notes = gr.TextArea(label='Notes', lines=4)
+
+        generate_random_prompt.click(fn=self.generate_random_prompt, inputs=[self.edit_name_input], outputs=[random_prompt], show_progress=False)
+
+        def select_tag(activation_text, evt: gr.SelectData):
+            tag = evt.value[0]
+
+            words = re.split(re_comma, activation_text)
+            if tag in words:
+                words = [x for x in words if x != tag and x.strip()]
+                return ", ".join(words)
+
+            return activation_text + ", " + tag if activation_text else tag
+
+        self.taginfo.select(fn=select_tag, inputs=[self.edit_activation_text], outputs=[self.edit_activation_text], show_progress=False)
+
+        self.create_default_buttons()
+
+        viewed_components = [
+            self.edit_name,
+            self.edit_description,
+            self.html_filedata,
+            self.html_preview,
+            self.edit_notes,
+            self.select_sd_version,
+            self.taginfo,
+            self.edit_activation_text,
+            self.slider_preferred_weight,
+            row_random_prompt,
+            random_prompt,
+        ]
+
+        self.button_edit\
+            .click(fn=self.put_values_into_components, inputs=[self.edit_name_input], outputs=viewed_components)\
+            .then(fn=lambda: gr.update(visible=True), inputs=[], outputs=[self.box])
+
+        edited_components = [
+            self.edit_description,
+            self.select_sd_version,
+            self.edit_activation_text,
+            self.slider_preferred_weight,
+            self.edit_notes,
+        ]
+
+        self.setup_save_handler(self.button_save, self.save_lora_user_metadata, edited_components)

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -1,8 +1,11 @@
-import json
 import os
-import lora
+
+import network
+import networks
 
 from modules import shared, ui_extra_networks
+from modules.ui_extra_networks import quote_js
+from ui_edit_user_metadata import LoraUserMetadataEditor
 
 
 class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
@@ -10,27 +13,67 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         super().__init__('Lora')
 
     def refresh(self):
-        lora.list_available_loras()
+        networks.list_available_networks()
+
+    def create_item(self, name, index=None, enable_filter=True):
+        lora_on_disk = networks.available_networks.get(name)
 
-    def list_items(self):
-        for name, lora_on_disk in lora.available_loras.items():
         path, ext = os.path.splitext(lora_on_disk.filename)
-            previews = [path + ".png", path + ".preview.png"]
 
-            preview = None
-            for file in previews:
-                if os.path.isfile(file):
-                    preview = "./file=" + file.replace('\\', '/') + "?mtime=" + str(os.path.getmtime(file))
-                    break
+        alias = lora_on_disk.get_alias()
 
-            yield {
+        item = {
             "name": name,
-                "filename": path,
-                "preview": preview,
-                "prompt": json.dumps(f"<lora:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
-                "local_preview": path + ".png",
+            "filename": lora_on_disk.filename,
+            "shorthash": lora_on_disk.shorthash,
+            "preview": self.find_preview(path),
+            "description": self.find_description(path),
+            "search_term": self.search_terms_from_path(lora_on_disk.filename) + " " + (lora_on_disk.hash or ""),
+            "local_preview": f"{path}.{shared.opts.samples_format}",
+            "metadata": lora_on_disk.metadata,
+            "sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
+            "sd_version": lora_on_disk.sd_version.name,
         }
 
-    def allowed_directories_for_previews(self):
-        return [shared.cmd_opts.lora_dir]
+        self.read_user_metadata(item)
+        activation_text = item["user_metadata"].get("activation text")
+        preferred_weight = item["user_metadata"].get("preferred weight", 0.0)
+        item["prompt"] = quote_js(f"<lora:{alias}:") + " + " + (str(preferred_weight) if preferred_weight else "opts.extra_networks_default_multiplier") + " + " + quote_js(">")
 
+        if activation_text:
+            item["prompt"] += " + " + quote_js(" " + activation_text)
+
+        sd_version = item["user_metadata"].get("sd version")
+        if sd_version in network.SdVersion.__members__:
+            item["sd_version"] = sd_version
+            sd_version = network.SdVersion[sd_version]
+        else:
+            sd_version = lora_on_disk.sd_version
+
+        if shared.opts.lora_show_all or not enable_filter:
+            pass
+        elif sd_version == network.SdVersion.Unknown:
+            model_version = network.SdVersion.SDXL if shared.sd_model.is_sdxl else network.SdVersion.SD2 if shared.sd_model.is_sd2 else network.SdVersion.SD1
+            if model_version.name in shared.opts.lora_hide_unknown_for_versions:
+                return None
+        elif shared.sd_model.is_sdxl and sd_version != network.SdVersion.SDXL:
+            return None
+        elif shared.sd_model.is_sd2 and sd_version != network.SdVersion.SD2:
+            return None
+        elif shared.sd_model.is_sd1 and sd_version != network.SdVersion.SD1:
+            return None
+
+        return item
+
+    def list_items(self):
+        for index, name in enumerate(networks.available_networks):
+            item = self.create_item(name, index)
+
+            if item is not None:
+                yield item
+
+    def allowed_directories_for_previews(self):
+        return [shared.cmd_opts.lora_dir, shared.cmd_opts.lyco_dir_backcompat]
+
+    def create_user_metadata_editor(self, ui, tabname):
+        return LoraUserMetadataEditor(ui, tabname, self)

extensions-builtin/ScuNET/scripts/scunet_model.py

@@ -1,15 +1,16 @@
-import os.path
 import sys
-import traceback
 
 import PIL.Image
 import numpy as np
 import torch
-from basicsr.utils.download_util import load_file_from_url
+from tqdm import tqdm
 
 import modules.upscaler
-from modules import devices, modelloader
-from scunet_model_arch import SCUNet as net
+from modules import devices, modelloader, script_callbacks, errors
+from scunet_model_arch import SCUNet
+
+from modules.modelloader import load_file_from_url
+from modules.shared import opts
 
 
 class UpscalerScuNET(modules.upscaler.Upscaler):
@@ -25,7 +26,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         scalers = []
         add_model2 = True
         for file in model_paths:
-            if "http" in file:
+            if file.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
@@ -35,53 +36,109 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
                 scaler_data = modules.upscaler.UpscalerData(name, file, self, 4)
                 scalers.append(scaler_data)
             except Exception:
-                print(f"Error loading ScuNET model: {file}", file=sys.stderr)
-                print(traceback.format_exc(), file=sys.stderr)
+                errors.report(f"Error loading ScuNET model: {file}", exc_info=True)
         if add_model2:
             scaler_data2 = modules.upscaler.UpscalerData(self.model_name2, self.model_url2, self)
             scalers.append(scaler_data2)
         self.scalers = scalers
 
-    def do_upscale(self, img: PIL.Image, selected_file):
-        torch.cuda.empty_cache()
+    @staticmethod
+    @torch.no_grad()
+    def tiled_inference(img, model):
+        # test the image tile by tile
+        h, w = img.shape[2:]
+        tile = opts.SCUNET_tile
+        tile_overlap = opts.SCUNET_tile_overlap
+        if tile == 0:
+            return model(img)
 
+        device = devices.get_device_for('scunet')
+        assert tile % 8 == 0, "tile size should be a multiple of window_size"
+        sf = 1
+
+        stride = tile - tile_overlap
+        h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
+        w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
+        E = torch.zeros(1, 3, h * sf, w * sf, dtype=img.dtype, device=device)
+        W = torch.zeros_like(E, dtype=devices.dtype, device=device)
+
+        with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="ScuNET tiles") as pbar:
+            for h_idx in h_idx_list:
+
+                for w_idx in w_idx_list:
+
+                    in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
+
+                    out_patch = model(in_patch)
+                    out_patch_mask = torch.ones_like(out_patch)
+
+                    E[
+                        ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
+                    ].add_(out_patch)
+                    W[
+                        ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
+                    ].add_(out_patch_mask)
+                    pbar.update(1)
+        output = E.div_(W)
+
+        return output
+
+    def do_upscale(self, img: PIL.Image.Image, selected_file):
+
+        devices.torch_gc()
+
+        try:
             model = self.load_model(selected_file)
-        if model is None:
+        except Exception as e:
+            print(f"ScuNET: Unable to load model from {selected_file}: {e}", file=sys.stderr)
             return img
 
         device = devices.get_device_for('scunet')
-        img = np.array(img)
-        img = img[:, :, ::-1]
-        img = np.moveaxis(img, 2, 0) / 255
-        img = torch.from_numpy(img).float()
-        img = img.unsqueeze(0).to(device)
+        tile = opts.SCUNET_tile
+        h, w = img.height, img.width
+        np_img = np.array(img)
+        np_img = np_img[:, :, ::-1]  # RGB to BGR
+        np_img = np_img.transpose((2, 0, 1)) / 255  # HWC to CHW
+        torch_img = torch.from_numpy(np_img).float().unsqueeze(0).to(device)  # type: ignore
 
-        with torch.no_grad():
-            output = model(img)
-        output = output.squeeze().float().cpu().clamp_(0, 1).numpy()
-        output = 255. * np.moveaxis(output, 0, 2)
-        output = output.astype(np.uint8)
-        output = output[:, :, ::-1]
-        torch.cuda.empty_cache()
-        return PIL.Image.fromarray(output, 'RGB')
+        if tile > h or tile > w:
+            _img = torch.zeros(1, 3, max(h, tile), max(w, tile), dtype=torch_img.dtype, device=torch_img.device)
+            _img[:, :, :h, :w] = torch_img # pad image
+            torch_img = _img
+
+        torch_output = self.tiled_inference(torch_img, model).squeeze(0)
+        torch_output = torch_output[:, :h * 1, :w * 1] # remove padding, if any
+        np_output: np.ndarray = torch_output.float().cpu().clamp_(0, 1).numpy()
+        del torch_img, torch_output
+        devices.torch_gc()
+
+        output = np_output.transpose((1, 2, 0))  # CHW to HWC
+        output = output[:, :, ::-1]  # BGR to RGB
+        return PIL.Image.fromarray((output * 255).astype(np.uint8))
 
     def load_model(self, path: str):
         device = devices.get_device_for('scunet')
-        if "http" in path:
-            filename = load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="%s.pth" % self.name,
-                                          progress=True)
+        if path.startswith("http"):
+            # TODO: this doesn't use `path` at all?
+            filename = load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
         else:
             filename = path
-        if not os.path.exists(os.path.join(self.model_path, filename)) or filename is None:
-            print(f"ScuNET: Unable to load model from {filename}", file=sys.stderr)
-            return None
-
-        model = net(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
+        model = SCUNet(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
         model.load_state_dict(torch.load(filename), strict=True)
         model.eval()
-        for k, v in model.named_parameters():
+        for _, v in model.named_parameters():
             v.requires_grad = False
         model = model.to(device)
 
         return model
 
+
+def on_ui_settings():
+    import gradio as gr
+    from modules import shared
+
+    shared.opts.add_option("SCUNET_tile", shared.OptionInfo(256, "Tile size for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")).info("0 = no tiling"))
+    shared.opts.add_option("SCUNET_tile_overlap", shared.OptionInfo(8, "Tile overlap for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, section=('upscaling', "Upscaling")).info("Low values = visible seam"))
+
+
+script_callbacks.on_ui_settings(on_ui_settings)

extensions-builtin/ScuNET/scunet_model_arch.py

@@ -61,7 +61,9 @@ class WMSA(nn.Module):
         Returns:
             output: tensor shape [b h w c]
         """
-        if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2))
+        if self.type != 'W':
+            x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2))
+
         x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size)
         h_windows = x.size(1)
         w_windows = x.size(2)
@@ -85,8 +87,9 @@ class WMSA(nn.Module):
         output = self.linear(output)
         output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size)
 
-        if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2),
-                                                 dims=(1, 2))
+        if self.type != 'W':
+            output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2))
+
         return output
 
     def relative_embedding(self):

extensions-builtin/SwinIR/scripts/swinir_model.py

@@ -1,35 +1,35 @@
-import contextlib
-import os
+import sys
+import platform
 
 import numpy as np
 import torch
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
 from modules import modelloader, devices, script_callbacks, shared
-from modules.shared import cmd_opts, opts, state
-from swinir_model_arch import SwinIR as net
-from swinir_model_arch_v2 import Swin2SR as net2
+from modules.shared import opts, state
+from swinir_model_arch import SwinIR
+from swinir_model_arch_v2 import Swin2SR
 from modules.upscaler import Upscaler, UpscalerData
 
+SWINIR_MODEL_URL = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth"
 
 device_swinir = devices.get_device_for('swinir')
 
 
 class UpscalerSwinIR(Upscaler):
     def __init__(self, dirname):
+        self._cached_model = None           # keep the model when SWIN_torch_compile is on to prevent re-compile every runs
+        self._cached_model_config = None    # to clear '_cached_model' when changing model (v1/v2) or settings
         self.name = "SwinIR"
-        self.model_url = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0" \
-                         "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \
-                         "-L_x4_GAN.pth "
+        self.model_url = SWINIR_MODEL_URL
         self.model_name = "SwinIR 4x"
         self.user_path = dirname
         super().__init__()
         scalers = []
         model_files = self.find_models(ext_filter=[".pt", ".pth"])
         for model in model_files:
-            if "http" in model:
+            if model.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(model)
@@ -38,27 +38,39 @@ class UpscalerSwinIR(Upscaler):
         self.scalers = scalers
 
     def do_upscale(self, img, model_file):
+        use_compile = hasattr(opts, 'SWIN_torch_compile') and opts.SWIN_torch_compile \
+            and int(torch.__version__.split('.')[0]) >= 2 and platform.system() != "Windows"
+        current_config = (model_file, opts.SWIN_tile)
+
+        if use_compile and self._cached_model_config == current_config:
+            model = self._cached_model
+        else:
+            self._cached_model = None
+            try:
                 model = self.load_model(model_file)
-        if model is None:
+            except Exception as e:
+                print(f"Failed loading SwinIR model {model_file}: {e}", file=sys.stderr)
                 return img
             model = model.to(device_swinir, dtype=devices.dtype)
+            if use_compile:
+                model = torch.compile(model)
+                self._cached_model = model
+                self._cached_model_config = current_config
         img = upscale(img, model)
-        try:
-            torch.cuda.empty_cache()
-        except:
-            pass
+        devices.torch_gc()
         return img
 
     def load_model(self, path, scale=4):
-        if "http" in path:
-            dl_name = "%s%s" % (self.model_name.replace(" ", "_"), ".pth")
-            filename = load_file_from_url(url=path, model_dir=self.model_path, file_name=dl_name, progress=True)
+        if path.startswith("http"):
+            filename = modelloader.load_file_from_url(
+                url=path,
+                model_dir=self.model_download_path,
+                file_name=f"{self.model_name.replace(' ', '_')}.pth",
+            )
         else:
             filename = path
-        if filename is None or not os.path.exists(filename):
-            return None
         if filename.endswith(".v2.pth"):
-            model = net2(
+            model = Swin2SR(
                 upscale=scale,
                 in_chans=3,
                 img_size=64,
@@ -73,7 +85,7 @@ class UpscalerSwinIR(Upscaler):
             )
             params = None
         else:
-            model = net(
+            model = SwinIR(
                 upscale=scale,
                 in_chans=3,
                 img_size=64,
@@ -173,6 +185,8 @@ def on_ui_settings():
 
     shared.opts.add_option("SWIN_tile", shared.OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")))
     shared.opts.add_option("SWIN_tile_overlap", shared.OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}, section=('upscaling', "Upscaling")))
+    if int(torch.__version__.split('.')[0]) >= 2 and platform.system() != "Windows":    # torch.compile() require pytorch 2.0 or above, and not on Windows
+        shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
 
 
 script_callbacks.on_ui_settings(on_ui_settings)

extensions-builtin/SwinIR/swinir_model_arch.py

@@ -644,7 +644,7 @@ class SwinIR(nn.Module):
     """
 
     def __init__(self, img_size=64, patch_size=1, in_chans=3,
-                 embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
+                 embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
                  window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
                  drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                  norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
@@ -844,7 +844,7 @@ class SwinIR(nn.Module):
         H, W = self.patches_resolution
         flops += H * W * 3 * self.embed_dim * 9
         flops += self.patch_embed.flops()
-        for i, layer in enumerate(self.layers):
+        for layer in self.layers:
             flops += layer.flops()
         flops += H * W * 3 * self.embed_dim * self.embed_dim
         flops += self.upsample.flops()

extensions-builtin/SwinIR/swinir_model_arch_v2.py

@@ -74,7 +74,7 @@ class WindowAttention(nn.Module):
     """
 
     def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.,
-                 pretrained_window_size=[0, 0]):
+                 pretrained_window_size=(0, 0)):
 
         super().__init__()
         self.dim = dim
@@ -698,7 +698,7 @@ class Swin2SR(nn.Module):
     """
 
     def __init__(self, img_size=64, patch_size=1, in_chans=3,
-                 embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
+                 embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
                  window_size=7, mlp_ratio=4., qkv_bias=True,
                  drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                  norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
@@ -994,7 +994,7 @@ class Swin2SR(nn.Module):
         H, W = self.patches_resolution
         flops += H * W * 3 * self.embed_dim * 9
         flops += self.patch_embed.flops()
-        for i, layer in enumerate(self.layers):
+        for layer in self.layers:
             flops += layer.flops()
         flops += H * W * 3 * self.embed_dim * self.embed_dim
         flops += self.upsample.flops()

extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js

@@ -0,0 +1,962 @@
+onUiLoaded(async() => {
+    const elementIDs = {
+        img2imgTabs: "#mode_img2img .tab-nav",
+        inpaint: "#img2maskimg",
+        inpaintSketch: "#inpaint_sketch",
+        rangeGroup: "#img2img_column_size",
+        sketch: "#img2img_sketch"
+    };
+    const tabNameToElementId = {
+        "Inpaint sketch": elementIDs.inpaintSketch,
+        "Inpaint": elementIDs.inpaint,
+        "Sketch": elementIDs.sketch
+    };
+
+
+    // Helper functions
+    // Get active tab
+
+    /**
+     * Waits for an element to be present in the DOM.
+     */
+    const waitForElement = (id) => new Promise(resolve => {
+        const checkForElement = () => {
+            const element = document.querySelector(id);
+            if (element) return resolve(element);
+            setTimeout(checkForElement, 100);
+        };
+        checkForElement();
+    });
+
+    function getActiveTab(elements, all = false) {
+        const tabs = elements.img2imgTabs.querySelectorAll("button");
+
+        if (all) return tabs;
+
+        for (let tab of tabs) {
+            if (tab.classList.contains("selected")) {
+                return tab;
+            }
+        }
+    }
+
+    // Get tab ID
+    function getTabId(elements) {
+        const activeTab = getActiveTab(elements);
+        return tabNameToElementId[activeTab.innerText];
+    }
+
+    // Wait until opts loaded
+    async function waitForOpts() {
+        for (; ;) {
+            if (window.opts && Object.keys(window.opts).length) {
+                return window.opts;
+            }
+            await new Promise(resolve => setTimeout(resolve, 100));
+        }
+    }
+
+    // Detect whether the element has a horizontal scroll bar
+    function hasHorizontalScrollbar(element) {
+        return element.scrollWidth > element.clientWidth;
+    }
+
+    // Function for defining the "Ctrl", "Shift" and "Alt" keys
+    function isModifierKey(event, key) {
+        switch (key) {
+        case "Ctrl":
+            return event.ctrlKey;
+        case "Shift":
+            return event.shiftKey;
+        case "Alt":
+            return event.altKey;
+        default:
+            return false;
+        }
+    }
+
+    // Check if hotkey is valid
+    function isValidHotkey(value) {
+        const specialKeys = ["Ctrl", "Alt", "Shift", "Disable"];
+        return (
+            (typeof value === "string" &&
+                value.length === 1 &&
+                /[a-z]/i.test(value)) ||
+            specialKeys.includes(value)
+        );
+    }
+
+    // Normalize hotkey
+    function normalizeHotkey(hotkey) {
+        return hotkey.length === 1 ? "Key" + hotkey.toUpperCase() : hotkey;
+    }
+
+    // Format hotkey for display
+    function formatHotkeyForDisplay(hotkey) {
+        return hotkey.startsWith("Key") ? hotkey.slice(3) : hotkey;
+    }
+
+    // Create hotkey configuration with the provided options
+    function createHotkeyConfig(defaultHotkeysConfig, hotkeysConfigOpts) {
+        const result = {}; // Resulting hotkey configuration
+        const usedKeys = new Set(); // Set of used hotkeys
+
+        // Iterate through defaultHotkeysConfig keys
+        for (const key in defaultHotkeysConfig) {
+            const userValue = hotkeysConfigOpts[key]; // User-provided hotkey value
+            const defaultValue = defaultHotkeysConfig[key]; // Default hotkey value
+
+            // Apply appropriate value for undefined, boolean, or object userValue
+            if (
+                userValue === undefined ||
+                typeof userValue === "boolean" ||
+                typeof userValue === "object" ||
+                userValue === "disable"
+            ) {
+                result[key] =
+                    userValue === undefined ? defaultValue : userValue;
+            } else if (isValidHotkey(userValue)) {
+                const normalizedUserValue = normalizeHotkey(userValue);
+
+                // Check for conflicting hotkeys
+                if (!usedKeys.has(normalizedUserValue)) {
+                    usedKeys.add(normalizedUserValue);
+                    result[key] = normalizedUserValue;
+                } else {
+                    console.error(
+                        `Hotkey: ${formatHotkeyForDisplay(
+                            userValue
+                        )} for ${key} is repeated and conflicts with another hotkey. The default hotkey is used: ${formatHotkeyForDisplay(
+                            defaultValue
+                        )}`
+                    );
+                    result[key] = defaultValue;
+                }
+            } else {
+                console.error(
+                    `Hotkey: ${formatHotkeyForDisplay(
+                        userValue
+                    )} for ${key} is not valid. The default hotkey is used: ${formatHotkeyForDisplay(
+                        defaultValue
+                    )}`
+                );
+                result[key] = defaultValue;
+            }
+        }
+
+        return result;
+    }
+
+    // Disables functions in the config object based on the provided list of function names
+    function disableFunctions(config, disabledFunctions) {
+        // Bind the hasOwnProperty method to the functionMap object to avoid errors
+        const hasOwnProperty =
+            Object.prototype.hasOwnProperty.bind(functionMap);
+
+        // Loop through the disabledFunctions array and disable the corresponding functions in the config object
+        disabledFunctions.forEach(funcName => {
+            if (hasOwnProperty(funcName)) {
+                const key = functionMap[funcName];
+                config[key] = "disable";
+            }
+        });
+
+        // Return the updated config object
+        return config;
+    }
+
+    /**
+     * The restoreImgRedMask function displays a red mask around an image to indicate the aspect ratio.
+     * If the image display property is set to 'none', the mask breaks. To fix this, the function
+     * temporarily sets the display property to 'block' and then hides the mask again after 300 milliseconds
+     * to avoid breaking the canvas. Additionally, the function adjusts the mask to work correctly on
+     * very long images.
+     */
+    function restoreImgRedMask(elements) {
+        const mainTabId = getTabId(elements);
+
+        if (!mainTabId) return;
+
+        const mainTab = gradioApp().querySelector(mainTabId);
+        const img = mainTab.querySelector("img");
+        const imageARPreview = gradioApp().querySelector("#imageARPreview");
+
+        if (!img || !imageARPreview) return;
+
+        imageARPreview.style.transform = "";
+        if (parseFloat(mainTab.style.width) > 865) {
+            const transformString = mainTab.style.transform;
+            const scaleMatch = transformString.match(
+                /scale\(([-+]?[0-9]*\.?[0-9]+)\)/
+            );
+            let zoom = 1; // default zoom
+
+            if (scaleMatch && scaleMatch[1]) {
+                zoom = Number(scaleMatch[1]);
+            }
+
+            imageARPreview.style.transformOrigin = "0 0";
+            imageARPreview.style.transform = `scale(${zoom})`;
+        }
+
+        if (img.style.display !== "none") return;
+
+        img.style.display = "block";
+
+        setTimeout(() => {
+            img.style.display = "none";
+        }, 400);
+    }
+
+    const hotkeysConfigOpts = await waitForOpts();
+
+    // Default config
+    const defaultHotkeysConfig = {
+        canvas_hotkey_zoom: "Alt",
+        canvas_hotkey_adjust: "Ctrl",
+        canvas_hotkey_reset: "KeyR",
+        canvas_hotkey_fullscreen: "KeyS",
+        canvas_hotkey_move: "KeyF",
+        canvas_hotkey_overlap: "KeyO",
+        canvas_disabled_functions: [],
+        canvas_show_tooltip: true,
+        canvas_auto_expand: true,
+        canvas_blur_prompt: false,
+    };
+
+    const functionMap = {
+        "Zoom": "canvas_hotkey_zoom",
+        "Adjust brush size": "canvas_hotkey_adjust",
+        "Moving canvas": "canvas_hotkey_move",
+        "Fullscreen": "canvas_hotkey_fullscreen",
+        "Reset Zoom": "canvas_hotkey_reset",
+        "Overlap": "canvas_hotkey_overlap"
+    };
+
+    // Loading the configuration from opts
+    const preHotkeysConfig = createHotkeyConfig(
+        defaultHotkeysConfig,
+        hotkeysConfigOpts
+    );
+
+    // Disable functions that are not needed by the user
+    const hotkeysConfig = disableFunctions(
+        preHotkeysConfig,
+        preHotkeysConfig.canvas_disabled_functions
+    );
+
+    let isMoving = false;
+    let mouseX, mouseY;
+    let activeElement;
+
+    const elements = Object.fromEntries(
+        Object.keys(elementIDs).map(id => [
+            id,
+            gradioApp().querySelector(elementIDs[id])
+        ])
+    );
+    const elemData = {};
+
+    // Apply functionality to the range inputs. Restore redmask and correct for long images.
+    const rangeInputs = elements.rangeGroup ?
+        Array.from(elements.rangeGroup.querySelectorAll("input")) :
+        [
+            gradioApp().querySelector("#img2img_width input[type='range']"),
+            gradioApp().querySelector("#img2img_height input[type='range']")
+        ];
+
+    for (const input of rangeInputs) {
+        input?.addEventListener("input", () => restoreImgRedMask(elements));
+    }
+
+    function applyZoomAndPan(elemId, isExtension = true) {
+        const targetElement = gradioApp().querySelector(elemId);
+
+        if (!targetElement) {
+            console.log("Element not found");
+            return;
+        }
+
+        targetElement.style.transformOrigin = "0 0";
+
+        elemData[elemId] = {
+            zoom: 1,
+            panX: 0,
+            panY: 0
+        };
+        let fullScreenMode = false;
+
+        // Create tooltip
+        function createTooltip() {
+            const toolTipElemnt =
+                targetElement.querySelector(".image-container");
+            const tooltip = document.createElement("div");
+            tooltip.className = "canvas-tooltip";
+
+            // Creating an item of information
+            const info = document.createElement("i");
+            info.className = "canvas-tooltip-info";
+            info.textContent = "";
+
+            // Create a container for the contents of the tooltip
+            const tooltipContent = document.createElement("div");
+            tooltipContent.className = "canvas-tooltip-content";
+
+            // Define an array with hotkey information and their actions
+            const hotkeysInfo = [
+                {
+                    configKey: "canvas_hotkey_zoom",
+                    action: "Zoom canvas",
+                    keySuffix: " + wheel"
+                },
+                {
+                    configKey: "canvas_hotkey_adjust",
+                    action: "Adjust brush size",
+                    keySuffix: " + wheel"
+                },
+                {configKey: "canvas_hotkey_reset", action: "Reset zoom"},
+                {
+                    configKey: "canvas_hotkey_fullscreen",
+                    action: "Fullscreen mode"
+                },
+                {configKey: "canvas_hotkey_move", action: "Move canvas"},
+                {configKey: "canvas_hotkey_overlap", action: "Overlap"}
+            ];
+
+            // Create hotkeys array with disabled property based on the config values
+            const hotkeys = hotkeysInfo.map(info => {
+                const configValue = hotkeysConfig[info.configKey];
+                const key = info.keySuffix ?
+                    `${configValue}${info.keySuffix}` :
+                    configValue.charAt(configValue.length - 1);
+                return {
+                    key,
+                    action: info.action,
+                    disabled: configValue === "disable"
+                };
+            });
+
+            for (const hotkey of hotkeys) {
+                if (hotkey.disabled) {
+                    continue;
+                }
+
+                const p = document.createElement("p");
+                p.innerHTML = `<b>${hotkey.key}</b> - ${hotkey.action}`;
+                tooltipContent.appendChild(p);
+            }
+
+            // Add information and content elements to the tooltip element
+            tooltip.appendChild(info);
+            tooltip.appendChild(tooltipContent);
+
+            // Add a hint element to the target element
+            toolTipElemnt.appendChild(tooltip);
+        }
+
+        //Show tool tip if setting enable
+        if (hotkeysConfig.canvas_show_tooltip) {
+            createTooltip();
+        }
+
+        // In the course of research, it was found that the tag img is very harmful when zooming and creates white canvases. This hack allows you to almost never think about this problem, it has no effect on webui.
+        function fixCanvas() {
+            const activeTab = getActiveTab(elements).textContent.trim();
+
+            if (activeTab !== "img2img") {
+                const img = targetElement.querySelector(`${elemId} img`);
+
+                if (img && img.style.display !== "none") {
+                    img.style.display = "none";
+                    img.style.visibility = "hidden";
+                }
+            }
+        }
+
+        // Reset the zoom level and pan position of the target element to their initial values
+        function resetZoom() {
+            elemData[elemId] = {
+                zoomLevel: 1,
+                panX: 0,
+                panY: 0
+            };
+
+            if (isExtension) {
+                targetElement.style.overflow = "hidden";
+            }
+
+            targetElement.isZoomed = false;
+
+            fixCanvas();
+            targetElement.style.transform = `scale(${elemData[elemId].zoomLevel}) translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px)`;
+
+            const canvas = gradioApp().querySelector(
+                `${elemId} canvas[key="interface"]`
+            );
+
+            toggleOverlap("off");
+            fullScreenMode = false;
+
+            const closeBtn = targetElement.querySelector("button[aria-label='Remove Image']");
+            if (closeBtn) {
+                closeBtn.addEventListener("click", resetZoom);
+            }
+
+            if (canvas && isExtension) {
+                const parentElement = targetElement.closest('[id^="component-"]');
+                if (
+                    canvas &&
+                    parseFloat(canvas.style.width) > parentElement.offsetWidth &&
+                    parseFloat(targetElement.style.width) > parentElement.offsetWidth
+                ) {
+                    fitToElement();
+                    return;
+                }
+
+            }
+
+            if (
+                canvas &&
+                !isExtension &&
+                parseFloat(canvas.style.width) > 865 &&
+                parseFloat(targetElement.style.width) > 865
+            ) {
+                fitToElement();
+                return;
+            }
+
+            targetElement.style.width = "";
+        }
+
+        // Toggle the zIndex of the target element between two values, allowing it to overlap or be overlapped by other elements
+        function toggleOverlap(forced = "") {
+            const zIndex1 = "0";
+            const zIndex2 = "998";
+
+            targetElement.style.zIndex =
+                targetElement.style.zIndex !== zIndex2 ? zIndex2 : zIndex1;
+
+            if (forced === "off") {
+                targetElement.style.zIndex = zIndex1;
+            } else if (forced === "on") {
+                targetElement.style.zIndex = zIndex2;
+            }
+        }
+
+        // Adjust the brush size based on the deltaY value from a mouse wheel event
+        function adjustBrushSize(
+            elemId,
+            deltaY,
+            withoutValue = false,
+            percentage = 5
+        ) {
+            const input =
+                gradioApp().querySelector(
+                    `${elemId} input[aria-label='Brush radius']`
+                ) ||
+                gradioApp().querySelector(
+                    `${elemId} button[aria-label="Use brush"]`
+                );
+
+            if (input) {
+                input.click();
+                if (!withoutValue) {
+                    const maxValue =
+                        parseFloat(input.getAttribute("max")) || 100;
+                    const changeAmount = maxValue * (percentage / 100);
+                    const newValue =
+                        parseFloat(input.value) +
+                        (deltaY > 0 ? -changeAmount : changeAmount);
+                    input.value = Math.min(Math.max(newValue, 0), maxValue);
+                    input.dispatchEvent(new Event("change"));
+                }
+            }
+        }
+
+        // Reset zoom when uploading a new image
+        const fileInput = gradioApp().querySelector(
+            `${elemId} input[type="file"][accept="image/*"].svelte-116rqfv`
+        );
+        fileInput.addEventListener("click", resetZoom);
+
+        // Update the zoom level and pan position of the target element based on the values of the zoomLevel, panX and panY variables
+        function updateZoom(newZoomLevel, mouseX, mouseY) {
+            newZoomLevel = Math.max(0.1, Math.min(newZoomLevel, 15));
+
+            elemData[elemId].panX +=
+                mouseX - (mouseX * newZoomLevel) / elemData[elemId].zoomLevel;
+            elemData[elemId].panY +=
+                mouseY - (mouseY * newZoomLevel) / elemData[elemId].zoomLevel;
+
+            targetElement.style.transformOrigin = "0 0";
+            targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${newZoomLevel})`;
+
+            toggleOverlap("on");
+            if (isExtension) {
+                targetElement.style.overflow = "visible";
+            }
+
+            return newZoomLevel;
+        }
+
+        // Change the zoom level based on user interaction
+        function changeZoomLevel(operation, e) {
+            if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
+                e.preventDefault();
+
+                let zoomPosX, zoomPosY;
+                let delta = 0.2;
+                if (elemData[elemId].zoomLevel > 7) {
+                    delta = 0.9;
+                } else if (elemData[elemId].zoomLevel > 2) {
+                    delta = 0.6;
+                }
+
+                zoomPosX = e.clientX;
+                zoomPosY = e.clientY;
+
+                fullScreenMode = false;
+                elemData[elemId].zoomLevel = updateZoom(
+                    elemData[elemId].zoomLevel +
+                    (operation === "+" ? delta : -delta),
+                    zoomPosX - targetElement.getBoundingClientRect().left,
+                    zoomPosY - targetElement.getBoundingClientRect().top
+                );
+
+                targetElement.isZoomed = true;
+            }
+        }
+
+        /**
+         * This function fits the target element to the screen by calculating
+         * the required scale and offsets. It also updates the global variables
+         * zoomLevel, panX, and panY to reflect the new state.
+         */
+
+        function fitToElement() {
+            //Reset Zoom
+            targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`;
+
+            let parentElement;
+
+            if (isExtension) {
+                parentElement = targetElement.closest('[id^="component-"]');
+            } else {
+                parentElement = targetElement.parentElement;
+            }
+
+
+            // Get element and screen dimensions
+            const elementWidth = targetElement.offsetWidth;
+            const elementHeight = targetElement.offsetHeight;
+
+            const screenWidth = parentElement.clientWidth;
+            const screenHeight = parentElement.clientHeight;
+
+            // Get element's coordinates relative to the parent element
+            const elementRect = targetElement.getBoundingClientRect();
+            const parentRect = parentElement.getBoundingClientRect();
+            const elementX = elementRect.x - parentRect.x;
+
+            // Calculate scale and offsets
+            const scaleX = screenWidth / elementWidth;
+            const scaleY = screenHeight / elementHeight;
+            const scale = Math.min(scaleX, scaleY);
+
+            const transformOrigin =
+                window.getComputedStyle(targetElement).transformOrigin;
+            const [originX, originY] = transformOrigin.split(" ");
+            const originXValue = parseFloat(originX);
+            const originYValue = parseFloat(originY);
+
+            const offsetX =
+                (screenWidth - elementWidth * scale) / 2 -
+                originXValue * (1 - scale);
+            const offsetY =
+                (screenHeight - elementHeight * scale) / 2.5 -
+                originYValue * (1 - scale);
+
+            // Apply scale and offsets to the element
+            targetElement.style.transform = `translate(${offsetX}px, ${offsetY}px) scale(${scale})`;
+
+            // Update global variables
+            elemData[elemId].zoomLevel = scale;
+            elemData[elemId].panX = offsetX;
+            elemData[elemId].panY = offsetY;
+
+            fullScreenMode = false;
+            toggleOverlap("off");
+        }
+
+        /**
+         * This function fits the target element to the screen by calculating
+         * the required scale and offsets. It also updates the global variables
+         * zoomLevel, panX, and panY to reflect the new state.
+         */
+
+        // Fullscreen mode
+        function fitToScreen() {
+            const canvas = gradioApp().querySelector(
+                `${elemId} canvas[key="interface"]`
+            );
+
+            if (!canvas) return;
+
+            if (canvas.offsetWidth > 862 || isExtension) {
+                targetElement.style.width = (canvas.offsetWidth + 2) + "px";
+            }
+
+            if (isExtension) {
+                targetElement.style.overflow = "visible";
+            }
+
+            if (fullScreenMode) {
+                resetZoom();
+                fullScreenMode = false;
+                return;
+            }
+
+            //Reset Zoom
+            targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`;
+
+            // Get scrollbar width to right-align the image
+            const scrollbarWidth =
+                window.innerWidth - document.documentElement.clientWidth;
+
+            // Get element and screen dimensions
+            const elementWidth = targetElement.offsetWidth;
+            const elementHeight = targetElement.offsetHeight;
+            const screenWidth = window.innerWidth - scrollbarWidth;
+            const screenHeight = window.innerHeight;
+
+            // Get element's coordinates relative to the page
+            const elementRect = targetElement.getBoundingClientRect();
+            const elementY = elementRect.y;
+            const elementX = elementRect.x;
+
+            // Calculate scale and offsets
+            const scaleX = screenWidth / elementWidth;
+            const scaleY = screenHeight / elementHeight;
+            const scale = Math.min(scaleX, scaleY);
+
+            // Get the current transformOrigin
+            const computedStyle = window.getComputedStyle(targetElement);
+            const transformOrigin = computedStyle.transformOrigin;
+            const [originX, originY] = transformOrigin.split(" ");
+            const originXValue = parseFloat(originX);
+            const originYValue = parseFloat(originY);
+
+            // Calculate offsets with respect to the transformOrigin
+            const offsetX =
+                (screenWidth - elementWidth * scale) / 2 -
+                elementX -
+                originXValue * (1 - scale);
+            const offsetY =
+                (screenHeight - elementHeight * scale) / 2 -
+                elementY -
+                originYValue * (1 - scale);
+
+            // Apply scale and offsets to the element
+            targetElement.style.transform = `translate(${offsetX}px, ${offsetY}px) scale(${scale})`;
+
+            // Update global variables
+            elemData[elemId].zoomLevel = scale;
+            elemData[elemId].panX = offsetX;
+            elemData[elemId].panY = offsetY;
+
+            fullScreenMode = true;
+            toggleOverlap("on");
+        }
+
+        // Handle keydown events
+        function handleKeyDown(event) {
+            // Disable key locks to make pasting from the buffer work correctly
+            if ((event.ctrlKey && event.code === 'KeyV') || (event.ctrlKey && event.code === 'KeyC') || event.code === "F5") {
+                return;
+            }
+
+            // before activating shortcut, ensure user is not actively typing in an input field
+            if (!hotkeysConfig.canvas_blur_prompt) {
+                if (event.target.nodeName === 'TEXTAREA' || event.target.nodeName === 'INPUT') {
+                    return;
+                }
+            }
+
+
+            const hotkeyActions = {
+                [hotkeysConfig.canvas_hotkey_reset]: resetZoom,
+                [hotkeysConfig.canvas_hotkey_overlap]: toggleOverlap,
+                [hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen
+            };
+
+            const action = hotkeyActions[event.code];
+            if (action) {
+                event.preventDefault();
+                action(event);
+            }
+
+            if (
+                isModifierKey(event, hotkeysConfig.canvas_hotkey_zoom) ||
+                isModifierKey(event, hotkeysConfig.canvas_hotkey_adjust)
+            ) {
+                event.preventDefault();
+            }
+        }
+
+        // Get Mouse position
+        function getMousePosition(e) {
+            mouseX = e.offsetX;
+            mouseY = e.offsetY;
+        }
+
+        // Simulation of the function to put a long image into the screen.
+        // We detect if an image has a scroll bar or not, make a fullscreen to reveal the image, then reduce it to fit into the element.
+        // We hide the image and show it to the user when it is ready.
+
+        targetElement.isExpanded = false;
+        function autoExpand() {
+            const canvas = document.querySelector(`${elemId} canvas[key="interface"]`);
+            if (canvas) {
+                if (hasHorizontalScrollbar(targetElement) && targetElement.isExpanded === false) {
+                    targetElement.style.visibility = "hidden";
+                    setTimeout(() => {
+                        fitToScreen();
+                        resetZoom();
+                        targetElement.style.visibility = "visible";
+                        targetElement.isExpanded = true;
+                    }, 10);
+                }
+            }
+        }
+
+        targetElement.addEventListener("mousemove", getMousePosition);
+
+        //observers
+        // Creating an observer with a callback function to handle DOM changes
+        const observer = new MutationObserver((mutationsList, observer) => {
+            for (let mutation of mutationsList) {
+                // If the style attribute of the canvas has changed, by observation it happens only when the picture changes
+                if (mutation.type === 'attributes' && mutation.attributeName === 'style' &&
+                    mutation.target.tagName.toLowerCase() === 'canvas') {
+                    targetElement.isExpanded = false;
+                    setTimeout(resetZoom, 10);
+                }
+            }
+        });
+
+        // Apply auto expand if enabled
+        if (hotkeysConfig.canvas_auto_expand) {
+            targetElement.addEventListener("mousemove", autoExpand);
+            // Set up an observer to track attribute changes
+            observer.observe(targetElement, {attributes: true, childList: true, subtree: true});
+        }
+
+        // Handle events only inside the targetElement
+        let isKeyDownHandlerAttached = false;
+
+        function handleMouseMove() {
+            if (!isKeyDownHandlerAttached) {
+                document.addEventListener("keydown", handleKeyDown);
+                isKeyDownHandlerAttached = true;
+
+                activeElement = elemId;
+            }
+        }
+
+        function handleMouseLeave() {
+            if (isKeyDownHandlerAttached) {
+                document.removeEventListener("keydown", handleKeyDown);
+                isKeyDownHandlerAttached = false;
+
+                activeElement = null;
+            }
+        }
+
+        // Add mouse event handlers
+        targetElement.addEventListener("mousemove", handleMouseMove);
+        targetElement.addEventListener("mouseleave", handleMouseLeave);
+
+        // Reset zoom when click on another tab
+        elements.img2imgTabs.addEventListener("click", resetZoom);
+        elements.img2imgTabs.addEventListener("click", () => {
+            // targetElement.style.width = "";
+            if (parseInt(targetElement.style.width) > 865) {
+                setTimeout(fitToElement, 0);
+            }
+        });
+
+        targetElement.addEventListener("wheel", e => {
+            // change zoom level
+            const operation = e.deltaY > 0 ? "-" : "+";
+            changeZoomLevel(operation, e);
+
+            // Handle brush size adjustment with ctrl key pressed
+            if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
+                e.preventDefault();
+
+                // Increase or decrease brush size based on scroll direction
+                adjustBrushSize(elemId, e.deltaY);
+            }
+        });
+
+        // Handle the move event for pan functionality. Updates the panX and panY variables and applies the new transform to the target element.
+        function handleMoveKeyDown(e) {
+
+            // Disable key locks to make pasting from the buffer work correctly
+            if ((e.ctrlKey && e.code === 'KeyV') || (e.ctrlKey && event.code === 'KeyC') || e.code === "F5") {
+                return;
+            }
+
+            // before activating shortcut, ensure user is not actively typing in an input field
+            if (!hotkeysConfig.canvas_blur_prompt) {
+                if (e.target.nodeName === 'TEXTAREA' || e.target.nodeName === 'INPUT') {
+                    return;
+                }
+            }
+
+
+            if (e.code === hotkeysConfig.canvas_hotkey_move) {
+                if (!e.ctrlKey && !e.metaKey && isKeyDownHandlerAttached) {
+                    e.preventDefault();
+                    document.activeElement.blur();
+                    isMoving = true;
+                }
+            }
+        }
+
+        function handleMoveKeyUp(e) {
+            if (e.code === hotkeysConfig.canvas_hotkey_move) {
+                isMoving = false;
+            }
+        }
+
+        document.addEventListener("keydown", handleMoveKeyDown);
+        document.addEventListener("keyup", handleMoveKeyUp);
+
+        // Detect zoom level and update the pan speed.
+        function updatePanPosition(movementX, movementY) {
+            let panSpeed = 2;
+
+            if (elemData[elemId].zoomLevel > 8) {
+                panSpeed = 3.5;
+            }
+
+            elemData[elemId].panX += movementX * panSpeed;
+            elemData[elemId].panY += movementY * panSpeed;
+
+            // Delayed redraw of an element
+            requestAnimationFrame(() => {
+                targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${elemData[elemId].zoomLevel})`;
+                toggleOverlap("on");
+            });
+        }
+
+        function handleMoveByKey(e) {
+            if (isMoving && elemId === activeElement) {
+                updatePanPosition(e.movementX, e.movementY);
+                targetElement.style.pointerEvents = "none";
+
+                if (isExtension) {
+                    targetElement.style.overflow = "visible";
+                }
+
+            } else {
+                targetElement.style.pointerEvents = "auto";
+            }
+        }
+
+        // Prevents sticking to the mouse
+        window.onblur = function() {
+            isMoving = false;
+        };
+
+        // Checks for extension
+        function checkForOutBox() {
+            const parentElement = targetElement.closest('[id^="component-"]');
+            if (parentElement.offsetWidth < targetElement.offsetWidth && !targetElement.isExpanded) {
+                resetZoom();
+                targetElement.isExpanded = true;
+            }
+
+            if (parentElement.offsetWidth < targetElement.offsetWidth && elemData[elemId].zoomLevel == 1) {
+                resetZoom();
+            }
+
+            if (parentElement.offsetWidth < targetElement.offsetWidth && targetElement.offsetWidth * elemData[elemId].zoomLevel > parentElement.offsetWidth && elemData[elemId].zoomLevel < 1 && !targetElement.isZoomed) {
+                resetZoom();
+            }
+        }
+
+        if (isExtension) {
+            targetElement.addEventListener("mousemove", checkForOutBox);
+        }
+
+
+        window.addEventListener('resize', (e) => {
+            resetZoom();
+
+            if (isExtension) {
+                targetElement.isExpanded = false;
+                targetElement.isZoomed = false;
+            }
+        });
+
+        gradioApp().addEventListener("mousemove", handleMoveByKey);
+
+
+    }
+
+    applyZoomAndPan(elementIDs.sketch, false);
+    applyZoomAndPan(elementIDs.inpaint, false);
+    applyZoomAndPan(elementIDs.inpaintSketch, false);
+
+    // Make the function global so that other extensions can take advantage of this solution
+    const applyZoomAndPanIntegration = async(id, elementIDs) => {
+        const mainEl = document.querySelector(id);
+        if (id.toLocaleLowerCase() === "none") {
+            for (const elementID of elementIDs) {
+                const el = await waitForElement(elementID);
+                if (!el) break;
+                applyZoomAndPan(elementID);
+            }
+            return;
+        }
+
+        if (!mainEl) return;
+        mainEl.addEventListener("click", async() => {
+            for (const elementID of elementIDs) {
+                const el = await waitForElement(elementID);
+                if (!el) break;
+                applyZoomAndPan(elementID);
+            }
+        }, {once: true});
+    };
+
+    window.applyZoomAndPan = applyZoomAndPan; // Only 1 elements, argument elementID, for example applyZoomAndPan("#txt2img_controlnet_ControlNet_input_image")
+
+    window.applyZoomAndPanIntegration = applyZoomAndPanIntegration; // for any extension
+
+    /*
+        The function `applyZoomAndPanIntegration` takes two arguments:
+
+        1. `id`: A string identifier for the element to which zoom and pan functionality will be applied on click.
+        If the `id` value is "none", the functionality will be applied to all elements specified in the second argument without a click event.
+
+        2. `elementIDs`: An array of string identifiers for elements. Zoom and pan functionality will be applied to each of these elements on click of the element specified by the first argument.
+        If "none" is specified in the first argument, the functionality will be applied to each of these elements without a click event.
+
+        Example usage:
+        applyZoomAndPanIntegration("#txt2img_controlnet", ["#txt2img_controlnet_ControlNet_input_image"]);
+        In this example, zoom and pan functionality will be applied to the element with the identifier "txt2img_controlnet_ControlNet_input_image" upon clicking the element with the identifier "txt2img_controlnet".
+    */
+
+    // More examples
+    // Add integration with ControlNet txt2img One TAB
+    // applyZoomAndPanIntegration("#txt2img_controlnet", ["#txt2img_controlnet_ControlNet_input_image"]);
+
+    // Add integration with ControlNet txt2img Tabs
+    // applyZoomAndPanIntegration("#txt2img_controlnet",Array.from({ length: 10 }, (_, i) => `#txt2img_controlnet_ControlNet-${i}_input_image`));
+
+    // Add integration with Inpaint Anything
+    // applyZoomAndPanIntegration("None", ["#ia_sam_image", "#ia_sel_mask"]);
+});

extensions-builtin/canvas-zoom-and-pan/scripts/hotkey_config.py

@@ -0,0 +1,15 @@
+import gradio as gr
+from modules import shared
+
+shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas Hotkeys"), {
+    "canvas_hotkey_zoom": shared.OptionInfo("Alt", "Zoom canvas", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
+    "canvas_hotkey_adjust": shared.OptionInfo("Ctrl", "Adjust brush size", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
+    "canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas").info("To work correctly in firefox, turn off 'Automatically search the page text when typing' in the browser settings"),
+    "canvas_hotkey_fullscreen": shared.OptionInfo("S", "Fullscreen Mode, maximizes the picture so that it fits into the screen and stretches it to its full width "),
+    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas positon"),
+    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, neededs for testing"),
+    "canvas_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
+    "canvas_auto_expand": shared.OptionInfo(True, "Automatically expands an image that does not fit completely in the canvas area, similar to manually pressing the S and R buttons"),
+    "canvas_blur_prompt": shared.OptionInfo(False, "Take the focus off the prompt when working with a canvas"),
+    "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size", "Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
+}))

extensions-builtin/canvas-zoom-and-pan/style.css

@@ -0,0 +1,66 @@
+.canvas-tooltip-info {
+  position: absolute;
+  top: 10px;
+  left: 10px;
+  cursor: help;
+  background-color: rgba(0, 0, 0, 0.3);
+  width: 20px;
+  height: 20px;
+  border-radius: 50%;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  flex-direction: column; 
+
+  z-index: 100;
+}
+
+.canvas-tooltip-info::after {
+  content: '';
+  display: block;
+  width: 2px;
+  height: 7px;
+  background-color: white;
+  margin-top: 2px; 
+}
+
+.canvas-tooltip-info::before {
+  content: '';
+  display: block;
+  width: 2px;
+  height: 2px;
+  background-color: white;
+}
+
+.canvas-tooltip-content {
+  display: none;
+  background-color: #f9f9f9; 
+  color: #333; 
+  border: 1px solid #ddd;
+  padding: 15px; 
+  position: absolute;
+  top: 40px;
+  left: 10px;
+  width: 250px;
+  font-size: 16px;
+  opacity: 0;
+  border-radius: 8px;
+  box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2); 
+
+  z-index: 100;
+}
+
+.canvas-tooltip:hover .canvas-tooltip-content {
+  display: block;
+  animation: fadeIn 0.5s; 
+  opacity: 1;
+}
+
+@keyframes fadeIn {
+  from {opacity: 0;}
+  to {opacity: 1;}
+}
+
+.styler {
+  overflow:inherit !important;
+}

extensions-builtin/extra-options-section/scripts/extra_options_section.py

@@ -0,0 +1,74 @@
+import math
+
+import gradio as gr
+from modules import scripts, shared, ui_components, ui_settings, generation_parameters_copypaste
+from modules.ui_components import FormColumn
+
+
+class ExtraOptionsSection(scripts.Script):
+    section = "extra_options"
+
+    def __init__(self):
+        self.comps = None
+        self.setting_names = None
+
+    def title(self):
+        return "Extra options"
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def ui(self, is_img2img):
+        self.comps = []
+        self.setting_names = []
+        self.infotext_fields = []
+        extra_options = shared.opts.extra_options_img2img if is_img2img else shared.opts.extra_options_txt2img
+
+        mapping = {k: v for v, k in generation_parameters_copypaste.infotext_to_setting_name_mapping}
+
+        with gr.Blocks() as interface:
+            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
+
+                row_count = math.ceil(len(extra_options) / shared.opts.extra_options_cols)
+
+                for row in range(row_count):
+                    with gr.Row():
+                        for col in range(shared.opts.extra_options_cols):
+                            index = row * shared.opts.extra_options_cols + col
+                            if index >= len(extra_options):
+                                break
+
+                            setting_name = extra_options[index]
+
+                            with FormColumn():
+                                comp = ui_settings.create_setting_component(setting_name)
+
+                            self.comps.append(comp)
+                            self.setting_names.append(setting_name)
+
+                            setting_infotext_name = mapping.get(setting_name)
+                            if setting_infotext_name is not None:
+                                self.infotext_fields.append((comp, setting_infotext_name))
+
+        def get_settings_values():
+            res = [ui_settings.get_value_for_setting(key) for key in self.setting_names]
+            return res[0] if len(res) == 1 else res
+
+        interface.load(fn=get_settings_values, inputs=[], outputs=self.comps, queue=False, show_progress=False)
+
+        return self.comps
+
+    def before_process(self, p, *args):
+        for name, value in zip(self.setting_names, args):
+            if name not in p.override_settings:
+                p.override_settings[name] = value
+
+
+shared.options_templates.update(shared.options_section(('ui', "User interface"), {
+    "extra_options_txt2img": shared.OptionInfo([], "Options in main UI - txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
+    "extra_options_img2img": shared.OptionInfo([], "Options in main UI - img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
+    "extra_options_cols": shared.OptionInfo(1, "Options in main UI - number of columns", gr.Number, {"precision": 0}).needs_reload_ui(),
+    "extra_options_accordion": shared.OptionInfo(False, "Options in main UI - place into an accordion").needs_reload_ui()
+}))
+
+

extensions-builtin/mobile/javascript/mobile.js

@@ -0,0 +1,32 @@
+var isSetupForMobile = false;
+
+function isMobile() {
+    for (var tab of ["txt2img", "img2img"]) {
+        var imageTab = gradioApp().getElementById(tab + '_results');
+        if (imageTab && imageTab.offsetParent && imageTab.offsetLeft == 0) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+function reportWindowSize() {
+    var currentlyMobile = isMobile();
+    if (currentlyMobile == isSetupForMobile) return;
+    isSetupForMobile = currentlyMobile;
+
+    for (var tab of ["txt2img", "img2img"]) {
+        var button = gradioApp().getElementById(tab + '_generate_box');
+        var target = gradioApp().getElementById(currentlyMobile ? tab + '_results' : tab + '_actions_column');
+        target.insertBefore(button, target.firstElementChild);
+
+        gradioApp().getElementById(tab + '_results').classList.toggle('mobile', currentlyMobile);
+    }
+}
+
+window.addEventListener("resize", reportWindowSize);
+
+onUiLoaded(function() {
+    reportWindowSize();
+});

extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js

@@ -1,110 +1,42 @@
 // Stable Diffusion WebUI - Bracket checker
-// Version 1.0
-// By Hingashi no Florin/Bwin4L
+// By Hingashi no Florin/Bwin4L & @akx
 // Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs.
 // If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong.
 
-function checkBrackets(evt, textArea, counterElt) {
-  errorStringParen  = '(...) - Different number of opening and closing parentheses detected.\n';
-  errorStringSquare = '[...] - Different number of opening and closing square brackets detected.\n';
-  errorStringCurly  = '{...} - Different number of opening and closing curly brackets detected.\n';
+function checkBrackets(textArea, counterElt) {
+    var counts = {};
+    (textArea.value.match(/[(){}[\]]/g) || []).forEach(bracket => {
+        counts[bracket] = (counts[bracket] || 0) + 1;
+    });
+    var errors = [];
 
-  openBracketRegExp = /\(/g;
-  closeBracketRegExp = /\)/g;
-
-  openSquareBracketRegExp = /\[/g;
-  closeSquareBracketRegExp = /\]/g;
-
-  openCurlyBracketRegExp = /\{/g;
-  closeCurlyBracketRegExp = /\}/g;
-
-  totalOpenBracketMatches = 0;
-  totalCloseBracketMatches = 0;
-  totalOpenSquareBracketMatches = 0;
-  totalCloseSquareBracketMatches = 0;
-  totalOpenCurlyBracketMatches = 0;
-  totalCloseCurlyBracketMatches = 0;
-
-  openBracketMatches = textArea.value.match(openBracketRegExp);
-  if(openBracketMatches) {
-    totalOpenBracketMatches = openBracketMatches.length;
+    function checkPair(open, close, kind) {
+        if (counts[open] !== counts[close]) {
+            errors.push(
+                `${open}...${close} - Detected ${counts[open] || 0} opening and ${counts[close] || 0} closing ${kind}.`
+            );
+        }
     }
 
-  closeBracketMatches = textArea.value.match(closeBracketRegExp);
-  if(closeBracketMatches) {
-    totalCloseBracketMatches = closeBracketMatches.length;
-  }
-
-  openSquareBracketMatches = textArea.value.match(openSquareBracketRegExp);
-  if(openSquareBracketMatches) {
-    totalOpenSquareBracketMatches = openSquareBracketMatches.length;
-  }
-
-  closeSquareBracketMatches = textArea.value.match(closeSquareBracketRegExp);
-  if(closeSquareBracketMatches) {
-    totalCloseSquareBracketMatches = closeSquareBracketMatches.length;
-  }
-
-  openCurlyBracketMatches = textArea.value.match(openCurlyBracketRegExp);
-  if(openCurlyBracketMatches) {
-    totalOpenCurlyBracketMatches = openCurlyBracketMatches.length;
-  }
-
-  closeCurlyBracketMatches = textArea.value.match(closeCurlyBracketRegExp);
-  if(closeCurlyBracketMatches) {
-    totalCloseCurlyBracketMatches = closeCurlyBracketMatches.length;
-  }
-
-  if(totalOpenBracketMatches != totalCloseBracketMatches) {
-    if(!counterElt.title.includes(errorStringParen)) {
-      counterElt.title += errorStringParen;
-    }
-  } else {
-    counterElt.title = counterElt.title.replace(errorStringParen, '');
-  }
-
-  if(totalOpenSquareBracketMatches != totalCloseSquareBracketMatches) {
-    if(!counterElt.title.includes(errorStringSquare)) {
-      counterElt.title += errorStringSquare;
-    }
-  } else {
-    counterElt.title = counterElt.title.replace(errorStringSquare, '');
-  }
-
-  if(totalOpenCurlyBracketMatches != totalCloseCurlyBracketMatches) {
-    if(!counterElt.title.includes(errorStringCurly)) {
-      counterElt.title += errorStringCurly;
-    }
-  } else {
-    counterElt.title = counterElt.title.replace(errorStringCurly, '');
-  }
-
-  if(counterElt.title != '') {
-    counterElt.classList.add('error');
-  } else {
-    counterElt.classList.remove('error');
-  }
+    checkPair('(', ')', 'round brackets');
+    checkPair('[', ']', 'square brackets');
+    checkPair('{', '}', 'curly brackets');
+    counterElt.title = errors.join('\n');
+    counterElt.classList.toggle('error', errors.length !== 0);
 }
 
 function setupBracketChecking(id_prompt, id_counter) {
     var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
-    var counter = gradioApp().getElementById(id_counter)
-    textarea.addEventListener("input", function(evt){
-        checkBrackets(evt, textarea, counter)
-    });
+    var counter = gradioApp().getElementById(id_counter);
+
+    if (textarea && counter) {
+        textarea.addEventListener("input", () => checkBrackets(textarea, counter));
+    }
 }
 
-var shadowRootLoaded = setInterval(function() {
-    var shadowRoot = document.querySelector('gradio-app').shadowRoot;
-    if(! shadowRoot)  return false;
-
-    var shadowTextArea = shadowRoot.querySelectorAll('#txt2img_prompt > label > textarea');
-    if(shadowTextArea.length < 1)  return false;
-
-    clearInterval(shadowRootLoaded);
-
-    setupBracketChecking('txt2img_prompt', 'txt2img_token_counter')
-    setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter')
-    setupBracketChecking('img2img_prompt', 'imgimg_token_counter')
-    setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter')
-}, 1000);
+onUiLoaded(function() {
+    setupBracketChecking('txt2img_prompt', 'txt2img_token_counter');
+    setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter');
+    setupBracketChecking('img2img_prompt', 'img2img_token_counter');
+    setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter');
+});

html/extra-networks-card.html

@@ -1,11 +1,14 @@
-<div class='card' {preview_html} onclick={card_clicked}>
+<div class='card' style={style} onclick={card_clicked} data-name="{name}" {sort_keys}>
+	{background_image}
+	<div class="button-row">
+		{metadata_button}
+		{edit_button}
+	</div>
 	<div class='actions'>
 		<div class='additional'>
-			<ul>
-				<a href="#" title="replace preview image with currently selected in gallery" onclick={save_card_preview}>replace preview</a>
-			</ul>
+			<span style="display:none" class='search_term{search_only}'>{search_term}</span>
 		</div>
 		<span class='name'>{name}</span>
+		<span class='description'>{description}</span>
 	</div>
 </div>
-

html/footer.html

@@ -1,10 +1,12 @@
 <div>
-        <a href="/docs">API</a>
+        <a href="{api_docs}">API</a>
          • 
         <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Github</a>
          • 
         <a href="https://gradio.app">Gradio</a>
          • 
+        <a href="#" onclick="showProfile('./internal/profile-startup'); return false;">Startup profile</a>
+         • 
         <a href="/" onclick="javascript:gradioApp().getElementById('settings_restart_gradio').click(); return false">Reload UI</a>
 </div>
 <br />

html/image-update.svg

@@ -1,7 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
-  <filter id='shadow' color-interpolation-filters="sRGB">
-    <feDropShadow flood-color="black" dx="0" dy="0" flood-opacity="0.9" stdDeviation="0.5"/>
-    <feDropShadow flood-color="black" dx="0" dy="0" flood-opacity="0.9" stdDeviation="0.5"/>
-  </filter>
-  <path style="filter:url(#shadow);" fill="#FFFFFF" d="M13.18 19C13.35 19.72 13.64 20.39 14.03 21H5C3.9 21 3 20.11 3 19V5C3 3.9 3.9 3 5 3H19C20.11 3 21 3.9 21 5V11.18C20.5 11.07 20 11 19.5 11C19.33 11 19.17 11 19 11.03V5H5V19H13.18M11.21 15.83L9.25 13.47L6.5 17H13.03C13.14 15.54 13.73 14.22 14.64 13.19L13.96 12.29L11.21 15.83M19 13.5V12L16.75 14.25L19 16.5V15C20.38 15 21.5 16.12 21.5 17.5C21.5 17.9 21.41 18.28 21.24 18.62L22.33 19.71C22.75 19.08 23 18.32 23 17.5C23 15.29 21.21 13.5 19 13.5M19 20C17.62 20 16.5 18.88 16.5 17.5C16.5 17.1 16.59 16.72 16.76 16.38L15.67 15.29C15.25 15.92 15 16.68 15 17.5C15 19.71 16.79 21.5 19 21.5V23L21.25 20.75L19 18.5V20Z" />
-</svg>

html/licenses.html

@@ -417,3 +417,274 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
 </pre>
 
+<h2><a href="https://github.com/huggingface/diffusers/blob/c7da8fd23359a22d0df2741688b5b4f33c26df21/LICENSE">Scaled Dot Product Attention</a></h2>
+<small>Some small amounts of code borrowed and reworked.</small>
+<pre>
+   Copyright 2023 The HuggingFace Team. All rights reserved.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+      http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+</pre>
+
+<h2><a href="https://github.com/explosion/curated-transformers/blob/main/LICENSE">Curated transformers</a></h2>
+<small>The MPS workaround for nn.Linear on macOS 13.2.X is based on the MPS workaround for nn.Linear created by danieldk for Curated transformers</small>
+<pre>
+The MIT License (MIT)
+
+Copyright (C) 2021 ExplosionAI GmbH
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+</pre>
+
+<h2><a href="https://github.com/madebyollin/taesd/blob/main/LICENSE">TAESD</a></h2>
+<small>Tiny AutoEncoder for Stable Diffusion option for live previews</small>
+<pre>
+MIT License
+
+Copyright (c) 2023 Ollin Boer Bohan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+</pre>

javascript/aspectRatioOverlay.js

@@ -6,13 +6,13 @@ let arFrameTimeout = setTimeout(function(){},0);
 function dimensionChange(e, is_width, is_height) {
 
     if (is_width) {
-		currentWidth = e.target.value*1.0
+        currentWidth = e.target.value * 1.0;
     }
     if (is_height) {
-		currentHeight = e.target.value*1.0
+        currentHeight = e.target.value * 1.0;
     }
 
-	var inImg2img   = Boolean(gradioApp().querySelector("button.rounded-t-lg.border-gray-200"))
+    var inImg2img = gradioApp().querySelector("#tab_img2img").style.display == "block";
 
     if (!inImg2img) {
         return;
@@ -20,9 +20,9 @@ function dimensionChange(e, is_width, is_height){
 
     var targetElement = null;
 
-    var tabIndex = get_tab_index('mode_img2img')
+    var tabIndex = get_tab_index('mode_img2img');
     if (tabIndex == 0) { // img2img
-		targetElement = gradioApp().querySelector('div[data-testid=image] img');
+        targetElement = gradioApp().querySelector('#img2img_image div[data-testid=image] img');
     } else if (tabIndex == 1) { //Sketch
         targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
     } else if (tabIndex == 2) { // Inpaint
@@ -36,38 +36,33 @@ function dimensionChange(e, is_width, is_height){
 
         var arPreviewRect = gradioApp().querySelector('#imageARPreview');
         if (!arPreviewRect) {
-		    arPreviewRect = document.createElement('div')
+            arPreviewRect = document.createElement('div');
             arPreviewRect.id = "imageARPreview";
-		    gradioApp().getRootNode().appendChild(arPreviewRect)
+            gradioApp().appendChild(arPreviewRect);
         }
 
 
 
         var viewportOffset = targetElement.getBoundingClientRect();
 
-		viewportscale = Math.min(  targetElement.clientWidth/targetElement.naturalWidth, targetElement.clientHeight/targetElement.naturalHeight )
+        var viewportscale = Math.min(targetElement.clientWidth / targetElement.naturalWidth, targetElement.clientHeight / targetElement.naturalHeight);
 
-		scaledx = targetElement.naturalWidth*viewportscale
-		scaledy = targetElement.naturalHeight*viewportscale
+        var scaledx = targetElement.naturalWidth * viewportscale;
+        var scaledy = targetElement.naturalHeight * viewportscale;
 
-		cleintRectTop    = (viewportOffset.top+window.scrollY)
-		cleintRectLeft   = (viewportOffset.left+window.scrollX)
-		cleintRectCentreY = cleintRectTop  + (targetElement.clientHeight/2)
-		cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth/2)
+        var cleintRectTop = (viewportOffset.top + window.scrollY);
+        var cleintRectLeft = (viewportOffset.left + window.scrollX);
+        var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight / 2);
+        var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth / 2);
 
-		viewRectTop    = cleintRectCentreY-(scaledy/2)
-		viewRectLeft   = cleintRectCentreX-(scaledx/2)
-		arRectWidth  = scaledx
-		arRectHeight = scaledy
+        var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
+        var arscaledx = currentWidth * arscale;
+        var arscaledy = currentHeight * arscale;
 
-		arscale = Math.min(  arRectWidth/currentWidth, arRectHeight/currentHeight )
-		arscaledx = currentWidth*arscale
-		arscaledy = currentHeight*arscale
-
-		arRectTop    = cleintRectCentreY-(arscaledy/2)
-		arRectLeft   = cleintRectCentreX-(arscaledx/2)
-		arRectWidth  = arscaledx
-		arRectHeight = arscaledy
+        var arRectTop = cleintRectCentreY - (arscaledy / 2);
+        var arRectLeft = cleintRectCentreX - (arscaledx / 2);
+        var arRectWidth = arscaledx;
+        var arRectHeight = arscaledy;
 
         arPreviewRect.style.top = arRectTop + 'px';
         arPreviewRect.style.left = arRectLeft + 'px';
@@ -86,28 +81,33 @@ function dimensionChange(e, is_width, is_height){
 }
 
 
-onUiUpdate(function(){
+onAfterUiUpdate(function() {
     var arPreviewRect = gradioApp().querySelector('#imageARPreview');
     if (arPreviewRect) {
         arPreviewRect.style.display = 'none';
     }
-	var inImg2img   = Boolean(gradioApp().querySelector("button.rounded-t-lg.border-gray-200"))
+    var tabImg2img = gradioApp().querySelector("#tab_img2img");
+    if (tabImg2img) {
+        var inImg2img = tabImg2img.style.display == "block";
         if (inImg2img) {
             let inputs = gradioApp().querySelectorAll('input');
             inputs.forEach(function(e) {
-		    var is_width = e.parentElement.id == "img2img_width"
-		    var is_height = e.parentElement.id == "img2img_height"
+                var is_width = e.parentElement.id == "img2img_width";
+                var is_height = e.parentElement.id == "img2img_height";
 
                 if ((is_width || is_height) && !e.classList.contains('scrollwatch')) {
-				e.addEventListener('input', function(e){dimensionChange(e, is_width, is_height)} )
-				e.classList.add('scrollwatch')
+                    e.addEventListener('input', function(e) {
+                        dimensionChange(e, is_width, is_height);
+                    });
+                    e.classList.add('scrollwatch');
                 }
                 if (is_width) {
-				currentWidth = e.value*1.0
+                    currentWidth = e.value * 1.0;
                 }
                 if (is_height) {
-				currentHeight = e.value*1.0
-			}
-		})
+                    currentHeight = e.value * 1.0;
+                }
+            });
+        }
     }
 });

javascript/contextMenus.js

@@ -1,49 +1,48 @@
 
-contextMenuInit = function(){
+var contextMenuInit = function() {
     let eventListenerApplied = false;
     let menuSpecs = new Map();
 
     const uid = function() {
-    return Date.now().toString(36) + Math.random().toString(36).substr(2);
-  }
+        return Date.now().toString(36) + Math.random().toString(36).substring(2);
+    };
 
     function showContextMenu(event, element, menuEntries) {
         let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
         let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
 
-    let oldMenu = gradioApp().querySelector('#context-menu')
+        let oldMenu = gradioApp().querySelector('#context-menu');
         if (oldMenu) {
-      oldMenu.remove()
+            oldMenu.remove();
         }
 
-    let tabButton = uiCurrentTab
-    let baseStyle = window.getComputedStyle(tabButton)
+        let baseStyle = window.getComputedStyle(uiCurrentTab);
 
-    const contextMenu = document.createElement('nav')
-    contextMenu.id = "context-menu"
-    contextMenu.style.background = baseStyle.background
-    contextMenu.style.color = baseStyle.color
-    contextMenu.style.fontFamily = baseStyle.fontFamily
-    contextMenu.style.top = posy+'px'
-    contextMenu.style.left = posx+'px'
+        const contextMenu = document.createElement('nav');
+        contextMenu.id = "context-menu";
+        contextMenu.style.background = baseStyle.background;
+        contextMenu.style.color = baseStyle.color;
+        contextMenu.style.fontFamily = baseStyle.fontFamily;
+        contextMenu.style.top = posy + 'px';
+        contextMenu.style.left = posx + 'px';
 
 
 
-    const contextMenuList = document.createElement('ul')
+        const contextMenuList = document.createElement('ul');
         contextMenuList.className = 'context-menu-items';
         contextMenu.append(contextMenuList);
 
         menuEntries.forEach(function(entry) {
-      let contextMenuEntry = document.createElement('a')
-      contextMenuEntry.innerHTML = entry['name']
-      contextMenuEntry.addEventListener("click", function(e) {
+            let contextMenuEntry = document.createElement('a');
+            contextMenuEntry.innerHTML = entry['name'];
+            contextMenuEntry.addEventListener("click", function() {
                 entry['func']();
-      })
+            });
             contextMenuList.append(contextMenuEntry);
 
-    })
+        });
 
-    gradioApp().getRootNode().appendChild(contextMenu)
+        gradioApp().appendChild(contextMenu);
 
         let menuWidth = contextMenu.offsetWidth + 4;
         let menuHeight = contextMenu.offsetHeight + 4;
@@ -63,29 +62,35 @@ contextMenuInit = function(){
 
     function appendContextMenuOption(targetElementSelector, entryName, entryFunction) {
 
-    currentItems = menuSpecs.get(targetElementSelector)
+        var currentItems = menuSpecs.get(targetElementSelector);
 
         if (!currentItems) {
-      currentItems = []
+            currentItems = [];
             menuSpecs.set(targetElementSelector, currentItems);
         }
-    let newItem = {'id':targetElementSelector+'_'+uid(),
-                   'name':entryName,
-                   'func':entryFunction,
-                   'isNew':true}
+        let newItem = {
+            id: targetElementSelector + '_' + uid(),
+            name: entryName,
+            func: entryFunction,
+            isNew: true
+        };
 
-    currentItems.push(newItem)
-    return newItem['id']
+        currentItems.push(newItem);
+        return newItem['id'];
     }
 
     function removeContextMenuOption(uid) {
-    menuSpecs.forEach(function(v,k) {
-      let index = -1
-      v.forEach(function(e,ei){if(e['id']==uid){index=ei}})
+        menuSpecs.forEach(function(v) {
+            let index = -1;
+            v.forEach(function(e, ei) {
+                if (e['id'] == uid) {
+                    index = ei;
+                }
+            });
             if (index >= 0) {
                 v.splice(index, 1);
             }
-    })
+        });
     }
 
     function addContextMenuEventListener() {
@@ -93,40 +98,38 @@ contextMenuInit = function(){
             return;
         }
         gradioApp().addEventListener("click", function(e) {
-      let source = e.composedPath()[0]
-      if(source.id && source.id.indexOf('check_progress')>-1){
-        return
+            if (!e.isTrusted) {
+                return;
             }
 
-      let oldMenu = gradioApp().querySelector('#context-menu')
+            let oldMenu = gradioApp().querySelector('#context-menu');
             if (oldMenu) {
-        oldMenu.remove()
+                oldMenu.remove();
             }
         });
         gradioApp().addEventListener("contextmenu", function(e) {
-      let oldMenu = gradioApp().querySelector('#context-menu')
+            let oldMenu = gradioApp().querySelector('#context-menu');
             if (oldMenu) {
-        oldMenu.remove()
+                oldMenu.remove();
             }
             menuSpecs.forEach(function(v, k) {
                 if (e.composedPath()[0].matches(k)) {
-          showContextMenu(e,e.composedPath()[0],v)
-          e.preventDefault()
-          return
+                    showContextMenu(e, e.composedPath()[0], v);
+                    e.preventDefault();
                 }
-      })
             });
-    eventListenerApplied=true
+        });
+        eventListenerApplied = true;
 
     }
 
-  return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
-}
+    return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener];
+};
 
-initResponse = contextMenuInit();
-appendContextMenuOption     = initResponse[0];
-removeContextMenuOption     = initResponse[1];
-addContextMenuEventListener = initResponse[2];
+var initResponse = contextMenuInit();
+var appendContextMenuOption = initResponse[0];
+var removeContextMenuOption = initResponse[1];
+var addContextMenuEventListener = initResponse[2];
 
 (function() {
     //Start example Context Menu Items
@@ -136,42 +139,38 @@ addContextMenuEventListener = initResponse[2];
         if (!interruptbutton.offsetParent) {
             genbutton.click();
         }
-    clearInterval(window.generateOnRepeatInterval)
+        clearInterval(window.generateOnRepeatInterval);
         window.generateOnRepeatInterval = setInterval(function() {
             if (!interruptbutton.offsetParent) {
                 genbutton.click();
             }
         },
-    500)
-  }
+        500);
+    };
 
-  appendContextMenuOption('#txt2img_generate','Generate forever',function(){
+    let generateOnRepeat_txt2img = function() {
         generateOnRepeat('#txt2img_generate', '#txt2img_interrupt');
-  })
-  appendContextMenuOption('#img2img_generate','Generate forever',function(){
+    };
+
+    let generateOnRepeat_img2img = function() {
         generateOnRepeat('#img2img_generate', '#img2img_interrupt');
-  })
+    };
+
+    appendContextMenuOption('#txt2img_generate', 'Generate forever', generateOnRepeat_txt2img);
+    appendContextMenuOption('#txt2img_interrupt', 'Generate forever', generateOnRepeat_txt2img);
+    appendContextMenuOption('#img2img_generate', 'Generate forever', generateOnRepeat_img2img);
+    appendContextMenuOption('#img2img_interrupt', 'Generate forever', generateOnRepeat_img2img);
 
     let cancelGenerateForever = function() {
-    clearInterval(window.generateOnRepeatInterval)
-  }
+        clearInterval(window.generateOnRepeatInterval);
+    };
 
-  appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
-  appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever)
-  appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever)
-  appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever)
+    appendContextMenuOption('#txt2img_interrupt', 'Cancel generate forever', cancelGenerateForever);
+    appendContextMenuOption('#txt2img_generate', 'Cancel generate forever', cancelGenerateForever);
+    appendContextMenuOption('#img2img_interrupt', 'Cancel generate forever', cancelGenerateForever);
+    appendContextMenuOption('#img2img_generate', 'Cancel generate forever', cancelGenerateForever);
 
-  appendContextMenuOption('#roll','Roll three',
-    function(){
-      let rollbutton = get_uiCurrentTabContent().querySelector('#roll');
-      setTimeout(function(){rollbutton.click()},100)
-      setTimeout(function(){rollbutton.click()},200)
-      setTimeout(function(){rollbutton.click()},300)
-    }
-  )
 })();
 //End example Context Menu Items
 
-onUiUpdate(function(){
-  addContextMenuEventListener()
-});
+onAfterUiUpdate(addContextMenuEventListener);

javascript/dragdrop.js

@@ -39,7 +39,7 @@ function dropReplaceImage( imgWrap, files ) {
                     status: response.status,
                     statusText: response.statusText,
                     headers: response.headers
-                })
+                });
             }
             return response;
         };
@@ -48,12 +48,27 @@ function dropReplaceImage( imgWrap, files ) {
     }
 }
 
+function eventHasFiles(e) {
+    if (!e.dataTransfer || !e.dataTransfer.files) return false;
+    if (e.dataTransfer.files.length > 0) return true;
+    if (e.dataTransfer.items.length > 0 && e.dataTransfer.items[0].kind == "file") return true;
+
+    return false;
+}
+
+function dragDropTargetIsPrompt(target) {
+    if (target?.placeholder && target?.placeholder.indexOf("Prompt") >= 0) return true;
+    if (target?.parentNode?.parentNode?.className?.indexOf("prompt") > 0) return true;
+    return false;
+}
+
 window.document.addEventListener('dragover', e => {
     const target = e.composedPath()[0];
-    const imgWrap = target.closest('[data-testid="image"]');
-    if ( !imgWrap && target.placeholder && target.placeholder.indexOf("Prompt") == -1) {
-        return;
-    }
+    if (!eventHasFiles(e)) return;
+
+    var targetImage = target.closest('[data-testid="image"]');
+    if (!dragDropTargetIsPrompt(target) && !targetImage) return;
+
     e.stopPropagation();
     e.preventDefault();
     e.dataTransfer.dropEffect = 'copy';
@@ -61,17 +76,31 @@ window.document.addEventListener('dragover', e => {
 
 window.document.addEventListener('drop', e => {
     const target = e.composedPath()[0];
-    if (target.placeholder.indexOf("Prompt") == -1) {
-        return;
+    if (!eventHasFiles(e)) return;
+
+    if (dragDropTargetIsPrompt(target)) {
+        e.stopPropagation();
+        e.preventDefault();
+
+        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
+
+        const imgParent = gradioApp().getElementById(prompt_target);
+        const files = e.dataTransfer.files;
+        const fileInput = imgParent.querySelector('input[type="file"]');
+        if (fileInput) {
+            fileInput.files = files;
+            fileInput.dispatchEvent(new Event('change'));
         }
-    const imgWrap = target.closest('[data-testid="image"]');
-    if ( !imgWrap ) {
-        return;
     }
+
+    var targetImage = target.closest('[data-testid="image"]');
+    if (targetImage) {
         e.stopPropagation();
         e.preventDefault();
         const files = e.dataTransfer.files;
-    dropReplaceImage( imgWrap, files );
+        dropReplaceImage(targetImage, files);
+        return;
+    }
 });
 
 window.addEventListener('paste', e => {
@@ -81,17 +110,21 @@ window.addEventListener('paste', e => {
     }
 
     const visibleImageFields = [...gradioApp().querySelectorAll('[data-testid="image"]')]
-        .filter(el => uiElementIsVisible(el));
+        .filter(el => uiElementIsVisible(el))
+        .sort((a, b) => uiElementInSight(b) - uiElementInSight(a));
+
+
     if (!visibleImageFields.length) {
         return;
     }
 
     const firstFreeImageField = visibleImageFields
-        .filter(el => el.querySelector('input[type=file]'))?.[0];
+        .filter(el => !el.querySelector('img'))?.[0];
 
     dropReplaceImage(
         firstFreeImageField ?
             firstFreeImageField :
             visibleImageFields[visibleImageFields.length - 1]
-    , files );
+        , files
+    );
 });

javascript/edit-attention.js

@@ -1,10 +1,10 @@
 function keyupEditAttention(event) {
     let target = event.originalTarget || event.composedPath()[0];
-	if (!target.matches("[id*='_toprow'] textarea.gr-text-input[placeholder]")) return;
+    if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
     if (!(event.metaKey || event.ctrlKey)) return;
 
-	let isPlus = event.key == "ArrowUp"
-	let isMinus = event.key == "ArrowDown"
+    let isPlus = event.key == "ArrowUp";
+    let isMinus = event.key == "ArrowDown";
     if (!isPlus && !isMinus) return;
 
     let selectionStart = target.selectionStart;
@@ -18,22 +18,11 @@ function keyupEditAttention(event){
         const before = text.substring(0, selectionStart);
         let beforeParen = before.lastIndexOf(OPEN);
         if (beforeParen == -1) return false;
-		let beforeParenClose = before.lastIndexOf(CLOSE);
-		while (beforeParenClose !== -1 && beforeParenClose > beforeParen) {
-			beforeParen = before.lastIndexOf(OPEN, beforeParen - 1);
-			beforeParenClose = before.lastIndexOf(CLOSE, beforeParenClose - 1);
-		}
 
         // Find closing parenthesis around current cursor
         const after = text.substring(selectionStart);
         let afterParen = after.indexOf(CLOSE);
         if (afterParen == -1) return false;
-		let afterParenOpen = after.indexOf(OPEN);
-		while (afterParenOpen !== -1 && afterParen > afterParenOpen) {
-			afterParen = after.indexOf(CLOSE, afterParen + 1);
-			afterParenOpen = after.indexOf(OPEN, afterParenOpen + 1);
-		}
-		if (beforeParen === -1 || afterParen === -1) return false;
 
         // Set the selection to the text between the parenthesis
         const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
@@ -44,19 +33,42 @@ function keyupEditAttention(event){
         return true;
     }
 
-	// If the user hasn't selected anything, let's select their current parenthesis block
-    if(! selectCurrentParenthesisBlock('<', '>')){
-        selectCurrentParenthesisBlock('(', ')')
+    function selectCurrentWord() {
+        if (selectionStart !== selectionEnd) return false;
+        const whitespace_delimiters = {"Tab": "\t", "Carriage Return": "\r", "Line Feed": "\n"};
+        let delimiters = opts.keyedit_delimiters;
+
+        for (let i of opts.keyedit_delimiters_whitespace) {
+            delimiters += whitespace_delimiters[i];
+        }
+
+        // seek backward to find beginning
+        while (!delimiters.includes(text[selectionStart - 1]) && selectionStart > 0) {
+            selectionStart--;
+        }
+
+        // seek forward to find end
+        while (!delimiters.includes(text[selectionEnd]) && selectionEnd < text.length) {
+            selectionEnd++;
+        }
+
+        target.setSelectionRange(selectionStart, selectionEnd);
+        return true;
+    }
+
+    // If the user hasn't selected anything, let's select their current parenthesis block or word
+    if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) {
+        selectCurrentWord();
     }
 
     event.preventDefault();
 
-    closeCharacter = ')'
-    delta = opts.keyedit_precision_attention
+    var closeCharacter = ')';
+    var delta = opts.keyedit_precision_attention;
 
     if (selectionStart > 0 && text[selectionStart - 1] == '<') {
-        closeCharacter = '>'
-        delta = opts.keyedit_precision_extra
+        closeCharacter = '>';
+        delta = opts.keyedit_precision_extra;
     } else if (selectionStart == 0 || text[selectionStart - 1] != "(") {
 
         // do not include spaces at the end
@@ -64,7 +76,7 @@ function keyupEditAttention(event){
             selectionEnd -= 1;
         }
         if (selectionStart == selectionEnd) {
-            return
+            return;
         }
 
         text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
@@ -73,22 +85,29 @@ function keyupEditAttention(event){
         selectionEnd += 1;
     }
 
-	end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
-	weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end));
+    var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
+    var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + end));
     if (isNaN(weight)) return;
 
     weight += isPlus ? delta : -delta;
     weight = parseFloat(weight.toPrecision(12));
-	if(String(weight).length == 1) weight += ".0"
+    if (String(weight).length == 1) weight += ".0";
 
-	text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1);
+    if (closeCharacter == ')' && weight == 1) {
+        var endParenPos = text.substring(selectionEnd).indexOf(')');
+        text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + endParenPos + 1);
+        selectionStart--;
+        selectionEnd--;
+    } else {
+        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + end);
+    }
 
     target.focus();
     target.value = text;
     target.selectionStart = selectionStart;
     target.selectionEnd = selectionEnd;
 
-	updateInput(target)
+    updateInput(target);
 }
 
 addEventListener('keydown', (event) => {

javascript/edit-order.js

@@ -0,0 +1,41 @@
+/* alt+left/right moves text in prompt */
+
+function keyupEditOrder(event) {
+    if (!opts.keyedit_move) return;
+
+    let target = event.originalTarget || event.composedPath()[0];
+    if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
+    if (!event.altKey) return;
+
+    let isLeft = event.key == "ArrowLeft";
+    let isRight = event.key == "ArrowRight";
+    if (!isLeft && !isRight) return;
+    event.preventDefault();
+
+    let selectionStart = target.selectionStart;
+    let selectionEnd = target.selectionEnd;
+    let text = target.value;
+    let items = text.split(",");
+    let indexStart = (text.slice(0, selectionStart).match(/,/g) || []).length;
+    let indexEnd = (text.slice(0, selectionEnd).match(/,/g) || []).length;
+    let range = indexEnd - indexStart + 1;
+
+    if (isLeft && indexStart > 0) {
+        items.splice(indexStart - 1, 0, ...items.splice(indexStart, range));
+        target.value = items.join();
+        target.selectionStart = items.slice(0, indexStart - 1).join().length + (indexStart == 1 ? 0 : 1);
+        target.selectionEnd = items.slice(0, indexEnd).join().length;
+    } else if (isRight && indexEnd < items.length - 1) {
+        items.splice(indexStart + 1, 0, ...items.splice(indexStart, range));
+        target.value = items.join();
+        target.selectionStart = items.slice(0, indexStart + 1).join().length + 1;
+        target.selectionEnd = items.slice(0, indexEnd + 2).join().length;
+    }
+
+    event.preventDefault();
+    updateInput(target);
+}
+
+addEventListener('keydown', (event) => {
+    keyupEditOrder(event);
+});

javascript/extensions.js

@@ -1,35 +1,92 @@
 
-function extensions_apply(_, _){
-    disable = []
-    update = []
+function extensions_apply(_disabled_list, _update_list, disable_all) {
+    var disable = [];
+    var update = [];
+
     gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
-        if(x.name.startsWith("enable_") && ! x.checked)
-            disable.push(x.name.substr(7))
+        if (x.name.startsWith("enable_") && !x.checked) {
+            disable.push(x.name.substring(7));
+        }
 
-        if(x.name.startsWith("update_") && x.checked)
-            update.push(x.name.substr(7))
-    })
+        if (x.name.startsWith("update_") && x.checked) {
+            update.push(x.name.substring(7));
+        }
+    });
 
-    restart_reload()
+    restart_reload();
 
-    return [JSON.stringify(disable), JSON.stringify(update)]
+    return [JSON.stringify(disable), JSON.stringify(update), disable_all];
 }
 
 function extensions_check() {
-    gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x){
-        x.innerHTML = "Loading..."
-    })
+    var disable = [];
 
-    return []
+    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
+        if (x.name.startsWith("enable_") && !x.checked) {
+            disable.push(x.name.substring(7));
+        }
+    });
+
+    gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
+        x.innerHTML = "Loading...";
+    });
+
+
+    var id = randomId();
+    requestProgress(id, gradioApp().getElementById('extensions_installed_html'), null, function() {
+
+    });
+
+    return [id, JSON.stringify(disable)];
 }
 
 function install_extension_from_index(button, url) {
-    button.disabled = "disabled"
-    button.value = "Installing..."
+    button.disabled = "disabled";
+    button.value = "Installing...";
 
-    textarea = gradioApp().querySelector('#extension_to_install textarea')
-    textarea.value = url
-    updateInput(textarea)
+    var textarea = gradioApp().querySelector('#extension_to_install textarea');
+    textarea.value = url;
+    updateInput(textarea);
 
-    gradioApp().querySelector('#install_extension_button').click()
+    gradioApp().querySelector('#install_extension_button').click();
+}
+
+function config_state_confirm_restore(_, config_state_name, config_restore_type) {
+    if (config_state_name == "Current") {
+        return [false, config_state_name, config_restore_type];
+    }
+    let restored = "";
+    if (config_restore_type == "extensions") {
+        restored = "all saved extension versions";
+    } else if (config_restore_type == "webui") {
+        restored = "the webui version";
+    } else {
+        restored = "the webui version and all saved extension versions";
+    }
+    let confirmed = confirm("Are you sure you want to restore from this state?\nThis will reset " + restored + ".");
+    if (confirmed) {
+        restart_reload();
+        gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
+            x.innerHTML = "Loading...";
+        });
+    }
+    return [confirmed, config_state_name, config_restore_type];
+}
+
+function toggle_all_extensions(event) {
+    gradioApp().querySelectorAll('#extensions .extension_toggle').forEach(function(checkbox_el) {
+        checkbox_el.checked = event.target.checked;
+    });
+}
+
+function toggle_extension() {
+    let all_extensions_toggled = true;
+    for (const checkbox_el of gradioApp().querySelectorAll('#extensions .extension_toggle')) {
+        if (!checkbox_el.checked) {
+            all_extensions_toggled = false;
+            break;
+        }
+    }
+
+    gradioApp().querySelector('#extensions .all_extensions_toggle').checked = all_extensions_toggled;
 }

javascript/extraNetworks.js

@@ -1,38 +1,130 @@
-
-function setupExtraNetworksForTab(tabname){
-    gradioApp().querySelector('#'+tabname+'_extra_tabs').classList.add('extra-networks')
-
-    var tabs = gradioApp().querySelector('#'+tabname+'_extra_tabs > div')
-    var search = gradioApp().querySelector('#'+tabname+'_extra_search textarea')
-    var refresh = gradioApp().getElementById(tabname+'_extra_refresh')
-    var close = gradioApp().getElementById(tabname+'_extra_close')
-
-    search.classList.add('search')
-    tabs.appendChild(search)
-    tabs.appendChild(refresh)
-    tabs.appendChild(close)
-
-    search.addEventListener("input", function(evt){
-        searchTerm = search.value.toLowerCase()
-
-        gradioApp().querySelectorAll('#'+tabname+'_extra_tabs div.card').forEach(function(elem){
-            text = elem.querySelector('.name').textContent.toLowerCase()
-            elem.style.display = text.indexOf(searchTerm) == -1 ? "none" : ""
-        })
-    });
+function toggleCss(key, css, enable) {
+    var style = document.getElementById(key);
+    if (enable && !style) {
+        style = document.createElement('style');
+        style.id = key;
+        style.type = 'text/css';
+        document.head.appendChild(style);
+    }
+    if (style && !enable) {
+        document.head.removeChild(style);
+    }
+    if (style) {
+        style.innerHTML == '';
+        style.appendChild(document.createTextNode(css));
+    }
 }
 
+function setupExtraNetworksForTab(tabname) {
+    gradioApp().querySelector('#' + tabname + '_extra_tabs').classList.add('extra-networks');
+
+    var tabs = gradioApp().querySelector('#' + tabname + '_extra_tabs > div');
+    var searchDiv = gradioApp().getElementById(tabname + '_extra_search');
+    var search = searchDiv.querySelector('textarea');
+    var sort = gradioApp().getElementById(tabname + '_extra_sort');
+    var sortOrder = gradioApp().getElementById(tabname + '_extra_sortorder');
+    var refresh = gradioApp().getElementById(tabname + '_extra_refresh');
+    var showDirsDiv = gradioApp().getElementById(tabname + '_extra_show_dirs');
+    var showDirs = gradioApp().querySelector('#' + tabname + '_extra_show_dirs input');
+
+    sort.dataset.sortkey = 'sortDefault';
+    tabs.appendChild(searchDiv);
+    tabs.appendChild(sort);
+    tabs.appendChild(sortOrder);
+    tabs.appendChild(refresh);
+    tabs.appendChild(showDirsDiv);
+
+    var applyFilter = function() {
+        var searchTerm = search.value.toLowerCase();
+
+        gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
+            var searchOnly = elem.querySelector('.search_only');
+            var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase();
+
+            var visible = text.indexOf(searchTerm) != -1;
+
+            if (searchOnly && searchTerm.length < 4) {
+                visible = false;
+            }
+
+            elem.style.display = visible ? "" : "none";
+        });
+    };
+
+    var applySort = function() {
+        var reverse = sortOrder.classList.contains("sortReverse");
+        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim();
+        sortKey = sortKey ? "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1) : "";
+        var sortKeyStore = sortKey ? sortKey + (reverse ? "Reverse" : "") : "";
+        if (!sortKey || sortKeyStore == sort.dataset.sortkey) {
+            return;
+        }
+
+        sort.dataset.sortkey = sortKeyStore;
+
+        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
+        cards.forEach(function(card) {
+            card.originalParentElement = card.parentElement;
+        });
+        var sortedCards = Array.from(cards);
+        sortedCards.sort(function(cardA, cardB) {
+            var a = cardA.dataset[sortKey];
+            var b = cardB.dataset[sortKey];
+            if (!isNaN(a) && !isNaN(b)) {
+                return parseInt(a) - parseInt(b);
+            }
+
+            return (a < b ? -1 : (a > b ? 1 : 0));
+        });
+        if (reverse) {
+            sortedCards.reverse();
+        }
+        cards.forEach(function(card) {
+            card.remove();
+        });
+        sortedCards.forEach(function(card) {
+            card.originalParentElement.appendChild(card);
+        });
+    };
+
+    search.addEventListener("input", applyFilter);
+    applyFilter();
+    ["change", "blur", "click"].forEach(function(evt) {
+        sort.querySelector("input").addEventListener(evt, applySort);
+    });
+    sortOrder.addEventListener("click", function() {
+        sortOrder.classList.toggle("sortReverse");
+        applySort();
+    });
+
+    extraNetworksApplyFilter[tabname] = applyFilter;
+
+    var showDirsUpdate = function() {
+        var css = '#' + tabname + '_extra_tabs .extra-network-subdirs { display: none; }';
+        toggleCss(tabname + '_extra_show_dirs_style', css, !showDirs.checked);
+        localSet('extra-networks-show-dirs', showDirs.checked ? 1 : 0);
+    };
+    showDirs.checked = localGet('extra-networks-show-dirs', 1) == 1;
+    showDirs.addEventListener("change", showDirsUpdate);
+    showDirsUpdate();
+}
+
+function applyExtraNetworkFilter(tabname) {
+    setTimeout(extraNetworksApplyFilter[tabname], 1);
+}
+
+var extraNetworksApplyFilter = {};
 var activePromptTextarea = {};
 
 function setupExtraNetworks() {
-    setupExtraNetworksForTab('txt2img')
-    setupExtraNetworksForTab('img2img')
+    setupExtraNetworksForTab('txt2img');
+    setupExtraNetworksForTab('img2img');
 
     function registerPrompt(tabname, id) {
         var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
 
         if (!activePromptTextarea[tabname]) {
-            activePromptTextarea[tabname] = textarea
+            activePromptTextarea[tabname] = textarea;
         }
 
         textarea.addEventListener("focus", function() {
@@ -40,30 +132,221 @@ function setupExtraNetworks(){
         });
     }
 
-    registerPrompt('txt2img', 'txt2img_prompt')
-    registerPrompt('txt2img', 'txt2img_neg_prompt')
-    registerPrompt('img2img', 'img2img_prompt')
-    registerPrompt('img2img', 'img2img_neg_prompt')
+    registerPrompt('txt2img', 'txt2img_prompt');
+    registerPrompt('txt2img', 'txt2img_neg_prompt');
+    registerPrompt('img2img', 'img2img_prompt');
+    registerPrompt('img2img', 'img2img_neg_prompt');
 }
 
-onUiLoaded(setupExtraNetworks)
+onUiLoaded(setupExtraNetworks);
+
+var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
+var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
+
+function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
+    var m = text.match(re_extranet);
+    var replaced = false;
+    var newTextareaText;
+    if (m) {
+        var extraTextBeforeNet = opts.extra_networks_add_text_separator;
+        var extraTextAfterNet = m[2];
+        var partToSearch = m[1];
+        var foundAtPosition = -1;
+        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found, net, pos) {
+            m = found.match(re_extranet);
+            if (m[1] == partToSearch) {
+                replaced = true;
+                foundAtPosition = pos;
+                return "";
+            }
+            return found;
+        });
+
+        if (foundAtPosition >= 0) {
+            if (newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
+                newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
+            }
+            if (newTextareaText.substr(foundAtPosition - extraTextBeforeNet.length, extraTextBeforeNet.length) == extraTextBeforeNet) {
+                newTextareaText = newTextareaText.substr(0, foundAtPosition - extraTextBeforeNet.length) + newTextareaText.substr(foundAtPosition);
+            }
+        }
+    } else {
+        newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) {
+            if (found == text) {
+                replaced = true;
+                return "";
+            }
+            return found;
+        });
+    }
+
+    if (replaced) {
+        textarea.value = newTextareaText;
+        return true;
+    }
+
+    return false;
+}
 
 function cardClicked(tabname, textToAdd, allowNegativePrompt) {
-    var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea")
+    var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
 
-    textarea.value = textarea.value + " " + textToAdd
-    updateInput(textarea)
+    if (!tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)) {
+        textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd;
+    }
+
+    updateInput(textarea);
 }
 
 function saveCardPreview(event, tabname, filename) {
-    var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename  > label > textarea')
-    var button = gradioApp().getElementById(tabname + '_save_preview')
+    var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename  > label > textarea');
+    var button = gradioApp().getElementById(tabname + '_save_preview');
 
-    textarea.value = filename
-    updateInput(textarea)
+    textarea.value = filename;
+    updateInput(textarea);
 
-    button.click()
+    button.click();
 
-    event.stopPropagation()
-    event.preventDefault()
+    event.stopPropagation();
+    event.preventDefault();
+}
+
+function extraNetworksSearchButton(tabs_id, event) {
+    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > label > textarea');
+    var button = event.target;
+    var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
+
+    searchTextarea.value = text;
+    updateInput(searchTextarea);
+}
+
+var globalPopup = null;
+var globalPopupInner = null;
+
+function closePopup() {
+    if (!globalPopup) return;
+    globalPopup.style.display = "none";
+}
+
+function popup(contents) {
+    if (!globalPopup) {
+        globalPopup = document.createElement('div');
+        globalPopup.classList.add('global-popup');
+
+        var close = document.createElement('div');
+        close.classList.add('global-popup-close');
+        close.addEventListener("click", closePopup);
+        close.title = "Close";
+        globalPopup.appendChild(close);
+
+        globalPopupInner = document.createElement('div');
+        globalPopupInner.classList.add('global-popup-inner');
+        globalPopup.appendChild(globalPopupInner);
+
+        gradioApp().querySelector('.main').appendChild(globalPopup);
+    }
+
+    globalPopupInner.innerHTML = '';
+    globalPopupInner.appendChild(contents);
+
+    globalPopup.style.display = "flex";
+}
+
+var storedPopupIds = {};
+function popupId(id) {
+    if (!storedPopupIds[id]) {
+        storedPopupIds[id] = gradioApp().getElementById(id);
+    }
+
+    popup(storedPopupIds[id]);
+}
+
+function extraNetworksShowMetadata(text) {
+    var elem = document.createElement('pre');
+    elem.classList.add('popup-metadata');
+    elem.textContent = text;
+
+    popup(elem);
+}
+
+function requestGet(url, data, handler, errorHandler) {
+    var xhr = new XMLHttpRequest();
+    var args = Object.keys(data).map(function(k) {
+        return encodeURIComponent(k) + '=' + encodeURIComponent(data[k]);
+    }).join('&');
+    xhr.open("GET", url + "?" + args, true);
+
+    xhr.onreadystatechange = function() {
+        if (xhr.readyState === 4) {
+            if (xhr.status === 200) {
+                try {
+                    var js = JSON.parse(xhr.responseText);
+                    handler(js);
+                } catch (error) {
+                    console.error(error);
+                    errorHandler();
+                }
+            } else {
+                errorHandler();
+            }
+        }
+    };
+    var js = JSON.stringify(data);
+    xhr.send(js);
+}
+
+function extraNetworksRequestMetadata(event, extraPage, cardName) {
+    var showError = function() {
+        extraNetworksShowMetadata("there was an error getting metadata");
+    };
+
+    requestGet("./sd_extra_networks/metadata", {page: extraPage, item: cardName}, function(data) {
+        if (data && data.metadata) {
+            extraNetworksShowMetadata(data.metadata);
+        } else {
+            showError();
+        }
+    }, showError);
+
+    event.stopPropagation();
+}
+
+var extraPageUserMetadataEditors = {};
+
+function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
+    var id = tabname + '_' + extraPage + '_edit_user_metadata';
+
+    var editor = extraPageUserMetadataEditors[id];
+    if (!editor) {
+        editor = {};
+        editor.page = gradioApp().getElementById(id);
+        editor.nameTextarea = gradioApp().querySelector("#" + id + "_name" + ' textarea');
+        editor.button = gradioApp().querySelector("#" + id + "_button");
+        extraPageUserMetadataEditors[id] = editor;
+    }
+
+    editor.nameTextarea.value = cardName;
+    updateInput(editor.nameTextarea);
+
+    editor.button.click();
+
+    popup(editor.page);
+
+    event.stopPropagation();
+}
+
+function extraNetworksRefreshSingleCard(page, tabname, name) {
+    requestGet("./sd_extra_networks/get-single-card", {page: page, tabname: tabname, name: name}, function(data) {
+        if (data && data.html) {
+            var card = gradioApp().querySelector(`#${tabname}_${page.replace(" ", "_")}_cards > .card[data-name="${name}"]`);
+
+            var newDiv = document.createElement('DIV');
+            newDiv.innerHTML = data.html;
+            var newCard = newDiv.firstElementChild;
+
+            newCard.style.display = '';
+            card.parentElement.insertBefore(newCard, card);
+            card.parentElement.removeChild(card);
+        }
+    });
 }

javascript/generationParams.js

@@ -1,33 +1,35 @@
 // attaches listeners to the txt2img and img2img galleries to update displayed generation param text when the image changes
 
 let txt2img_gallery, img2img_gallery, modal = undefined;
-onUiUpdate(function(){
+onAfterUiUpdate(function() {
     if (!txt2img_gallery) {
-		txt2img_gallery = attachGalleryListeners("txt2img")
+        txt2img_gallery = attachGalleryListeners("txt2img");
     }
     if (!img2img_gallery) {
-		img2img_gallery = attachGalleryListeners("img2img")
+        img2img_gallery = attachGalleryListeners("img2img");
     }
     if (!modal) {
-		modal = gradioApp().getElementById('lightboxModal')
+        modal = gradioApp().getElementById('lightboxModal');
         modalObserver.observe(modal, {attributes: true, attributeFilter: ['style']});
     }
 });
 
 let modalObserver = new MutationObserver(function(mutations) {
     mutations.forEach(function(mutationRecord) {
-		let selectedTab = gradioApp().querySelector('#tabs div button.bg-white')?.innerText
-		if (mutationRecord.target.style.display === 'none' && selectedTab === 'txt2img' || selectedTab === 'img2img')
-			gradioApp().getElementById(selectedTab+"_generation_info_button").click()
+        let selectedTab = gradioApp().querySelector('#tabs div button.selected')?.innerText;
+        if (mutationRecord.target.style.display === 'none' && (selectedTab === 'txt2img' || selectedTab === 'img2img')) {
+            gradioApp().getElementById(selectedTab + "_generation_info_button")?.click();
+        }
     });
 });
 
 function attachGalleryListeners(tab_name) {
-	gallery = gradioApp().querySelector('#'+tab_name+'_gallery')
+    var gallery = gradioApp().querySelector('#' + tab_name + '_gallery');
     gallery?.addEventListener('click', () => gradioApp().getElementById(tab_name + "_generation_info_button").click());
     gallery?.addEventListener('keydown', (e) => {
-		if (e.keyCode == 37 || e.keyCode == 39) // left or right arrow
-			gradioApp().getElementById(tab_name+"_generation_info_button").click()
+        if (e.keyCode == 37 || e.keyCode == 39) { // left or right arrow
+            gradioApp().getElementById(tab_name + "_generation_info_button").click();
+        }
     });
     return gallery;
 }

javascript/hints.js

@@ -1,27 +1,29 @@
 // mouseover tooltips for various UI elements
 
-titles = {
+var titles = {
     "Sampling steps": "How many times to improve the generated image iteratively; higher values take longer; very low values can produce bad results",
     "Sampling method": "Which algorithm to use to produce the image",
     "GFPGAN": "Restore low quality faces using GFPGAN neural network",
     "Euler a": "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help",
     "DDIM": "Denoising Diffusion Implicit Models - best at inpainting",
+    "UniPC": "Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models",
     "DPM adaptive": "Ignores step count - uses a number of steps determined by the CFG and resolution",
 
-	"Batch count": "How many batches of images to create",
-	"Batch size": "How many image to create in a single batch",
+    "\u{1F4D0}": "Auto detect size from img2img",
+    "Batch count": "How many batches of images to create (has no impact on generation performance or VRAM usage)",
+    "Batch size": "How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)",
     "CFG Scale": "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results",
     "Seed": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result",
     "\u{1f3b2}\ufe0f": "Set seed to -1, which will cause a new random number to be used every time",
-    "\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomed",
+    "\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomized",
     "\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
     "\u{1f4c2}": "Open images output directory",
     "\u{1f4be}": "Save style",
-    "\U0001F5D1": "Clear prompt",
+    "\u{1f5d1}\ufe0f": "Clear prompt",
     "\u{1f4cb}": "Apply selected styles to current prompt",
     "\u{1f4d2}": "Paste available values into the field",
-    "\u{1f3b4}": "Show extra networks",
-
+    "\u{1f3b4}": "Show/hide extra networks",
+    "\u{1f300}": "Restore progress",
 
     "Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt",
     "SD upscale": "Upscale image normally, split result into tiles, improve each tile using img2img, merge whole image back",
@@ -39,7 +41,6 @@ titles = {
     "Inpaint at full resolution": "Upscale masked region to target resolution, do inpainting, downscale back and paste into original image",
 
     "Denoising strength": "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.",
-    "Denoising strength change factor": "In loopback mode, on each loop the denoising strength is multiplied by this value. <1 means decreasing variety so your sequence will converge on a fixed picture. >1 means increasing variety so your sequence will become more and more chaotic.",
 
     "Skip": "Stop processing current image and continue processing.",
     "Interrupt": "Stop processing images and return any results accumulated so far.",
@@ -50,7 +51,7 @@ titles = {
 
     "None": "Do not do anything special",
     "Prompt matrix": "Separate prompts into parts using vertical pipe character (|) and the script will create a picture for every combination of them (except for the first part, which will be present in all combinations)",
-    "X/Y plot": "Create a grid where images will have different parameters. Use inputs below to specify which parameters will be shared by columns and rows",
+    "X/Y/Z plot": "Create grid(s) where images will have different parameters. Use inputs below to specify which parameters will be shared by columns and rows",
     "Custom code": "Run Python code. Advanced user only. Must run program with --allow-code for this to work",
 
     "Prompt S/R": "Separate a list of words with commas, and the first word will be used as a keyword: script will search for this word in the prompt, and replace it with others",
@@ -66,12 +67,14 @@ titles = {
 
     "Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
 
-    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Images filename pattern": "Use tags like [seed] and [date] to define how filenames for images are chosen. Leave empty for default.",
+    "Directory name pattern": "Use tags like [seed] and [date] to define how subdirectories for images and grids are chosen. Leave empty for default.",
     "Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
 
-    "Loopback": "Process an image, use it as an input, repeat.",
-    "Loops": "How many times to repeat processing an image and using it as input for the next iteration",
+    "Loopback": "Performs img2img processing multiple times. Output images are used as input for the next loop.",
+    "Loops": "How many times to process an image. Each output is used as the input of the next loop. If set to 1, behavior will be as if this script were not used.",
+    "Final denoising strength": "The denoising strength for the final loop of each image in the batch.",
+    "Denoising strength curve": "The denoising curve controls the rate of denoising strength change each loop. Aggressive: Most of the change will happen towards the start of the loops. Linear: Change will be constant through all loops. Lazy: Most of the change will happen towards the end of the loops.",
 
     "Style 1": "Style to apply; styles have components for both positive and negative prompts and apply to both",
     "Style 2": "Style to apply; styles have components for both positive and negative prompts and apply to both",
@@ -81,10 +84,7 @@ titles = {
     "Checkpoint name": "Loads weights from checkpoint before making images. You can either use hash or a part of filename (as seen in settings) for checkpoint name. Recommended to use with Y axis for less switching.",
     "Inpainting conditioning mask strength": "Only applies to inpainting models. Determines how strongly to mask off the original image for inpainting and img2img. 1.0 means fully masked, which is the default behaviour. 0.0 means a fully unmasked conditioning. Lower values will help preserve the overall composition of the image, but will struggle with large changes.",
 
-    "vram": "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.\nTorch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.\nSys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%).",
-
     "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.",
-    "Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.",
 
     "Filename word regex": "This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.",
     "Filename join string": "This string will be used to join split words into a single line if the option above is enabled.",
@@ -108,39 +108,96 @@ titles = {
     "Upscale by": "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.",
     "Resize width to": "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.",
     "Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.",
-    "Multiplier for extra networks": "When adding extra network such as Hypernetwork or Lora to prompt, use this multiplier for it.",
     "Discard weights with matching name": "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.",
-    "Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order lsited."
-}
+    "Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order listed.",
+    "Negative Guidance minimum sigma": "Skip negative prompt for steps where image is already mostly denoised; the higher this value, the more skips there will be; provides increased performance in exchange for minor quality reduction."
+};
 
+function updateTooltip(element) {
+    if (element.title) return; // already has a title
 
-onUiUpdate(function(){
-	gradioApp().querySelectorAll('span, button, select, p').forEach(function(span){
-		tooltip = titles[span.textContent];
+    let text = element.textContent;
+    let tooltip = localization[titles[text]] || titles[text];
 
     if (!tooltip) {
-		    tooltip = titles[span.value];
+        let value = element.value;
+        if (value) tooltip = localization[titles[value]] || titles[value];
     }
 
     if (!tooltip) {
-			for (const c of span.classList) {
+        // Gradio dropdown options have `data-value`.
+        let dataValue = element.dataset.value;
+        if (dataValue) tooltip = localization[titles[dataValue]] || titles[dataValue];
+    }
+
+    if (!tooltip) {
+        for (const c of element.classList) {
             if (c in titles) {
-					tooltip = titles[c];
+                tooltip = localization[titles[c]] || titles[c];
                 break;
             }
         }
     }
 
     if (tooltip) {
-			span.title = tooltip;
+        element.title = tooltip;
     }
-	})
-
-	gradioApp().querySelectorAll('select').forEach(function(select){
-	    if (select.onchange != null) return;
-
-	    select.onchange = function(){
-            select.title = titles[select.value] || "";
 }
-	})
-})
+
+// Nodes to check for adding tooltips.
+const tooltipCheckNodes = new Set();
+// Timer for debouncing tooltip check.
+let tooltipCheckTimer = null;
+
+function processTooltipCheckNodes() {
+    for (const node of tooltipCheckNodes) {
+        updateTooltip(node);
+    }
+    tooltipCheckNodes.clear();
+}
+
+onUiUpdate(function(mutationRecords) {
+    for (const record of mutationRecords) {
+        if (record.type === "childList" && record.target.classList.contains("options")) {
+            // This smells like a Gradio dropdown menu having changed,
+            // so let's enqueue an update for the input element that shows the current value.
+            let wrap = record.target.parentNode;
+            let input = wrap?.querySelector("input");
+            if (input) {
+                input.title = ""; // So we'll even have a chance to update it.
+                tooltipCheckNodes.add(input);
+            }
+        }
+        for (const node of record.addedNodes) {
+            if (node.nodeType === Node.ELEMENT_NODE && !node.classList.contains("hide")) {
+                if (!node.title) {
+                    if (
+                        node.tagName === "SPAN" ||
+                        node.tagName === "BUTTON" ||
+                        node.tagName === "P" ||
+                        node.tagName === "INPUT" ||
+                        (node.tagName === "LI" && node.classList.contains("item")) // Gradio dropdown item
+                    ) {
+                        tooltipCheckNodes.add(node);
+                    }
+                }
+                node.querySelectorAll('span, button, p').forEach(n => tooltipCheckNodes.add(n));
+            }
+        }
+    }
+    if (tooltipCheckNodes.size) {
+        clearTimeout(tooltipCheckTimer);
+        tooltipCheckTimer = setTimeout(processTooltipCheckNodes, 1000);
+    }
+});
+
+onUiLoaded(function() {
+    for (var comp of window.gradio_config.components) {
+        if (comp.props.webui_tooltip && comp.props.elem_id) {
+            var elem = gradioApp().getElementById(comp.props.elem_id);
+            if (elem) {
+                elem.title = comp.props.webui_tooltip;
+            }
+        }
+    }
+});

javascript/hires_fix.js

@@ -1,22 +1,18 @@
 
-function setInactive(elem, inactive){
-    if(inactive){
-        elem.classList.add('inactive')
-    } else{
-        elem.classList.remove('inactive')
-    }
-}
-
 function onCalcResolutionHires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y) {
-    hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale')
-    hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x')
-    hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y')
-
-    gradioApp().getElementById('txt2img_hires_fix_row2').style.display = opts.use_old_hires_fix_width_height ? "none" : ""
-
-    setInactive(hrUpscaleBy, opts.use_old_hires_fix_width_height || hr_resize_x > 0 || hr_resize_y > 0)
-    setInactive(hrResizeX, opts.use_old_hires_fix_width_height || hr_resize_x == 0)
-    setInactive(hrResizeY, opts.use_old_hires_fix_width_height || hr_resize_y == 0)
-
-    return [enable, width, height, hr_scale, hr_resize_x, hr_resize_y]
+    function setInactive(elem, inactive) {
+        elem.classList.toggle('inactive', !!inactive);
+    }
+
+    var hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale');
+    var hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x');
+    var hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y');
+
+    gradioApp().getElementById('txt2img_hires_fix_row2').style.display = opts.use_old_hires_fix_width_height ? "none" : "";
+
+    setInactive(hrUpscaleBy, opts.use_old_hires_fix_width_height || hr_resize_x > 0 || hr_resize_y > 0);
+    setInactive(hrResizeX, opts.use_old_hires_fix_width_height || hr_resize_x == 0);
+    setInactive(hrResizeY, opts.use_old_hires_fix_width_height || hr_resize_y == 0);
+
+    return [enable, width, height, hr_scale, hr_resize_x, hr_resize_y];
 }

javascript/imageMaskFix.js

@@ -2,11 +2,9 @@
  * temporary fix for https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/668
  * @see https://github.com/gradio-app/gradio/issues/1721
  */
-window.addEventListener( 'resize', () => imageMaskResize());
 function imageMaskResize() {
     const canvases = gradioApp().querySelectorAll('#img2maskimg .touch-none canvas');
     if (!canvases.length) {
-    canvases_fixed = false;
         window.removeEventListener('resize', imageMaskResize);
         return;
     }
@@ -15,7 +13,7 @@ function imageMaskResize() {
     const previewImage = wrapper.previousElementSibling;
 
     if (!previewImage.complete) {
-        previewImage.addEventListener( 'load', () => imageMaskResize());
+        previewImage.addEventListener('load', imageMaskResize);
         return;
     }
 
@@ -24,7 +22,6 @@ function imageMaskResize() {
     const nw = previewImage.naturalWidth;
     const nh = previewImage.naturalHeight;
     const portrait = nh > nw;
-    const factor = portrait;
 
     const wW = Math.min(w, portrait ? h / nh * nw : w / nw * nw);
     const wH = Math.min(h, portrait ? h / nh * nh : w / nw * nh);
@@ -42,4 +39,5 @@ function imageMaskResize() {
     });
 }
 
- onUiUpdate(() => imageMaskResize());
+onAfterUiUpdate(imageMaskResize);
+window.addEventListener('resize', imageMaskResize);

javascript/imageParams.js

@@ -1,19 +0,0 @@
-window.onload = (function(){
-    window.addEventListener('drop', e => {
-        const target = e.composedPath()[0];
-        const idx = selected_gallery_index();
-        if (target.placeholder.indexOf("Prompt") == -1) return;
-
-        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
-
-        e.stopPropagation();
-        e.preventDefault();
-        const imgParent = gradioApp().getElementById(prompt_target);
-        const files = e.dataTransfer.files;
-        const fileInput = imgParent.querySelector('input[type="file"]');
-        if ( fileInput ) {
-            fileInput.files = files;
-            fileInput.dispatchEvent(new Event('change'));
-        }
-    });
-});

javascript/imageviewer.js

@@ -5,24 +5,24 @@ function closeModal() {
 
 function showModal(event) {
     const source = event.target || event.srcElement;
-    const modalImage = gradioApp().getElementById("modalImage")
-    const lb = gradioApp().getElementById("lightboxModal")
-    modalImage.src = source.src
+    const modalImage = gradioApp().getElementById("modalImage");
+    const lb = gradioApp().getElementById("lightboxModal");
+    modalImage.src = source.src;
     if (modalImage.style.display === 'none') {
         lb.style.setProperty('background-image', 'url(' + source.src + ')');
     }
-    lb.style.display = "block";
-    lb.focus()
+    lb.style.display = "flex";
+    lb.focus();
 
-    const tabTxt2Img = gradioApp().getElementById("tab_txt2img")
-    const tabImg2Img = gradioApp().getElementById("tab_img2img")
+    const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
+    const tabImg2Img = gradioApp().getElementById("tab_img2img");
     // show the save button in modal only on txt2img or img2img tabs
     if (tabTxt2Img.style.display != "none" || tabImg2Img.style.display != "none") {
-        gradioApp().getElementById("modal_save").style.display = "inline"
+        gradioApp().getElementById("modal_save").style.display = "inline";
     } else {
-        gradioApp().getElementById("modal_save").style.display = "none"
+        gradioApp().getElementById("modal_save").style.display = "none";
     }
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
 function negmod(n, m) {
@@ -30,105 +30,88 @@ function negmod(n, m) {
 }
 
 function updateOnBackgroundChange() {
-    const modalImage = gradioApp().getElementById("modalImage")
+    const modalImage = gradioApp().getElementById("modalImage");
     if (modalImage && modalImage.offsetParent) {
-        let allcurrentButtons = gradioApp().querySelectorAll(".gallery-item.transition-all.\\!ring-2")
-        let currentButton = null
-        allcurrentButtons.forEach(function(elem) {
-            if (elem.parentElement.offsetParent) {
-                currentButton = elem;
-            }
-        })
+        let currentButton = selected_gallery_button();
 
         if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
             modalImage.src = currentButton.children[0].src;
             if (modalImage.style.display === 'none') {
-                modal.style.setProperty('background-image', `url(${modalImage.src})`)
+                const modal = gradioApp().getElementById("lightboxModal");
+                modal.style.setProperty('background-image', `url(${modalImage.src})`);
             }
         }
     }
 }
 
 function modalImageSwitch(offset) {
-    var allgalleryButtons = gradioApp().querySelectorAll(".gallery-item.transition-all")
-    var galleryButtons = []
-    allgalleryButtons.forEach(function(elem) {
-        if (elem.parentElement.offsetParent) {
-            galleryButtons.push(elem);
-        }
-    })
+    var galleryButtons = all_gallery_buttons();
 
     if (galleryButtons.length > 1) {
-        var allcurrentButtons = gradioApp().querySelectorAll(".gallery-item.transition-all.\\!ring-2")
-        var currentButton = null
-        allcurrentButtons.forEach(function(elem) {
-            if (elem.parentElement.offsetParent) {
-                currentButton = elem;
-            }
-        })
+        var currentButton = selected_gallery_button();
 
-        var result = -1
+        var result = -1;
         galleryButtons.forEach(function(v, i) {
             if (v == currentButton) {
-                result = i
+                result = i;
             }
-        })
+        });
 
         if (result != -1) {
-            nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)]
-            nextButton.click()
+            var nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)];
+            nextButton.click();
             const modalImage = gradioApp().getElementById("modalImage");
             const modal = gradioApp().getElementById("lightboxModal");
             modalImage.src = nextButton.children[0].src;
             if (modalImage.style.display === 'none') {
-                modal.style.setProperty('background-image', `url(${modalImage.src})`)
+                modal.style.setProperty('background-image', `url(${modalImage.src})`);
             }
             setTimeout(function() {
-                modal.focus()
-            }, 10)
+                modal.focus();
+            }, 10);
         }
     }
 }
 
 function saveImage() {
-    const tabTxt2Img = gradioApp().getElementById("tab_txt2img")
-    const tabImg2Img = gradioApp().getElementById("tab_img2img")
-    const saveTxt2Img = "save_txt2img"
-    const saveImg2Img = "save_img2img"
+    const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
+    const tabImg2Img = gradioApp().getElementById("tab_img2img");
+    const saveTxt2Img = "save_txt2img";
+    const saveImg2Img = "save_img2img";
     if (tabTxt2Img.style.display != "none") {
-        gradioApp().getElementById(saveTxt2Img).click()
+        gradioApp().getElementById(saveTxt2Img).click();
     } else if (tabImg2Img.style.display != "none") {
-        gradioApp().getElementById(saveImg2Img).click()
+        gradioApp().getElementById(saveImg2Img).click();
     } else {
-        console.error("missing implementation for saving modal of this type")
+        console.error("missing implementation for saving modal of this type");
     }
 }
 
 function modalSaveImage(event) {
-    saveImage()
-    event.stopPropagation()
+    saveImage();
+    event.stopPropagation();
 }
 
 function modalNextImage(event) {
-    modalImageSwitch(1)
-    event.stopPropagation()
+    modalImageSwitch(1);
+    event.stopPropagation();
 }
 
 function modalPrevImage(event) {
-    modalImageSwitch(-1)
-    event.stopPropagation()
+    modalImageSwitch(-1);
+    event.stopPropagation();
 }
 
 function modalKeyHandler(event) {
     switch (event.key) {
     case "s":
-            saveImage()
+        saveImage();
         break;
     case "ArrowLeft":
-            modalPrevImage(event)
+        modalPrevImage(event);
         break;
     case "ArrowRight":
-            modalNextImage(event)
+        modalNextImage(event);
         break;
     case "Escape":
         closeModal();
@@ -136,51 +119,45 @@ function modalKeyHandler(event) {
     }
 }
 
-function showGalleryImage() {
-    setTimeout(function() {
-        fullImg_preview = gradioApp().querySelectorAll('img.w-full.object-contain')
-
-        if (fullImg_preview != null) {
-            fullImg_preview.forEach(function function_name(e) {
-                if (e.dataset.modded)
+function setupImageForLightbox(e) {
+    if (e.dataset.modded) {
         return;
-                e.dataset.modded = true;
-                if(e && e.parentElement.tagName == 'DIV'){
-                    e.style.cursor='pointer'
-                    e.style.userSelect='none'
+    }
 
-                    var isFirefox = isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1
+    e.dataset.modded = true;
+    e.style.cursor = 'pointer';
+    e.style.userSelect = 'none';
+
+    var isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1;
 
     // For Firefox, listening on click first switched to next image then shows the lightbox.
     // If you know how to fix this without switching to mousedown event, please.
     // For other browsers the event is click to make it possiblr to drag picture.
-                    var event = isFirefox ? 'mousedown' : 'click'
+    var event = isFirefox ? 'mousedown' : 'click';
 
     e.addEventListener(event, function(evt) {
+        if (evt.button == 1) {
+            open(evt.target.src);
+            evt.preventDefault();
+            return;
+        }
         if (!opts.js_modal_lightbox || evt.button != 0) return;
-                        modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed)
-                        evt.preventDefault()
-                        showModal(evt)
-                    }, true);
-                }
-            });
-        }
 
-    }, 100);
+        modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed);
+        evt.preventDefault();
+        showModal(evt);
+    }, true);
+
 }
 
 function modalZoomSet(modalImage, enable) {
-    if (enable) {
-        modalImage.classList.add('modalImageFullscreen');
-    } else {
-        modalImage.classList.remove('modalImageFullscreen');
-    }
+    if (modalImage) modalImage.classList.toggle('modalImageFullscreen', !!enable);
 }
 
 function modalZoomToggle(event) {
-    modalImage = gradioApp().getElementById("modalImage");
-    modalZoomSet(modalImage, !modalImage.classList.contains('modalImageFullscreen'))
-    event.stopPropagation()
+    var modalImage = gradioApp().getElementById("modalImage");
+    modalZoomSet(modalImage, !modalImage.classList.contains('modalImageFullscreen'));
+    event.stopPropagation();
 }
 
 function modalTileImageToggle(event) {
@@ -189,97 +166,94 @@ function modalTileImageToggle(event) {
     const isTiling = modalImage.style.display === 'none';
     if (isTiling) {
         modalImage.style.display = 'block';
-        modal.style.setProperty('background-image', 'none')
+        modal.style.setProperty('background-image', 'none');
     } else {
         modalImage.style.display = 'none';
-        modal.style.setProperty('background-image', `url(${modalImage.src})`)
+        modal.style.setProperty('background-image', `url(${modalImage.src})`);
     }
 
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
-function galleryImageHandler(e) {
-    if (e && e.parentElement.tagName == 'BUTTON') {
-        e.onclick = showGalleryImage;
-    }
-}
-
-onUiUpdate(function() {
-    fullImg_preview = gradioApp().querySelectorAll('img.w-full')
+onAfterUiUpdate(function() {
+    var fullImg_preview = gradioApp().querySelectorAll('.gradio-gallery > div > img');
     if (fullImg_preview != null) {
-        fullImg_preview.forEach(galleryImageHandler);
+        fullImg_preview.forEach(setupImageForLightbox);
     }
     updateOnBackgroundChange();
-})
+});
 
 document.addEventListener("DOMContentLoaded", function() {
-    const modalFragment = document.createDocumentFragment();
-    const modal = document.createElement('div')
+    //const modalFragment = document.createDocumentFragment();
+    const modal = document.createElement('div');
     modal.onclick = closeModal;
     modal.id = "lightboxModal";
-    modal.tabIndex = 0
-    modal.addEventListener('keydown', modalKeyHandler, true)
+    modal.tabIndex = 0;
+    modal.addEventListener('keydown', modalKeyHandler, true);
 
-    const modalControls = document.createElement('div')
+    const modalControls = document.createElement('div');
     modalControls.className = 'modalControls gradio-container';
     modal.append(modalControls);
 
-    const modalZoom = document.createElement('span')
+    const modalZoom = document.createElement('span');
     modalZoom.className = 'modalZoom cursor';
-    modalZoom.innerHTML = '⤡'
-    modalZoom.addEventListener('click', modalZoomToggle, true)
+    modalZoom.innerHTML = '⤡';
+    modalZoom.addEventListener('click', modalZoomToggle, true);
     modalZoom.title = "Toggle zoomed view";
-    modalControls.appendChild(modalZoom)
+    modalControls.appendChild(modalZoom);
 
-    const modalTileImage = document.createElement('span')
+    const modalTileImage = document.createElement('span');
     modalTileImage.className = 'modalTileImage cursor';
-    modalTileImage.innerHTML = '⊞'
-    modalTileImage.addEventListener('click', modalTileImageToggle, true)
+    modalTileImage.innerHTML = '⊞';
+    modalTileImage.addEventListener('click', modalTileImageToggle, true);
     modalTileImage.title = "Preview tiling";
-    modalControls.appendChild(modalTileImage)
+    modalControls.appendChild(modalTileImage);
 
-    const modalSave = document.createElement("span")
-    modalSave.className = "modalSave cursor"
-    modalSave.id = "modal_save"
-    modalSave.innerHTML = "🖫"
-    modalSave.addEventListener("click", modalSaveImage, true)
-    modalSave.title = "Save Image(s)"
-    modalControls.appendChild(modalSave)
+    const modalSave = document.createElement("span");
+    modalSave.className = "modalSave cursor";
+    modalSave.id = "modal_save";
+    modalSave.innerHTML = "🖫";
+    modalSave.addEventListener("click", modalSaveImage, true);
+    modalSave.title = "Save Image(s)";
+    modalControls.appendChild(modalSave);
 
-    const modalClose = document.createElement('span')
+    const modalClose = document.createElement('span');
     modalClose.className = 'modalClose cursor';
-    modalClose.innerHTML = '×'
+    modalClose.innerHTML = '×';
     modalClose.onclick = closeModal;
     modalClose.title = "Close image viewer";
-    modalControls.appendChild(modalClose)
+    modalControls.appendChild(modalClose);
 
-    const modalImage = document.createElement('img')
+    const modalImage = document.createElement('img');
     modalImage.id = 'modalImage';
     modalImage.onclick = closeModal;
-    modalImage.tabIndex = 0
-    modalImage.addEventListener('keydown', modalKeyHandler, true)
-    modal.appendChild(modalImage)
+    modalImage.tabIndex = 0;
+    modalImage.addEventListener('keydown', modalKeyHandler, true);
+    modal.appendChild(modalImage);
 
-    const modalPrev = document.createElement('a')
+    const modalPrev = document.createElement('a');
     modalPrev.className = 'modalPrev';
-    modalPrev.innerHTML = '❮'
-    modalPrev.tabIndex = 0
+    modalPrev.innerHTML = '❮';
+    modalPrev.tabIndex = 0;
     modalPrev.addEventListener('click', modalPrevImage, true);
-    modalPrev.addEventListener('keydown', modalKeyHandler, true)
-    modal.appendChild(modalPrev)
+    modalPrev.addEventListener('keydown', modalKeyHandler, true);
+    modal.appendChild(modalPrev);
 
-    const modalNext = document.createElement('a')
+    const modalNext = document.createElement('a');
     modalNext.className = 'modalNext';
-    modalNext.innerHTML = '❯'
-    modalNext.tabIndex = 0
+    modalNext.innerHTML = '❯';
+    modalNext.tabIndex = 0;
     modalNext.addEventListener('click', modalNextImage, true);
-    modalNext.addEventListener('keydown', modalKeyHandler, true)
+    modalNext.addEventListener('keydown', modalKeyHandler, true);
 
-    modal.appendChild(modalNext)
+    modal.appendChild(modalNext);
 
+    try {
+        gradioApp().appendChild(modal);
+    } catch (e) {
+        gradioApp().body.appendChild(modal);
+    }
 
-    gradioApp().getRootNode().appendChild(modal)
-
-    document.body.appendChild(modalFragment);
+    document.body.appendChild(modal);
 
 });

javascript/imageviewerGamepad.js

@@ -0,0 +1,63 @@
+let gamepads = [];
+
+window.addEventListener('gamepadconnected', (e) => {
+    const index = e.gamepad.index;
+    let isWaiting = false;
+    gamepads[index] = setInterval(async() => {
+        if (!opts.js_modal_lightbox_gamepad || isWaiting) return;
+        const gamepad = navigator.getGamepads()[index];
+        const xValue = gamepad.axes[0];
+        if (xValue <= -0.3) {
+            modalPrevImage(e);
+            isWaiting = true;
+        } else if (xValue >= 0.3) {
+            modalNextImage(e);
+            isWaiting = true;
+        }
+        if (isWaiting) {
+            await sleepUntil(() => {
+                const xValue = navigator.getGamepads()[index].axes[0];
+                if (xValue < 0.3 && xValue > -0.3) {
+                    return true;
+                }
+            }, opts.js_modal_lightbox_gamepad_repeat);
+            isWaiting = false;
+        }
+    }, 10);
+});
+
+window.addEventListener('gamepaddisconnected', (e) => {
+    clearInterval(gamepads[e.gamepad.index]);
+});
+
+/*
+Primarily for vr controller type pointer devices.
+I use the wheel event because there's currently no way to do it properly with web xr.
+ */
+let isScrolling = false;
+window.addEventListener('wheel', (e) => {
+    if (!opts.js_modal_lightbox_gamepad || isScrolling) return;
+    isScrolling = true;
+
+    if (e.deltaX <= -0.6) {
+        modalPrevImage(e);
+    } else if (e.deltaX >= 0.6) {
+        modalNextImage(e);
+    }
+
+    setTimeout(() => {
+        isScrolling = false;
+    }, opts.js_modal_lightbox_gamepad_repeat);
+});
+
+function sleepUntil(f, timeout) {
+    return new Promise((resolve) => {
+        const timeStart = new Date();
+        const wait = setInterval(function() {
+            if (f() || new Date() - timeStart > timeout) {
+                clearInterval(wait);
+                resolve();
+            }
+        }, 20);
+    });
+}

javascript/inputAccordion.js

@@ -0,0 +1,37 @@
+var observerAccordionOpen = new MutationObserver(function(mutations) {
+    mutations.forEach(function(mutationRecord) {
+        var elem = mutationRecord.target;
+        var open = elem.classList.contains('open');
+
+        var accordion = elem.parentNode;
+        accordion.classList.toggle('input-accordion-open', open);
+
+        var checkbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input");
+        checkbox.checked = open;
+        updateInput(checkbox);
+
+        var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
+        if (extra) {
+            extra.style.display = open ? "" : "none";
+        }
+    });
+});
+
+function inputAccordionChecked(id, checked) {
+    var label = gradioApp().querySelector('#' + id + " .label-wrap");
+    if (label.classList.contains('open') != checked) {
+        label.click();
+    }
+}
+
+onUiLoaded(function() {
+    for (var accordion of gradioApp().querySelectorAll('.input-accordion')) {
+        var labelWrap = accordion.querySelector('.label-wrap');
+        observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']});
+
+        var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
+        if (extra) {
+            labelWrap.insertBefore(extra, labelWrap.lastElementChild);
+        }
+    }
+});

javascript/localStorage.js

@@ -0,0 +1,26 @@
+
+function localSet(k, v) {
+    try {
+        localStorage.setItem(k, v);
+    } catch (e) {
+        console.warn(`Failed to save ${k} to localStorage: ${e}`);
+    }
+}
+
+function localGet(k, def) {
+    try {
+        return localStorage.getItem(k);
+    } catch (e) {
+        console.warn(`Failed to load ${k} from localStorage: ${e}`);
+    }
+
+    return def;
+}
+
+function localRemove(k) {
+    try {
+        return localStorage.removeItem(k);
+    } catch (e) {
+        console.warn(`Failed to remove ${k} from localStorage: ${e}`);
+    }
+}

javascript/localization.js

@@ -1,10 +1,9 @@
 
 // localization = {} -- the dict with translations is created by the backend
 
-ignore_ids_for_localization={
+var ignore_ids_for_localization = {
     setting_sd_hypernetwork: 'OPTION',
     setting_sd_model_checkpoint: 'OPTION',
-    setting_realesrgan_enabled_models: 'OPTION',
     modelmerger_primary_model_name: 'OPTION',
     modelmerger_secondary_model_name: 'OPTION',
     modelmerger_tertiary_model_name: 'OPTION',
@@ -12,22 +11,26 @@ ignore_ids_for_localization={
     train_hypernetwork: 'OPTION',
     txt2img_styles: 'OPTION',
     img2img_styles: 'OPTION',
-    setting_random_artist_categories: 'SPAN',
-    setting_face_restoration_model: 'SPAN',
-    setting_realesrgan_enabled_models: 'SPAN',
-    extras_upscaler_1: 'SPAN',
-    extras_upscaler_2: 'SPAN',
+    setting_random_artist_categories: 'OPTION',
+    setting_face_restoration_model: 'OPTION',
+    setting_realesrgan_enabled_models: 'OPTION',
+    extras_upscaler_1: 'OPTION',
+    extras_upscaler_2: 'OPTION',
+};
+
+var re_num = /^[.\d]+$/;
+var re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u;
+
+var original_lines = {};
+var translated_lines = {};
+
+function hasLocalization() {
+    return window.localization && Object.keys(window.localization).length > 0;
 }
 
-re_num = /^[\.\d]+$/
-re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u
-
-original_lines = {}
-translated_lines = {}
-
 function textNodesUnder(el) {
     var n, a = [], walk = document.createTreeWalker(el, NodeFilter.SHOW_TEXT, null, false);
-    while(n=walk.nextNode()) a.push(n);
+    while ((n = walk.nextNode())) a.push(n);
     return a;
 }
 
@@ -35,13 +38,13 @@ function canBeTranslated(node, text){
     if (!text) return false;
     if (!node.parentElement) return false;
 
-    parentType = node.parentElement.nodeName
+    var parentType = node.parentElement.nodeName;
     if (parentType == 'SCRIPT' || parentType == 'STYLE' || parentType == 'TEXTAREA') return false;
 
     if (parentType == 'OPTION' || parentType == 'SPAN') {
-        pnode = node
+        var pnode = node;
         for (var level = 0; level < 4; level++) {
-            pnode = pnode.parentElement
+            pnode = pnode.parentElement;
             if (!pnode) break;
 
             if (ignore_ids_for_localization[pnode.id] == parentType) return false;
@@ -50,86 +53,137 @@ function canBeTranslated(node, text){
 
     if (re_num.test(text)) return false;
     if (re_emoji.test(text)) return false;
-    return true
+    return true;
 }
 
 function getTranslation(text) {
-    if(! text) return undefined
+    if (!text) return undefined;
 
     if (translated_lines[text] === undefined) {
-        original_lines[text] = 1
+        original_lines[text] = 1;
     }
 
-    tl = localization[text]
+    var tl = localization[text];
     if (tl !== undefined) {
-        translated_lines[tl] = 1
+        translated_lines[tl] = 1;
     }
 
-    return tl
+    return tl;
 }
 
 function processTextNode(node) {
-    text = node.textContent.trim()
+    var text = node.textContent.trim();
 
-    if(! canBeTranslated(node, text)) return
+    if (!canBeTranslated(node, text)) return;
 
-    tl = getTranslation(text)
+    var tl = getTranslation(text);
     if (tl !== undefined) {
-        node.textContent = tl
+        node.textContent = tl;
     }
 }
 
 function processNode(node) {
     if (node.nodeType == 3) {
-        processTextNode(node)
-        return
+        processTextNode(node);
+        return;
     }
 
     if (node.title) {
-        tl = getTranslation(node.title)
+        let tl = getTranslation(node.title);
         if (tl !== undefined) {
-            node.title = tl
+            node.title = tl;
         }
     }
 
     if (node.placeholder) {
-        tl = getTranslation(node.placeholder)
+        let tl = getTranslation(node.placeholder);
         if (tl !== undefined) {
-            node.placeholder = tl
+            node.placeholder = tl;
         }
     }
 
     textNodesUnder(node).forEach(function(node) {
-        processTextNode(node)
-    })
+        processTextNode(node);
+    });
+}
+
+function localizeWholePage() {
+    processNode(gradioApp());
+
+    function elem(comp) {
+        var elem_id = comp.props.elem_id ? comp.props.elem_id : "component-" + comp.id;
+        return gradioApp().getElementById(elem_id);
+    }
+
+    for (var comp of window.gradio_config.components) {
+        if (comp.props.webui_tooltip) {
+            let e = elem(comp);
+
+            let tl = e ? getTranslation(e.title) : undefined;
+            if (tl !== undefined) {
+                e.title = tl;
+            }
+        }
+        if (comp.props.placeholder) {
+            let e = elem(comp);
+            let textbox = e ? e.querySelector('[placeholder]') : null;
+
+            let tl = textbox ? getTranslation(textbox.placeholder) : undefined;
+            if (tl !== undefined) {
+                textbox.placeholder = tl;
+            }
+        }
+    }
 }
 
 function dumpTranslations() {
-    dumped = {}
+    if (!hasLocalization()) {
+        // If we don't have any localization,
+        // we will not have traversed the app to find
+        // original_lines, so do that now.
+        localizeWholePage();
+    }
+    var dumped = {};
     if (localization.rtl) {
-        dumped.rtl = true
+        dumped.rtl = true;
     }
 
-    Object.keys(original_lines).forEach(function(text){
-        if(dumped[text] !== undefined)  return
+    for (const text in original_lines) {
+        if (dumped[text] !== undefined) continue;
+        dumped[text] = localization[text] || text;
+    }
 
-        dumped[text] = localization[text] || text
-    })
+    return dumped;
+}
 
-    return dumped
+function download_localization() {
+    var text = JSON.stringify(dumpTranslations(), null, 4);
+
+    var element = document.createElement('a');
+    element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
+    element.setAttribute('download', "localization.json");
+    element.style.display = 'none';
+    document.body.appendChild(element);
+
+    element.click();
+
+    document.body.removeChild(element);
+}
+
+document.addEventListener("DOMContentLoaded", function() {
+    if (!hasLocalization()) {
+        return;
     }
 
     onUiUpdate(function(m) {
         m.forEach(function(mutation) {
             mutation.addedNodes.forEach(function(node) {
-            processNode(node)
-        })
+                processNode(node);
+            });
+        });
     });
-})
 
-
-document.addEventListener("DOMContentLoaded", function() {
-    processNode(gradioApp())
+    localizeWholePage();
 
     if (localization.rtl) { // if the language is from right to left,
         (new MutationObserver((mutations, observer) => { // wait for the style to load
@@ -144,22 +198,8 @@ document.addEventListener("DOMContentLoaded", function() {
                             }
                         }
                     }
-                })
+                });
             });
         })).observe(gradioApp(), {childList: true});
     }
-})
-
-function download_localization() {
-    text = JSON.stringify(dumpTranslations(), null, 4)
-
-    var element = document.createElement('a');
-    element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
-    element.setAttribute('download', "localization.json");
-    element.style.display = 'none';
-    document.body.appendChild(element);
-
-    element.click();
-
-    document.body.removeChild(element);
-}
+});

javascript/notification.js

@@ -2,20 +2,20 @@
 
 let lastHeadImg = null;
 
-notificationButton = null
+let notificationButton = null;
 
-onUiUpdate(function(){
+onAfterUiUpdate(function() {
     if (notificationButton == null) {
-        notificationButton = gradioApp().getElementById('request_notifications')
+        notificationButton = gradioApp().getElementById('request_notifications');
 
         if (notificationButton != null) {
-            notificationButton.addEventListener('click', function (evt) {
-                Notification.requestPermission();
+            notificationButton.addEventListener('click', () => {
+                void Notification.requestPermission();
             }, true);
         }
     }
 
-    const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"][style*="display: block"] img.h-full.w-full.overflow-hidden');
+    const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"] div[id$="_results"] .thumbnail-item > img');
 
     if (galleryPreviews == null) return;
 

javascript/profilerVisualization.js

@@ -0,0 +1,153 @@
+
+function createRow(table, cellName, items) {
+    var tr = document.createElement('tr');
+    var res = [];
+
+    items.forEach(function(x, i) {
+        if (x === undefined) {
+            res.push(null);
+            return;
+        }
+
+        var td = document.createElement(cellName);
+        td.textContent = x;
+        tr.appendChild(td);
+        res.push(td);
+
+        var colspan = 1;
+        for (var n = i + 1; n < items.length; n++) {
+            if (items[n] !== undefined) {
+                break;
+            }
+
+            colspan += 1;
+        }
+
+        if (colspan > 1) {
+            td.colSpan = colspan;
+        }
+    });
+
+    table.appendChild(tr);
+
+    return res;
+}
+
+function showProfile(path, cutoff = 0.05) {
+    requestGet(path, {}, function(data) {
+        var table = document.createElement('table');
+        table.className = 'popup-table';
+
+        data.records['total'] = data.total;
+        var keys = Object.keys(data.records).sort(function(a, b) {
+            return data.records[b] - data.records[a];
+        });
+        var items = keys.map(function(x) {
+            return {key: x, parts: x.split('/'), time: data.records[x]};
+        });
+        var maxLength = items.reduce(function(a, b) {
+            return Math.max(a, b.parts.length);
+        }, 0);
+
+        var cols = createRow(table, 'th', ['record', 'seconds']);
+        cols[0].colSpan = maxLength;
+
+        function arraysEqual(a, b) {
+            return !(a < b || b < a);
+        }
+
+        var addLevel = function(level, parent, hide) {
+            var matching = items.filter(function(x) {
+                return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
+            });
+            var sorted = matching.sort(function(a, b) {
+                return b.time - a.time;
+            });
+            var othersTime = 0;
+            var othersList = [];
+            var othersRows = [];
+            var childrenRows = [];
+            sorted.forEach(function(x) {
+                var visible = x.time >= cutoff && !hide;
+
+                var cells = [];
+                for (var i = 0; i < maxLength; i++) {
+                    cells.push(x.parts[i]);
+                }
+                cells.push(x.time.toFixed(3));
+                var cols = createRow(table, 'td', cells);
+                for (i = 0; i < level; i++) {
+                    cols[i].className = 'muted';
+                }
+
+                var tr = cols[0].parentNode;
+                if (!visible) {
+                    tr.classList.add("hidden");
+                }
+
+                if (x.time >= cutoff) {
+                    childrenRows.push(tr);
+                } else {
+                    othersTime += x.time;
+                    othersList.push(x.parts[level]);
+                    othersRows.push(tr);
+                }
+
+                var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
+                if (children.length > 0) {
+                    var cell = cols[level];
+                    var onclick = function() {
+                        cell.classList.remove("link");
+                        cell.removeEventListener("click", onclick);
+                        children.forEach(function(x) {
+                            x.classList.remove("hidden");
+                        });
+                    };
+                    cell.classList.add("link");
+                    cell.addEventListener("click", onclick);
+                }
+            });
+
+            if (othersTime > 0) {
+                var cells = [];
+                for (var i = 0; i < maxLength; i++) {
+                    cells.push(parent[i]);
+                }
+                cells.push(othersTime.toFixed(3));
+                cells[level] = 'others';
+                var cols = createRow(table, 'td', cells);
+                for (i = 0; i < level; i++) {
+                    cols[i].className = 'muted';
+                }
+
+                var cell = cols[level];
+                var tr = cell.parentNode;
+                var onclick = function() {
+                    tr.classList.add("hidden");
+                    cell.classList.remove("link");
+                    cell.removeEventListener("click", onclick);
+                    othersRows.forEach(function(x) {
+                        x.classList.remove("hidden");
+                    });
+                };
+
+                cell.title = othersList.join(", ");
+                cell.classList.add("link");
+                cell.addEventListener("click", onclick);
+
+                if (hide) {
+                    tr.classList.add("hidden");
+                }
+
+                childrenRows.push(tr);
+            }
+
+            return childrenRows;
+        };
+
+        addLevel(0, []);
+
+        popup(table);
+    });
+}
+

javascript/progressbar.js

@@ -1,81 +1,15 @@
 // code related to showing and updating progressbar shown as the image is being made
 
+function rememberGallerySelection() {
 
-galleries = {}
-storedGallerySelections = {}
-galleryObservers = {}
-
-function rememberGallerySelection(id_gallery){
-    storedGallerySelections[id_gallery] = getGallerySelectedIndex(id_gallery)
 }
 
-function getGallerySelectedIndex(id_gallery){
-    let galleryButtons = gradioApp().querySelectorAll('#'+id_gallery+' .gallery-item')
-    let galleryBtnSelected = gradioApp().querySelector('#'+id_gallery+' .gallery-item.\\!ring-2')
+function getGallerySelectedIndex() {
 
-     let currentlySelectedIndex = -1
-     galleryButtons.forEach(function(v, i){ if(v==galleryBtnSelected) { currentlySelectedIndex = i } })
-
-     return currentlySelectedIndex
 }
 
-// this is a workaround for https://github.com/gradio-app/gradio/issues/2984
-function check_gallery(id_gallery){
-    let gallery = gradioApp().getElementById(id_gallery)
-    // if gallery has no change, no need to setting up observer again.
-    if (gallery && galleries[id_gallery] !== gallery){
-        galleries[id_gallery] = gallery;
-        if(galleryObservers[id_gallery]){
-            galleryObservers[id_gallery].disconnect();
-        }
-
-        storedGallerySelections[id_gallery] = -1
-
-        galleryObservers[id_gallery] = new MutationObserver(function (){
-            let galleryButtons = gradioApp().querySelectorAll('#'+id_gallery+' .gallery-item')
-            let galleryBtnSelected = gradioApp().querySelector('#'+id_gallery+' .gallery-item.\\!ring-2')
-            let currentlySelectedIndex = getGallerySelectedIndex(id_gallery)
-            prevSelectedIndex = storedGallerySelections[id_gallery]
-            storedGallerySelections[id_gallery] = -1
-
-            if (prevSelectedIndex !== -1 && galleryButtons.length>prevSelectedIndex && !galleryBtnSelected) {
-                // automatically re-open previously selected index (if exists)
-                activeElement = gradioApp().activeElement;
-                let scrollX = window.scrollX;
-                let scrollY = window.scrollY;
-
-                galleryButtons[prevSelectedIndex].click();
-                showGalleryImage();
-
-                // When the gallery button is clicked, it gains focus and scrolls itself into view
-                // We need to scroll back to the previous position
-                setTimeout(function (){
-                    window.scrollTo(scrollX, scrollY);
-                }, 50);
-
-                if(activeElement){
-                    // i fought this for about an hour; i don't know why the focus is lost or why this helps recover it
-                    // if someone has a better solution please by all means
-                    setTimeout(function (){
-                        activeElement.focus({
-                            preventScroll: true // Refocus the element that was focused before the gallery was opened without scrolling to it
-                        })
-                    }, 1);
-                }
-            }
-        })
-        galleryObservers[id_gallery].observe( gallery, { childList:true, subtree:false })
-    }
-}
-
-onUiUpdate(function(){
-    check_gallery('txt2img_gallery')
-    check_gallery('img2img_gallery')
-})
-
 function request(url, data, handler, errorHandler) {
     var xhr = new XMLHttpRequest();
-    var url = url;
     xhr.open("POST", url, true);
     xhr.setRequestHeader("Content-Type", "application/json");
     xhr.onreadystatechange = function() {
@@ -83,13 +17,13 @@ function request(url, data, handler, errorHandler){
             if (xhr.status === 200) {
                 try {
                     var js = JSON.parse(xhr.responseText);
-                    handler(js)
+                    handler(js);
                 } catch (error) {
                     console.error(error);
-                    errorHandler()
+                    errorHandler();
                 }
             } else {
-                errorHandler()
+                errorHandler();
             }
         }
     };
@@ -98,21 +32,21 @@ function request(url, data, handler, errorHandler){
 }
 
 function pad2(x) {
-    return x<10 ? '0'+x : x
+    return x < 10 ? '0' + x : x;
 }
 
 function formatTime(secs) {
     if (secs > 3600) {
-        return pad2(Math.floor(secs/60/60)) + ":" + pad2(Math.floor(secs/60)%60) + ":" + pad2(Math.floor(secs)%60)
+        return pad2(Math.floor(secs / 60 / 60)) + ":" + pad2(Math.floor(secs / 60) % 60) + ":" + pad2(Math.floor(secs) % 60);
     } else if (secs > 60) {
-        return pad2(Math.floor(secs/60)) + ":" + pad2(Math.floor(secs)%60)
+        return pad2(Math.floor(secs / 60)) + ":" + pad2(Math.floor(secs) % 60);
     } else {
-        return Math.floor(secs) + "s"
+        return Math.floor(secs) + "s";
     }
 }
 
 function setTitle(progress) {
-    var title = 'Stable Diffusion'
+    var title = 'Stable Diffusion';
 
     if (opts.show_progress_in_title && progress) {
         title = '[' + progress.trim() + '] ' + title;
@@ -125,119 +59,128 @@ function setTitle(progress){
 
 
 function randomId() {
-    return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7)+")"
+    return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + ")";
 }
 
 // starts sending progress requests to "/internal/progress" uri, creating progressbar above progressbarContainer element and
 // preview inside gallery element. Cleans up all created stuff when the task is over and calls atEnd.
 // calls onProgress every time there is a progress update
-function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress){
-    var dateStart = new Date()
-    var wasEverActive = false
-    var parentProgressbar = progressbarContainer.parentNode
-    var parentGallery = gallery ? gallery.parentNode : null
+function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress, inactivityTimeout = 40) {
+    var dateStart = new Date();
+    var wasEverActive = false;
+    var parentProgressbar = progressbarContainer.parentNode;
 
-    var divProgress = document.createElement('div')
-    divProgress.className='progressDiv'
-    divProgress.style.display = opts.show_progressbar ? "" : "none"
-    var divInner = document.createElement('div')
-    divInner.className='progress'
+    var divProgress = document.createElement('div');
+    divProgress.className = 'progressDiv';
+    divProgress.style.display = opts.show_progressbar ? "block" : "none";
+    var divInner = document.createElement('div');
+    divInner.className = 'progress';
 
-    divProgress.appendChild(divInner)
-    parentProgressbar.insertBefore(divProgress, progressbarContainer)
+    divProgress.appendChild(divInner);
+    parentProgressbar.insertBefore(divProgress, progressbarContainer);
 
-    if(parentGallery){
-        var livePreview = document.createElement('div')
-        livePreview.className='livePreview'
-        parentGallery.insertBefore(livePreview, gallery)
-    }
+    var livePreview = null;
 
     var removeProgressBar = function() {
-        setTitle("")
-        parentProgressbar.removeChild(divProgress)
-        if(parentGallery) parentGallery.removeChild(livePreview)
-        atEnd()
-    }
+        if (!divProgress) return;
 
-    var fun = function(id_task, id_live_preview){
-        request("./internal/progress", {"id_task": id_task, "id_live_preview": id_live_preview}, function(res){
+        setTitle("");
+        parentProgressbar.removeChild(divProgress);
+        if (gallery && livePreview) gallery.removeChild(livePreview);
+        atEnd();
+
+        divProgress = null;
+    };
+
+    var funProgress = function(id_task) {
+        request("./internal/progress", {id_task: id_task, live_preview: false}, function(res) {
             if (res.completed) {
-                removeProgressBar()
-                return
+                removeProgressBar();
+                return;
             }
 
-            var rect = progressbarContainer.getBoundingClientRect()
+            let progressText = "";
 
-            if(rect.width){
-                divProgress.style.width = rect.width + "px";
-            }
-
-            progressText = ""
-
-            divInner.style.width = ((res.progress || 0) * 100.0) + '%'
-            divInner.style.background = res.progress ? "" : "transparent"
+            divInner.style.width = ((res.progress || 0) * 100.0) + '%';
+            divInner.style.background = res.progress ? "" : "transparent";
 
             if (res.progress > 0) {
-                progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%'
+                progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%';
             }
 
             if (res.eta) {
-                progressText += " ETA: " + formatTime(res.eta)
+                progressText += " ETA: " + formatTime(res.eta);
             }
 
-
-            setTitle(progressText)
+            setTitle(progressText);
 
             if (res.textinfo && res.textinfo.indexOf("\n") == -1) {
-                progressText = res.textinfo + " " + progressText
+                progressText = res.textinfo + " " + progressText;
             }
 
-            divInner.textContent = progressText
+            divInner.textContent = progressText;
 
-            var elapsedFromStart = (new Date() - dateStart) / 1000
+            var elapsedFromStart = (new Date() - dateStart) / 1000;
 
             if (res.active) wasEverActive = true;
 
             if (!res.active && wasEverActive) {
-                removeProgressBar()
-                return
+                removeProgressBar();
+                return;
             }
 
-            if(elapsedFromStart > 5 && !res.queued && !res.active){
-                removeProgressBar()
-                return
+            if (elapsedFromStart > inactivityTimeout && !res.queued && !res.active) {
+                removeProgressBar();
+                return;
             }
 
-
-            if(res.live_preview && gallery){
-                var rect = gallery.getBoundingClientRect()
-                if(rect.width){
-                    livePreview.style.width = rect.width + "px"
-                    livePreview.style.height = rect.height + "px"
-                }
-
-                var img = new Image();
-                img.onload = function() {
-                    livePreview.appendChild(img)
-                    if(livePreview.childElementCount > 2){
-                        livePreview.removeChild(livePreview.firstElementChild)
-                    }
-                }
-                img.src = res.live_preview;
-            }
-
-
             if (onProgress) {
-                onProgress(res)
+                onProgress(res);
             }
 
             setTimeout(() => {
-                fun(id_task, res.id_live_preview);
-            }, opts.live_preview_refresh_period || 500)
+                funProgress(id_task, res.id_live_preview);
+            }, opts.live_preview_refresh_period || 500);
         }, function() {
-            removeProgressBar()
-        })
+            removeProgressBar();
+        });
+    };
+
+    var funLivePreview = function(id_task, id_live_preview) {
+        request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) {
+            if (!divProgress) {
+                return;
+            }
+
+            if (res.live_preview && gallery) {
+                var img = new Image();
+                img.onload = function() {
+                    if (!livePreview) {
+                        livePreview = document.createElement('div');
+                        livePreview.className = 'livePreview';
+                        gallery.insertBefore(livePreview, gallery.firstElementChild);
+                    }
+
+                    livePreview.appendChild(img);
+                    if (livePreview.childElementCount > 2) {
+                        livePreview.removeChild(livePreview.firstElementChild);
+                    }
+                };
+                img.src = res.live_preview;
+            }
+
+            setTimeout(() => {
+                funLivePreview(id_task, res.id_live_preview);
+            }, opts.live_preview_refresh_period || 500);
+        }, function() {
+            removeProgressBar();
+        });
+    };
+
+    funProgress(id_task, 0);
+
+    if (gallery) {
+        funLivePreview(id_task, 0);
     }
 
-    fun(id_task, 0)
 }

javascript/resizeHandle.js

@@ -0,0 +1,141 @@
+(function() {
+    const GRADIO_MIN_WIDTH = 320;
+    const GRID_TEMPLATE_COLUMNS = '1fr 16px 1fr';
+    const PAD = 16;
+    const DEBOUNCE_TIME = 100;
+
+    const R = {
+        tracking: false,
+        parent: null,
+        parentWidth: null,
+        leftCol: null,
+        leftColStartWidth: null,
+        screenX: null,
+    };
+
+    let resizeTimer;
+    let parents = [];
+
+    function setLeftColGridTemplate(el, width) {
+        el.style.gridTemplateColumns = `${width}px 16px 1fr`;
+    }
+
+    function displayResizeHandle(parent) {
+        if (window.innerWidth < GRADIO_MIN_WIDTH * 2 + PAD * 4) {
+            parent.style.display = 'flex';
+            if (R.handle != null) {
+                R.handle.style.opacity = '0';
+            }
+            return false;
+        } else {
+            parent.style.display = 'grid';
+            if (R.handle != null) {
+                R.handle.style.opacity = '100';
+            }
+            return true;
+        }
+    }
+
+    function afterResize(parent) {
+        if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != GRID_TEMPLATE_COLUMNS) {
+            const oldParentWidth = R.parentWidth;
+            const newParentWidth = parent.offsetWidth;
+            const widthL = parseInt(parent.style.gridTemplateColumns.split(' ')[0]);
+
+            const ratio = newParentWidth / oldParentWidth;
+
+            const newWidthL = Math.max(Math.floor(ratio * widthL), GRADIO_MIN_WIDTH);
+            setLeftColGridTemplate(parent, newWidthL);
+
+            R.parentWidth = newParentWidth;
+        }
+    }
+
+    function setup(parent) {
+        const leftCol = parent.firstElementChild;
+        const rightCol = parent.lastElementChild;
+
+        parents.push(parent);
+
+        parent.style.display = 'grid';
+        parent.style.gap = '0';
+        parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS;
+
+        const resizeHandle = document.createElement('div');
+        resizeHandle.classList.add('resize-handle');
+        parent.insertBefore(resizeHandle, rightCol);
+
+        resizeHandle.addEventListener('mousedown', (evt) => {
+            if (evt.button !== 0) return;
+
+            evt.preventDefault();
+            evt.stopPropagation();
+
+            document.body.classList.add('resizing');
+
+            R.tracking = true;
+            R.parent = parent;
+            R.parentWidth = parent.offsetWidth;
+            R.handle = resizeHandle;
+            R.leftCol = leftCol;
+            R.leftColStartWidth = leftCol.offsetWidth;
+            R.screenX = evt.screenX;
+        });
+
+        resizeHandle.addEventListener('dblclick', (evt) => {
+            evt.preventDefault();
+            evt.stopPropagation();
+
+            parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS;
+        });
+
+        afterResize(parent);
+    }
+
+    window.addEventListener('mousemove', (evt) => {
+        if (evt.button !== 0) return;
+
+        if (R.tracking) {
+            evt.preventDefault();
+            evt.stopPropagation();
+
+            const delta = R.screenX - evt.screenX;
+            const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - GRADIO_MIN_WIDTH - PAD), GRADIO_MIN_WIDTH);
+            setLeftColGridTemplate(R.parent, leftColWidth);
+        }
+    });
+
+    window.addEventListener('mouseup', (evt) => {
+        if (evt.button !== 0) return;
+
+        if (R.tracking) {
+            evt.preventDefault();
+            evt.stopPropagation();
+
+            R.tracking = false;
+
+            document.body.classList.remove('resizing');
+        }
+    });
+
+
+    window.addEventListener('resize', () => {
+        clearTimeout(resizeTimer);
+
+        resizeTimer = setTimeout(function() {
+            for (const parent of parents) {
+                afterResize(parent);
+            }
+        }, DEBOUNCE_TIME);
+    });
+
+    setupResizeHandle = setup;
+})();
+
+onUiLoaded(function() {
+    for (var elem of gradioApp().querySelectorAll('.resize-handle-row')) {
+        if (!elem.querySelector('.resize-handle')) {
+            setupResizeHandle(elem);
+        }
+    }
+});

javascript/settings.js

@@ -0,0 +1,46 @@
+let settingsExcludeTabsFromShowAll = {
+    settings_tab_defaults: 1,
+    settings_tab_sysinfo: 1,
+    settings_tab_actions: 1,
+    settings_tab_licenses: 1,
+};
+
+function settingsShowAllTabs() {
+    gradioApp().querySelectorAll('#settings > div').forEach(function(elem) {
+        if (settingsExcludeTabsFromShowAll[elem.id]) return;
+
+        elem.style.display = "block";
+    });
+}
+
+function settingsShowOneTab() {
+    gradioApp().querySelector('#settings_show_one_page').click();
+}
+
+onUiLoaded(function() {
+    var edit = gradioApp().querySelector('#settings_search');
+    var editTextarea = gradioApp().querySelector('#settings_search > label > input');
+    var buttonShowAllPages = gradioApp().getElementById('settings_show_all_pages');
+    var settings_tabs = gradioApp().querySelector('#settings div');
+
+    onEdit('settingsSearch', editTextarea, 250, function() {
+        var searchText = (editTextarea.value || "").trim().toLowerCase();
+
+        gradioApp().querySelectorAll('#settings > div[id^=settings_] div[id^=column_settings_] > *').forEach(function(elem) {
+            var visible = elem.textContent.trim().toLowerCase().indexOf(searchText) != -1;
+            elem.style.display = visible ? "" : "none";
+        });
+
+        if (searchText != "") {
+            settingsShowAllTabs();
+        } else {
+            settingsShowOneTab();
+        }
+    });
+
+    settings_tabs.insertBefore(edit, settings_tabs.firstChild);
+    settings_tabs.appendChild(buttonShowAllPages);
+
+
+    buttonShowAllPages.addEventListener("click", settingsShowAllTabs);
+});

javascript/textualInversion.js

@@ -2,16 +2,16 @@
 
 
 function start_training_textual_inversion() {
-    gradioApp().querySelector('#ti_error').innerHTML=''
+    gradioApp().querySelector('#ti_error').innerHTML = '';
 
-    var id = randomId()
+    var id = randomId();
     requestProgress(id, gradioApp().getElementById('ti_output'), gradioApp().getElementById('ti_gallery'), function() {}, function(progress) {
-        gradioApp().getElementById('ti_progress').innerHTML = progress.textinfo
-    })
+        gradioApp().getElementById('ti_progress').innerHTML = progress.textinfo;
+    });
 
-    var res = args_to_array(arguments)
+    var res = Array.from(arguments);
 
-    res[0] = id
+    res[0] = id;
 
-    return res
+    return res;
 }

javascript/token-counters.js

@@ -0,0 +1,75 @@
+let promptTokenCountUpdateFunctions = {};
+
+function update_txt2img_tokens(...args) {
+    // Called from Gradio
+    update_token_counter("txt2img_token_button");
+    update_token_counter("txt2img_negative_token_button");
+    if (args.length == 2) {
+        return args[0];
+    }
+    return args;
+}
+
+function update_img2img_tokens(...args) {
+    // Called from Gradio
+    update_token_counter("img2img_token_button");
+    update_token_counter("img2img_negative_token_button");
+    if (args.length == 2) {
+        return args[0];
+    }
+    return args;
+}
+
+function update_token_counter(button_id) {
+    promptTokenCountUpdateFunctions[button_id]?.();
+}
+
+
+function recalculatePromptTokens(name) {
+    promptTokenCountUpdateFunctions[name]?.();
+}
+
+function recalculate_prompts_txt2img() {
+    // Called from Gradio
+    recalculatePromptTokens('txt2img_prompt');
+    recalculatePromptTokens('txt2img_neg_prompt');
+    return Array.from(arguments);
+}
+
+function recalculate_prompts_img2img() {
+    // Called from Gradio
+    recalculatePromptTokens('img2img_prompt');
+    recalculatePromptTokens('img2img_neg_prompt');
+    return Array.from(arguments);
+}
+
+function setupTokenCounting(id, id_counter, id_button) {
+    var prompt = gradioApp().getElementById(id);
+    var counter = gradioApp().getElementById(id_counter);
+    var textarea = gradioApp().querySelector(`#${id} > label > textarea`);
+
+    if (opts.disable_token_counters) {
+        counter.style.display = "none";
+        return;
+    }
+
+    if (counter.parentElement == prompt.parentElement) {
+        return;
+    }
+
+    prompt.parentElement.insertBefore(counter, prompt);
+    prompt.parentElement.style.position = "relative";
+
+    var func = onEdit(id, textarea, 800, function() {
+        gradioApp().getElementById(id_button)?.click();
+    });
+    promptTokenCountUpdateFunctions[id] = func;
+    promptTokenCountUpdateFunctions[id_button] = func;
+}
+
+function setupTokenCounters() {
+    setupTokenCounting('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button');
+    setupTokenCounting('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button');
+    setupTokenCounting('img2img_prompt', 'img2img_token_counter', 'img2img_token_button');
+    setupTokenCounting('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button');
+}

javascript/ui.js

@@ -1,48 +1,55 @@
 // various functions for interaction with ui.py not large enough to warrant putting them in separate files
 
 function set_theme(theme) {
-    gradioURL = window.location.href
+    var gradioURL = window.location.href;
     if (!gradioURL.includes('?__theme=')) {
         window.location.replace(gradioURL + '?__theme=' + theme);
     }
 }
 
+function all_gallery_buttons() {
+    var allGalleryButtons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery].gradio-gallery .thumbnails > .thumbnail-item.thumbnail-small');
+    var visibleGalleryButtons = [];
+    allGalleryButtons.forEach(function(elem) {
+        if (elem.parentElement.offsetParent) {
+            visibleGalleryButtons.push(elem);
+        }
+    });
+    return visibleGalleryButtons;
+}
+
+function selected_gallery_button() {
+    return all_gallery_buttons().find(elem => elem.classList.contains('selected')) ?? null;
+}
+
 function selected_gallery_index() {
-    var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery] .gallery-item')
-    var button = gradioApp().querySelector('[style="display: block;"].tabitem div[id$=_gallery] .gallery-item.\\!ring-2')
-
-    var result = -1
-    buttons.forEach(function(v, i){ if(v==button) { result = i } })
-
-    return result
+    return all_gallery_buttons().findIndex(elem => elem.classList.contains('selected'));
 }
 
 function extract_image_from_gallery(gallery) {
+    if (gallery.length == 0) {
+        return [null];
+    }
     if (gallery.length == 1) {
-        return [gallery[0]]
+        return [gallery[0]];
     }
 
-    index = selected_gallery_index()
+    var index = selected_gallery_index();
 
     if (index < 0 || index >= gallery.length) {
-        return [null]
+        // Use the first image in the gallery as the default
+        index = 0;
     }
 
     return [gallery[index]];
 }
 
-function args_to_array(args){
-    res = []
-    for(var i=0;i<args.length;i++){
-        res.push(args[i])
-    }
-    return res
-}
+window.args_to_array = Array.from; // Compatibility with e.g. extensions that may expect this to be around
 
 function switch_to_txt2img() {
     gradioApp().querySelector('#tabs').querySelectorAll('button')[0].click();
 
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
 function switch_to_img2img_tab(no) {
@@ -51,157 +58,189 @@ function switch_to_img2img_tab(no){
 }
 function switch_to_img2img() {
     switch_to_img2img_tab(0);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
 function switch_to_sketch() {
     switch_to_img2img_tab(1);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
 function switch_to_inpaint() {
     switch_to_img2img_tab(2);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
 function switch_to_inpaint_sketch() {
     switch_to_img2img_tab(3);
-    return args_to_array(arguments);
-}
-
-function switch_to_inpaint(){
-    gradioApp().querySelector('#tabs').querySelectorAll('button')[1].click();
-    gradioApp().getElementById('mode_img2img').querySelectorAll('button')[2].click();
-
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
 function switch_to_extras() {
     gradioApp().querySelector('#tabs').querySelectorAll('button')[2].click();
 
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
 function get_tab_index(tabId) {
-    var res = 0
-
-    gradioApp().getElementById(tabId).querySelector('div').querySelectorAll('button').forEach(function(button, i){
-        if(button.className.indexOf('bg-white') != -1)
-            res = i
-    })
-
-    return res
+    let buttons = gradioApp().getElementById(tabId).querySelector('div').querySelectorAll('button');
+    for (let i = 0; i < buttons.length; i++) {
+        if (buttons[i].classList.contains('selected')) {
+            return i;
+        }
+    }
+    return 0;
 }
 
 function create_tab_index_args(tabId, args) {
-    var res = []
-    for(var i=0; i<args.length; i++){
-        res.push(args[i])
-    }
-
-    res[0] = get_tab_index(tabId)
-
-    return res
+    var res = Array.from(args);
+    res[0] = get_tab_index(tabId);
+    return res;
 }
 
 function get_img2img_tab_index() {
-    let res = args_to_array(arguments)
-    res.splice(-2)
-    res[0] = get_tab_index('mode_img2img')
-    return res
+    let res = Array.from(arguments);
+    res.splice(-2);
+    res[0] = get_tab_index('mode_img2img');
+    return res;
 }
 
 function create_submit_args(args) {
-    res = []
-    for(var i=0;i<args.length;i++){
-        res.push(args[i])
-    }
+    var res = Array.from(args);
 
     // As it is currently, txt2img and img2img send back the previous output args (txt2img_gallery, generation_info, html_info) whenever you generate a new image.
     // This can lead to uploading a huge gallery of previously generated images, which leads to an unnecessary delay between submitting and beginning to generate.
     // I don't know why gradio is sending outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some.
     // If gradio at some point stops sending outputs, this may break something
     if (Array.isArray(res[res.length - 3])) {
-        res[res.length - 3] = null
+        res[res.length - 3] = null;
     }
 
-    return res
+    return res;
 }
 
 function showSubmitButtons(tabname, show) {
-    gradioApp().getElementById(tabname+'_interrupt').style.display = show ? "none" : "block"
-    gradioApp().getElementById(tabname+'_skip').style.display = show ? "none" : "block"
+    gradioApp().getElementById(tabname + '_interrupt').style.display = show ? "none" : "block";
+    gradioApp().getElementById(tabname + '_skip').style.display = show ? "none" : "block";
+}
+
+function showRestoreProgressButton(tabname, show) {
+    var button = gradioApp().getElementById(tabname + "_restore_progress");
+    if (!button) return;
+
+    button.style.display = show ? "flex" : "none";
 }
 
 function submit() {
-    rememberGallerySelection('txt2img_gallery')
-    showSubmitButtons('txt2img', false)
+    showSubmitButtons('txt2img', false);
+
+    var id = randomId();
+    localSet("txt2img_task_id", id);
 
-    var id = randomId()
     requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
-        showSubmitButtons('txt2img', true)
+        showSubmitButtons('txt2img', true);
+        localRemove("txt2img_task_id");
+        showRestoreProgressButton('txt2img', false);
+    });
 
-    })
+    var res = create_submit_args(arguments);
 
-    var res = create_submit_args(arguments)
+    res[0] = id;
 
-    res[0] = id
-
-    return res
+    return res;
 }
 
 function submit_img2img() {
-    rememberGallerySelection('img2img_gallery')
-    showSubmitButtons('img2img', false)
+    showSubmitButtons('img2img', false);
+
+    var id = randomId();
+    localSet("img2img_task_id", id);
 
-    var id = randomId()
     requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
-        showSubmitButtons('img2img', true)
-    })
+        showSubmitButtons('img2img', true);
+        localRemove("img2img_task_id");
+        showRestoreProgressButton('img2img', false);
+    });
 
-    var res = create_submit_args(arguments)
+    var res = create_submit_args(arguments);
 
-    res[0] = id
-    res[1] = get_tab_index('mode_img2img')
+    res[0] = id;
+    res[1] = get_tab_index('mode_img2img');
 
-    return res
+    return res;
 }
 
-function modelmerger(){
-    var id = randomId()
-    requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function(){})
+function restoreProgressTxt2img() {
+    showRestoreProgressButton("txt2img", false);
+    var id = localGet("txt2img_task_id");
 
-    var res = create_submit_args(arguments)
-    res[0] = id
-    return res
+    if (id) {
+        requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
+            showSubmitButtons('txt2img', true);
+        }, null, 0);
+    }
+
+    return id;
+}
+
+function restoreProgressImg2img() {
+    showRestoreProgressButton("img2img", false);
+
+    var id = localGet("img2img_task_id");
+
+    if (id) {
+        requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
+            showSubmitButtons('img2img', true);
+        }, null, 0);
+    }
+
+    return id;
+}
+
+
+onUiLoaded(function() {
+    showRestoreProgressButton('txt2img', localGet("txt2img_task_id"));
+    showRestoreProgressButton('img2img', localGet("img2img_task_id"));
+});
+
+
+function modelmerger() {
+    var id = randomId();
+    requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function() {});
+
+    var res = create_submit_args(arguments);
+    res[0] = id;
+    return res;
 }
 
 
 function ask_for_style_name(_, prompt_text, negative_prompt_text) {
-    name_ = prompt('Style name:')
-    return [name_, prompt_text, negative_prompt_text]
+    var name_ = prompt('Style name:');
+    return [name_, prompt_text, negative_prompt_text];
 }
 
 function confirm_clear_prompt(prompt, negative_prompt) {
     if (confirm("Delete prompt?")) {
-        prompt = ""
-        negative_prompt = ""
+        prompt = "";
+        negative_prompt = "";
     }
 
-    return [prompt, negative_prompt]
+    return [prompt, negative_prompt];
 }
 
-opts = {}
-onUiUpdate(function(){
+
+var opts = {};
+onAfterUiUpdate(function() {
     if (Object.keys(opts).length != 0) return;
 
-	json_elem = gradioApp().getElementById('settings_json')
+    var json_elem = gradioApp().getElementById('settings_json');
     if (json_elem == null) return;
 
-    var textarea = json_elem.querySelector('textarea')
-    var jsdata = textarea.value
-    opts = JSON.parse(jsdata)
-    executeCallbacks(optionsChangedCallbacks);
+    var textarea = json_elem.querySelector('textarea');
+    var jsdata = textarea.value;
+    opts = JSON.parse(jsdata);
+
+    executeCallbacks(optionsChangedCallbacks); /*global optionsChangedCallbacks*/
 
     Object.defineProperty(textarea, 'value', {
         set: function(newValue) {
@@ -210,7 +249,7 @@ onUiUpdate(function(){
             valueProp.set.call(textarea, newValue);
 
             if (oldValue != newValue) {
-                opts = JSON.parse(textarea.value)
+                opts = JSON.parse(textarea.value);
             }
 
             executeCallbacks(optionsChangedCallbacks);
@@ -221,91 +260,111 @@ onUiUpdate(function(){
         }
     });
 
-    json_elem.parentElement.style.display="none"
+    json_elem.parentElement.style.display = "none";
 
-    function registerTextarea(id, id_counter, id_button){
-        var prompt = gradioApp().getElementById(id)
-        var counter = gradioApp().getElementById(id_counter)
-        var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
-
-        if(counter.parentElement == prompt.parentElement){
-            return
-        }
-
-
-        prompt.parentElement.insertBefore(counter, prompt)
-        counter.classList.add("token-counter")
-        prompt.parentElement.style.position = "relative"
-
-		textarea.addEventListener("input", function(){
-		    update_token_counter(id_button);
+    setupTokenCounters();
 });
-    }
-
-    registerTextarea('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button')
-    registerTextarea('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button')
-    registerTextarea('img2img_prompt', 'img2img_token_counter', 'img2img_token_button')
-    registerTextarea('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button')
-
-    show_all_pages = gradioApp().getElementById('settings_show_all_pages')
-    settings_tabs = gradioApp().querySelector('#settings div')
-    if(show_all_pages && settings_tabs){
-        settings_tabs.appendChild(show_all_pages)
-        show_all_pages.onclick = function(){
-            gradioApp().querySelectorAll('#settings > div').forEach(function(elem){
-                elem.style.display = "block";
-            })
-        }
-    }
-})
 
 onOptionsChanged(function() {
-    elem = gradioApp().getElementById('sd_checkpoint_hash')
-    sd_checkpoint_hash = opts.sd_checkpoint_hash || ""
-    shorthash = sd_checkpoint_hash.substr(0,10)
+    var elem = gradioApp().getElementById('sd_checkpoint_hash');
+    var sd_checkpoint_hash = opts.sd_checkpoint_hash || "";
+    var shorthash = sd_checkpoint_hash.substring(0, 10);
 
     if (elem && elem.textContent != shorthash) {
-	    elem.textContent = shorthash
-	    elem.title = sd_checkpoint_hash
-	    elem.href = "https://google.com/search?q=" + sd_checkpoint_hash
+        elem.textContent = shorthash;
+        elem.title = sd_checkpoint_hash;
+        elem.href = "https://google.com/search?q=" + sd_checkpoint_hash;
     }
-})
+});
 
 let txt2img_textarea, img2img_textarea = undefined;
-let wait_time = 800
-let token_timeout;
-
-function update_txt2img_tokens(...args) {
-	update_token_counter("txt2img_token_button")
-	if (args.length == 2)
-		return args[0]
-	return args;
-}
-
-function update_img2img_tokens(...args) {
-	update_token_counter("img2img_token_button")
-	if (args.length == 2)
-		return args[0]
-	return args;
-}
-
-function update_token_counter(button_id) {
-	if (token_timeout)
-		clearTimeout(token_timeout);
-	token_timeout = setTimeout(() => gradioApp().getElementById(button_id)?.click(), wait_time);
-}
 
 function restart_reload() {
     document.body.innerHTML = '<h1 style="font-family:monospace;margin-top:20%;color:lightgray;text-align:center;">Reloading...</h1>';
-    setTimeout(function(){location.reload()},2000)
 
-    return []
+    var requestPing = function() {
+        requestGet("./internal/ping", {}, function(data) {
+            location.reload();
+        }, function() {
+            setTimeout(requestPing, 500);
+        });
+    };
+
+    setTimeout(requestPing, 2000);
+
+    return [];
 }
 
 // Simulate an `input` DOM event for Gradio Textbox component. Needed after you edit its contents in javascript, otherwise your edits
 // will only visible on web page and not sent to python.
 function updateInput(target) {
-	let e = new Event("input", { bubbles: true })
-	Object.defineProperty(e, "target", {value: target})
+    let e = new Event("input", {bubbles: true});
+    Object.defineProperty(e, "target", {value: target});
     target.dispatchEvent(e);
 }
+
+
+var desiredCheckpointName = null;
+function selectCheckpoint(name) {
+    desiredCheckpointName = name;
+    gradioApp().getElementById('change_checkpoint').click();
+}
+
+function currentImg2imgSourceResolution(w, h, scaleBy) {
+    var img = gradioApp().querySelector('#mode_img2img > div[style="display: block;"] img');
+    return img ? [img.naturalWidth, img.naturalHeight, scaleBy] : [0, 0, scaleBy];
+}
+
+function updateImg2imgResizeToTextAfterChangingImage() {
+    // At the time this is called from gradio, the image has no yet been replaced.
+    // There may be a better solution, but this is simple and straightforward so I'm going with it.
+
+    setTimeout(function() {
+        gradioApp().getElementById('img2img_update_resize_to').click();
+    }, 500);
+
+    return [];
+
+}
+
+
+
+function setRandomSeed(elem_id) {
+    var input = gradioApp().querySelector("#" + elem_id + " input");
+    if (!input) return [];
+
+    input.value = "-1";
+    updateInput(input);
+    return [];
+}
+
+function switchWidthHeight(tabname) {
+    var width = gradioApp().querySelector("#" + tabname + "_width input[type=number]");
+    var height = gradioApp().querySelector("#" + tabname + "_height input[type=number]");
+    if (!width || !height) return [];
+
+    var tmp = width.value;
+    width.value = height.value;
+    height.value = tmp;
+
+    updateInput(width);
+    updateInput(height);
+    return [];
+}
+
+
+var onEditTimers = {};
+
+// calls func after afterMs milliseconds has passed since the input elem has beed enited by user
+function onEdit(editId, elem, afterMs, func) {
+    var edited = function() {
+        var existingTimer = onEditTimers[editId];
+        if (existingTimer) clearTimeout(existingTimer);
+
+        onEditTimers[editId] = setTimeout(func, afterMs);
+    };
+
+    elem.addEventListener("input", edited);
+
+    return edited;
+}

javascript/ui_settings_hints.js

@@ -0,0 +1,62 @@
+// various hints and extra info for the settings tab
+
+var settingsHintsSetup = false;
+
+onOptionsChanged(function() {
+    if (settingsHintsSetup) return;
+    settingsHintsSetup = true;
+
+    gradioApp().querySelectorAll('#settings [id^=setting_]').forEach(function(div) {
+        var name = div.id.substr(8);
+        var commentBefore = opts._comments_before[name];
+        var commentAfter = opts._comments_after[name];
+
+        if (!commentBefore && !commentAfter) return;
+
+        var span = null;
+        if (div.classList.contains('gradio-checkbox')) span = div.querySelector('label span');
+        else if (div.classList.contains('gradio-checkboxgroup')) span = div.querySelector('span').firstChild;
+        else if (div.classList.contains('gradio-radio')) span = div.querySelector('span').firstChild;
+        else span = div.querySelector('label span').firstChild;
+
+        if (!span) return;
+
+        if (commentBefore) {
+            var comment = document.createElement('DIV');
+            comment.className = 'settings-comment';
+            comment.innerHTML = commentBefore;
+            span.parentElement.insertBefore(document.createTextNode('\xa0'), span);
+            span.parentElement.insertBefore(comment, span);
+            span.parentElement.insertBefore(document.createTextNode('\xa0'), span);
+        }
+        if (commentAfter) {
+            comment = document.createElement('DIV');
+            comment.className = 'settings-comment';
+            comment.innerHTML = commentAfter;
+            span.parentElement.insertBefore(comment, span.nextSibling);
+            span.parentElement.insertBefore(document.createTextNode('\xa0'), span.nextSibling);
+        }
+    });
+});
+
+function settingsHintsShowQuicksettings() {
+    requestGet("./internal/quicksettings-hint", {}, function(data) {
+        var table = document.createElement('table');
+        table.className = 'popup-table';
+
+        data.forEach(function(obj) {
+            var tr = document.createElement('tr');
+            var td = document.createElement('td');
+            td.textContent = obj.name;
+            tr.appendChild(td);
+
+            td = document.createElement('td');
+            td.textContent = obj.label;
+            tr.appendChild(td);
+
+            table.appendChild(tr);
+        });
+
+        popup(table);
+    });
+}

launch.py

@@ -1,330 +1,48 @@
-# this scripts installs necessary requirements and launches main program in webui.py
-import subprocess
-import os
-import sys
-import importlib.util
-import shlex
-import platform
-import argparse
-import json
+from modules import launch_utils
 
-dir_repos = "repositories"
-dir_extensions = "extensions"
-python = sys.executable
-git = os.environ.get('GIT', "git")
-index_url = os.environ.get('INDEX_URL', "")
-stored_commit_hash = None
-skip_install = False
+args = launch_utils.args
+python = launch_utils.python
+git = launch_utils.git
+index_url = launch_utils.index_url
+dir_repos = launch_utils.dir_repos
 
+commit_hash = launch_utils.commit_hash
+git_tag = launch_utils.git_tag
 
-def commit_hash():
-    global stored_commit_hash
+run = launch_utils.run
+is_installed = launch_utils.is_installed
+repo_dir = launch_utils.repo_dir
 
-    if stored_commit_hash is not None:
-        return stored_commit_hash
+run_pip = launch_utils.run_pip
+check_run_python = launch_utils.check_run_python
+git_clone = launch_utils.git_clone
+git_pull_recursive = launch_utils.git_pull_recursive
+list_extensions = launch_utils.list_extensions
+run_extension_installer = launch_utils.run_extension_installer
+prepare_environment = launch_utils.prepare_environment
+configure_for_tests = launch_utils.configure_for_tests
+start = launch_utils.start
 
-    try:
-        stored_commit_hash = run(f"{git} rev-parse HEAD").strip()
-    except Exception:
-        stored_commit_hash = "<none>"
 
-    return stored_commit_hash
+def main():
+    if args.dump_sysinfo:
+        filename = launch_utils.dump_sysinfo()
 
+        print(f"Sysinfo saved as {filename}. Exiting...")
 
-def extract_arg(args, name):
-    return [x for x in args if x != name], name in args
-
-
-def extract_opt(args, name):
-    opt = None
-    is_present = False
-    if name in args:
-        is_present = True
-        idx = args.index(name)
-        del args[idx]
-        if idx < len(args) and args[idx][0] != "-":
-            opt = args[idx]
-            del args[idx]
-    return args, is_present, opt
-
-
-def run(command, desc=None, errdesc=None, custom_env=None, live=False):
-    if desc is not None:
-        print(desc)
-
-    if live:
-        result = subprocess.run(command, shell=True, env=os.environ if custom_env is None else custom_env)
-        if result.returncode != 0:
-            raise RuntimeError(f"""{errdesc or 'Error running command'}.
-Command: {command}
-Error code: {result.returncode}""")
-
-        return ""
-
-    result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True, env=os.environ if custom_env is None else custom_env)
-
-    if result.returncode != 0:
-
-        message = f"""{errdesc or 'Error running command'}.
-Command: {command}
-Error code: {result.returncode}
-stdout: {result.stdout.decode(encoding="utf8", errors="ignore") if len(result.stdout)>0 else '<empty>'}
-stderr: {result.stderr.decode(encoding="utf8", errors="ignore") if len(result.stderr)>0 else '<empty>'}
-"""
-        raise RuntimeError(message)
-
-    return result.stdout.decode(encoding="utf8", errors="ignore")
-
-
-def check_run(command):
-    result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
-    return result.returncode == 0
-
-
-def is_installed(package):
-    try:
-        spec = importlib.util.find_spec(package)
-    except ModuleNotFoundError:
-        return False
-
-    return spec is not None
-
-
-def repo_dir(name):
-    return os.path.join(dir_repos, name)
-
-
-def run_python(code, desc=None, errdesc=None):
-    return run(f'"{python}" -c "{code}"', desc, errdesc)
-
-
-def run_pip(args, desc=None):
-    if skip_install:
-        return
-
-    index_url_line = f' --index-url {index_url}' if index_url != '' else ''
-    return run(f'"{python}" -m pip {args} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
-
-
-def check_run_python(code):
-    return check_run(f'"{python}" -c "{code}"')
-
-
-def git_clone(url, dir, name, commithash=None):
-    # TODO clone into temporary dir and move if successful
-
-    if os.path.exists(dir):
-        if commithash is None:
-            return
-
-        current_hash = run(f'"{git}" -C "{dir}" rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}").strip()
-        if current_hash == commithash:
-            return
-
-        run(f'"{git}" -C "{dir}" fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}")
-        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}")
-        return
-
-    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}")
-
-    if commithash is not None:
-        run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
-
-        
-def version_check(commit):
-    try:
-        import requests
-        commits = requests.get('https://api.github.com/repos/AUTOMATIC1111/stable-diffusion-webui/branches/master').json()
-        if commit != "<none>" and commits['commit']['sha'] != commit:
-            print("--------------------------------------------------------")
-            print("| You are not up to date with the most recent release. |")
-            print("| Consider running `git pull` to update.               |")
-            print("--------------------------------------------------------")
-        elif commits['commit']['sha'] == commit:
-            print("You are up to date with the most recent release.")
-        else:
-            print("Not a git clone, can't perform version check.")
-    except Exception as e:
-        print("version check failed", e)
-
-
-def run_extension_installer(extension_dir):
-    path_installer = os.path.join(extension_dir, "install.py")
-    if not os.path.isfile(path_installer):
-        return
-
-    try:
-        env = os.environ.copy()
-        env['PYTHONPATH'] = os.path.abspath(".")
-
-        print(run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env))
-    except Exception as e:
-        print(e, file=sys.stderr)
-
-
-def list_extensions(settings_file):
-    settings = {}
-
-    try:
-        if os.path.isfile(settings_file):
-            with open(settings_file, "r", encoding="utf8") as file:
-                settings = json.load(file)
-    except Exception as e:
-        print(e, file=sys.stderr)
-
-    disabled_extensions = set(settings.get('disabled_extensions', []))
-
-    return [x for x in os.listdir(dir_extensions) if x not in disabled_extensions]
-
-
-def run_extensions_installers(settings_file):
-    if not os.path.isdir(dir_extensions):
-        return
-
-    for dirname_extension in list_extensions(settings_file):
-        run_extension_installer(os.path.join(dir_extensions, dirname_extension))
-
-
-def prepare_environment():
-    global skip_install
-
-    pip_installer_location = os.environ.get('PIP_INSTALLER_LOCATION', None)
-
-    torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117")
-    requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
-    commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
-
-    gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
-    clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
-    openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b")
-
-    stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
-    taming_transformers_repo = os.environ.get('TAMING_TRANSFORMERS_REPO', "https://github.com/CompVis/taming-transformers.git")
-    k_diffusion_repo = os.environ.get('K_DIFFUSION_REPO', 'https://github.com/crowsonkb/k-diffusion.git')
-    codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
-    blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
-
-    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "47b6b607fdd31875c9279cd2f4f16b92e4ea958e")
-    taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
-    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "5b3af030dd83e0297272d861c19477735d0317ec")
-    codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
-    blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
-
-    sys.argv += shlex.split(commandline_args)
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default='config.json')
-    args, _ = parser.parse_known_args(sys.argv)
-
-    sys.argv, _ = extract_arg(sys.argv, '-f')
-    sys.argv, skip_torch_cuda_test = extract_arg(sys.argv, '--skip-torch-cuda-test')
-    sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
-    sys.argv, reinstall_torch = extract_arg(sys.argv, '--reinstall-torch')
-    sys.argv, update_check = extract_arg(sys.argv, '--update-check')
-    sys.argv, run_tests, test_dir = extract_opt(sys.argv, '--tests')
-    sys.argv, skip_install = extract_arg(sys.argv, '--skip-install')
-    xformers = '--xformers' in sys.argv
-    ngrok = '--ngrok' in sys.argv
-
-    commit = commit_hash()
-
-    print(f"Python {sys.version}")
-    print(f"Commit hash: {commit}")
-
-    if pip_installer_location is not None and not is_installed("pip"):
-        run(f'"{python}" "{pip_installer_location}"', "Installing pip", "Couldn't install pip")
-
-    if reinstall_torch or not is_installed("torch") or not is_installed("torchvision"):
-        run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
-
-    if not skip_torch_cuda_test:
-        run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
-
-    if not is_installed("gfpgan"):
-        run_pip(f"install {gfpgan_package}", "gfpgan")
-
-    if not is_installed("clip"):
-        run_pip(f"install {clip_package}", "clip")
-
-    if not is_installed("open_clip"):
-        run_pip(f"install {openclip_package}", "open_clip")
-
-    if (not is_installed("xformers") or reinstall_xformers) and xformers:
-        if platform.system() == "Windows":
-            if platform.python_version().startswith("3.10"):
-                run_pip(f"install -U -I --no-deps xformers==0.0.16rc425", "xformers")
-            else:
-                print("Installation of xformers is not supported in this version of Python.")
-                print("You can also check this and build manually: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers#building-xformers-on-windows-by-duckness")
-                if not is_installed("xformers"):
-                    exit(0)
-        elif platform.system() == "Linux":
-            run_pip("install xformers==0.0.16rc425", "xformers")
-
-    if not is_installed("pyngrok") and ngrok:
-        run_pip("install pyngrok", "ngrok")
-
-    os.makedirs(dir_repos, exist_ok=True)
-
-    git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
-    git_clone(taming_transformers_repo, repo_dir('taming-transformers'), "Taming Transformers", taming_transformers_commit_hash)
-    git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
-    git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
-    git_clone(blip_repo, repo_dir('BLIP'), "BLIP", blip_commit_hash)
-
-    if not is_installed("lpips"):
-        run_pip(f"install -r {os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}", "requirements for CodeFormer")
-
-    run_pip(f"install -r {requirements_file}", "requirements for Web UI")
-
-    run_extensions_installers(settings_file=args.ui_settings_file)
-
-    if update_check:
-        version_check(commit)
-    
-    if "--exit" in sys.argv:
-        print("Exiting because of --exit argument")
         exit(0)
 
-    if run_tests:
-        exitcode = tests(test_dir)
-        exit(exitcode)
+    launch_utils.startup_timer.record("initial startup")
 
+    with launch_utils.startup_timer.subcategory("prepare environment"):
+        if not args.skip_prepare_environment:
+            prepare_environment()
 
-def tests(test_dir):
-    if "--api" not in sys.argv:
-        sys.argv.append("--api")
-    if "--ckpt" not in sys.argv:
-        sys.argv.append("--ckpt")
-        sys.argv.append("./test/test_files/empty.pt")
-    if "--skip-torch-cuda-test" not in sys.argv:
-        sys.argv.append("--skip-torch-cuda-test")
-    if "--disable-nan-check" not in sys.argv:
-        sys.argv.append("--disable-nan-check")
+    if args.test_server:
+        configure_for_tests()
 
-    print(f"Launching Web UI in another process for testing with arguments: {' '.join(sys.argv[1:])}")
-
-    os.environ['COMMANDLINE_ARGS'] = ""
-    with open('test/stdout.txt', "w", encoding="utf8") as stdout, open('test/stderr.txt', "w", encoding="utf8") as stderr:
-        proc = subprocess.Popen([sys.executable, *sys.argv], stdout=stdout, stderr=stderr)
-
-    import test.server_poll
-    exitcode = test.server_poll.run_tests(proc, test_dir)
-
-    print(f"Stopping Web UI process with id {proc.pid}")
-    proc.kill()
-    return exitcode
-
-
-def start():
-    print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with arguments: {' '.join(sys.argv[1:])}")
-    import webui
-    if '--nowebui' in sys.argv:
-        webui.api_only()
-    else:
-        webui.webui()
+    start()
 
 
 if __name__ == "__main__":
-    prepare_environment()
-    start()
+    main()

modules/api/api.py

@@ -1,41 +1,46 @@
 import base64
 import io
+import os
 import time
 import datetime
 import uvicorn
+import ipaddress
+import requests
+import gradio as gr
 from threading import Lock
 from io import BytesIO
-from gradio.processing_utils import decode_base64_to_file
-from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request, Response
+from fastapi import APIRouter, Depends, FastAPI, Request, Response
 from fastapi.security import HTTPBasic, HTTPBasicCredentials
+from fastapi.exceptions import HTTPException
+from fastapi.responses import JSONResponse
+from fastapi.encoders import jsonable_encoder
 from secrets import compare_digest
 
 import modules.shared as shared
-from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing
-from modules.api.models import *
+from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste
+from modules.api import models
+from modules.shared import opts
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
 from modules.textual_inversion.textual_inversion import create_embedding, train_embedding
 from modules.textual_inversion.preprocess import preprocess
 from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
 from PIL import PngImagePlugin,Image
-from modules.sd_models import checkpoints_list, find_checkpoint_config
+from modules.sd_models import unload_model_weights, reload_model_weights, checkpoint_aliases
+from modules.sd_models_config import find_checkpoint_config_near_filename
 from modules.realesrgan_model import get_realesrgan_models
 from modules import devices
-from typing import List
+from typing import Any
 import piexif
 import piexif.helper
+from contextlib import closing
 
-def upscaler_to_index(name: str):
-    try:
-        return [x.name.lower() for x in shared.sd_upscalers].index(name.lower())
-    except:
-        raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in sd_upscalers])}")
 
 def script_name_to_index(name, scripts):
     try:
         return [script.title().lower() for script in scripts].index(name.lower())
-    except:
-        raise HTTPException(status_code=422, detail=f"Script '{name}' not found")
+    except Exception as e:
+        raise HTTPException(status_code=422, detail=f"Script '{name}' not found") from e
+
 
 def validate_sampler_name(name):
     config = sd_samplers.all_samplers_map.get(name, None)
@@ -44,20 +49,57 @@ def validate_sampler_name(name):
 
     return name
 
+
 def setUpscalers(req: dict):
     reqDict = vars(req)
     reqDict['extras_upscaler_1'] = reqDict.pop('upscaler_1', None)
     reqDict['extras_upscaler_2'] = reqDict.pop('upscaler_2', None)
     return reqDict
 
+
+def verify_url(url):
+    """Returns True if the url refers to a global resource."""
+
+    import socket
+    from urllib.parse import urlparse
+    try:
+        parsed_url = urlparse(url)
+        domain_name = parsed_url.netloc
+        host = socket.gethostbyname_ex(domain_name)
+        for ip in host[2]:
+            ip_addr = ipaddress.ip_address(ip)
+            if not ip_addr.is_global:
+                return False
+    except Exception:
+        return False
+
+    return True
+
+
 def decode_base64_to_image(encoding):
+    if encoding.startswith("http://") or encoding.startswith("https://"):
+        if not opts.api_enable_requests:
+            raise HTTPException(status_code=500, detail="Requests not allowed")
+
+        if opts.api_forbid_local_requests and not verify_url(encoding):
+            raise HTTPException(status_code=500, detail="Request to local resource not allowed")
+
+        headers = {'user-agent': opts.api_useragent} if opts.api_useragent else {}
+        response = requests.get(encoding, timeout=30, headers=headers)
+        try:
+            image = Image.open(BytesIO(response.content))
+            return image
+        except Exception as e:
+            raise HTTPException(status_code=500, detail="Invalid image url") from e
+
     if encoding.startswith("data:image/"):
         encoding = encoding.split(";")[1].split(",")[1]
     try:
         image = Image.open(BytesIO(base64.b64decode(encoding)))
         return image
-    except Exception as err:
-        raise HTTPException(status_code=500, detail="Invalid encoded image")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Invalid encoded image") from e
+
 
 def encode_pil_to_base64(image):
     with io.BytesIO() as output_bytes:
@@ -72,6 +114,8 @@ def encode_pil_to_base64(image):
             image.save(output_bytes, format="PNG", pnginfo=(metadata if use_metadata else None), quality=opts.jpeg_quality)
 
         elif opts.samples_format.lower() in ("jpg", "jpeg", "webp"):
+            if image.mode == "RGBA":
+                image = image.convert("RGB")
             parameters = image.info.get('parameters', None)
             exif_bytes = piexif.dump({
                 "Exif": { piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(parameters or "", encoding="unicode") }
@@ -88,7 +132,19 @@ def encode_pil_to_base64(image):
 
     return base64.b64encode(bytes_data)
 
+
 def api_middleware(app: FastAPI):
+    rich_available = False
+    try:
+        if os.environ.get('WEBUI_RICH_EXCEPTIONS', None) is not None:
+            import anyio  # importing just so it can be placed on silent list
+            import starlette  # importing just so it can be placed on silent list
+            from rich.console import Console
+            console = Console()
+            rich_available = True
+    except Exception:
+        pass
+
     @app.middleware("http")
     async def log_and_time(req: Request, call_next):
         ts = time.time()
@@ -109,11 +165,42 @@ def api_middleware(app: FastAPI):
             ))
         return res
 
+    def handle_exception(request: Request, e: Exception):
+        err = {
+            "error": type(e).__name__,
+            "detail": vars(e).get('detail', ''),
+            "body": vars(e).get('body', ''),
+            "errors": str(e),
+        }
+        if not isinstance(e, HTTPException):  # do not print backtrace on known httpexceptions
+            message = f"API error: {request.method}: {request.url} {err}"
+            if rich_available:
+                print(message)
+                console.print_exception(show_locals=True, max_frames=2, extra_lines=1, suppress=[anyio, starlette], word_wrap=False, width=min([console.width, 200]))
+            else:
+                errors.report(message, exc_info=True)
+        return JSONResponse(status_code=vars(e).get('status_code', 500), content=jsonable_encoder(err))
+
+    @app.middleware("http")
+    async def exception_handling(request: Request, call_next):
+        try:
+            return await call_next(request)
+        except Exception as e:
+            return handle_exception(request, e)
+
+    @app.exception_handler(Exception)
+    async def fastapi_exception_handler(request: Request, e: Exception):
+        return handle_exception(request, e)
+
+    @app.exception_handler(HTTPException)
+    async def http_exception_handler(request: Request, e: HTTPException):
+        return handle_exception(request, e)
+
 
 class Api:
     def __init__(self, app: FastAPI, queue_lock: Lock):
         if shared.cmd_opts.api_auth:
-            self.credentials = dict()
+            self.credentials = {}
             for auth in shared.cmd_opts.api_auth.split(","):
                 user, password = auth.split(":")
                 self.credentials[user] = password
@@ -122,33 +209,49 @@ class Api:
         self.app = app
         self.queue_lock = queue_lock
         api_middleware(self.app)
-        self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse)
-        self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse)
-        self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse)
-        self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse)
-        self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse)
-        self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse)
+        self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=models.TextToImageResponse)
+        self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=models.ImageToImageResponse)
+        self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=models.ExtrasSingleImageResponse)
+        self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=models.ExtrasBatchImagesResponse)
+        self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=models.PNGInfoResponse)
+        self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=models.ProgressResponse)
         self.add_api_route("/sdapi/v1/interrogate", self.interrogateapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/interrupt", self.interruptapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/skip", self.skip, methods=["POST"])
-        self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=OptionsModel)
+        self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=models.OptionsModel)
         self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"])
-        self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=FlagsModel)
-        self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem])
-        self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[UpscalerItem])
-        self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[SDModelItem])
-        self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem])
-        self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem])
-        self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem])
-        self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem])
-        self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse)
+        self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel)
+        self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=list[models.SamplerItem])
+        self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=list[models.UpscalerItem])
+        self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=list[models.LatentUpscalerModeItem])
+        self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=list[models.SDModelItem])
+        self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=list[models.SDVaeItem])
+        self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=list[models.HypernetworkItem])
+        self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=list[models.FaceRestorerItem])
+        self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=list[models.RealesrganItem])
+        self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=list[models.PromptStyleItem])
+        self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse)
         self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
-        self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse)
-        self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse)
-        self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse)
-        self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse)
-        self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse)
-        self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse)
+        self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"])
+        self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse)
+        self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse)
+        self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse)
+        self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse)
+        self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse)
+        self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse)
+        self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"])
+        self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"])
+        self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList)
+        self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=list[models.ScriptInfo])
+        self.add_api_route("/sdapi/v1/extensions", self.get_extensions_list, methods=["GET"], response_model=list[models.ExtensionItem])
+
+        if shared.cmd_opts.api_server_stop:
+            self.add_api_route("/sdapi/v1/server-kill", self.kill_webui, methods=["POST"])
+            self.add_api_route("/sdapi/v1/server-restart", self.restart_webui, methods=["POST"])
+            self.add_api_route("/sdapi/v1/server-stop", self.stop_webui, methods=["POST"])
+
+        self.default_script_arg_txt2img = []
+        self.default_script_arg_img2img = []
 
     def add_api_route(self, path: str, endpoint, **kwargs):
         if shared.cmd_opts.api_auth:
@@ -162,98 +265,194 @@ class Api:
 
         raise HTTPException(status_code=401, detail="Incorrect username or password", headers={"WWW-Authenticate": "Basic"})
 
-    def get_script(self, script_name, script_runner):
-        if script_name is None:
+    def get_selectable_script(self, script_name, script_runner):
+        if script_name is None or script_name == "":
             return None, None
 
-        if not script_runner.scripts:
-            script_runner.initialize_scripts(False)
-            ui.create_ui()
-
         script_idx = script_name_to_index(script_name, script_runner.selectable_scripts)
         script = script_runner.selectable_scripts[script_idx]
         return script, script_idx
 
-    def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
-        script, script_idx = self.get_script(txt2imgreq.script_name, scripts.scripts_txt2img)
+    def get_scripts_list(self):
+        t2ilist = [script.name for script in scripts.scripts_txt2img.scripts if script.name is not None]
+        i2ilist = [script.name for script in scripts.scripts_img2img.scripts if script.name is not None]
+
+        return models.ScriptsList(txt2img=t2ilist, img2img=i2ilist)
+
+    def get_script_info(self):
+        res = []
+
+        for script_list in [scripts.scripts_txt2img.scripts, scripts.scripts_img2img.scripts]:
+            res += [script.api_info for script in script_list if script.api_info is not None]
+
+        return res
+
+    def get_script(self, script_name, script_runner):
+        if script_name is None or script_name == "":
+            return None, None
+
+        script_idx = script_name_to_index(script_name, script_runner.scripts)
+        return script_runner.scripts[script_idx]
+
+    def init_default_script_args(self, script_runner):
+        #find max idx from the scripts in runner and generate a none array to init script_args
+        last_arg_index = 1
+        for script in script_runner.scripts:
+            if last_arg_index < script.args_to:
+                last_arg_index = script.args_to
+        # None everywhere except position 0 to initialize script args
+        script_args = [None]*last_arg_index
+        script_args[0] = 0
+
+        # get default values
+        with gr.Blocks(): # will throw errors calling ui function without this
+            for script in script_runner.scripts:
+                if script.ui(script.is_img2img):
+                    ui_default_values = []
+                    for elem in script.ui(script.is_img2img):
+                        ui_default_values.append(elem.value)
+                    script_args[script.args_from:script.args_to] = ui_default_values
+        return script_args
+
+    def init_script_args(self, request, default_script_args, selectable_scripts, selectable_idx, script_runner):
+        script_args = default_script_args.copy()
+        # position 0 in script_arg is the idx+1 of the selectable script that is going to be run when using scripts.scripts_*2img.run()
+        if selectable_scripts:
+            script_args[selectable_scripts.args_from:selectable_scripts.args_to] = request.script_args
+            script_args[0] = selectable_idx + 1
+
+        # Now check for always on scripts
+        if request.alwayson_scripts:
+            for alwayson_script_name in request.alwayson_scripts.keys():
+                alwayson_script = self.get_script(alwayson_script_name, script_runner)
+                if alwayson_script is None:
+                    raise HTTPException(status_code=422, detail=f"always on script {alwayson_script_name} not found")
+                # Selectable script in always on script param check
+                if alwayson_script.alwayson is False:
+                    raise HTTPException(status_code=422, detail="Cannot have a selectable script in the always on scripts params")
+                # always on script with no arg should always run so you don't really need to add them to the requests
+                if "args" in request.alwayson_scripts[alwayson_script_name]:
+                    # min between arg length in scriptrunner and arg length in the request
+                    for idx in range(0, min((alwayson_script.args_to - alwayson_script.args_from), len(request.alwayson_scripts[alwayson_script_name]["args"]))):
+                        script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx]
+        return script_args
+
+    def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI):
+        script_runner = scripts.scripts_txt2img
+        if not script_runner.scripts:
+            script_runner.initialize_scripts(False)
+            ui.create_ui()
+        if not self.default_script_arg_txt2img:
+            self.default_script_arg_txt2img = self.init_default_script_args(script_runner)
+        selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner)
 
         populate = txt2imgreq.copy(update={  # Override __init__ params
             "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index),
-            "do_not_save_samples": True,
-            "do_not_save_grid": True
-            }
-        )
+            "do_not_save_samples": not txt2imgreq.save_images,
+            "do_not_save_grid": not txt2imgreq.save_images,
+        })
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
         args = vars(populate)
         args.pop('script_name', None)
+        args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them
+        args.pop('alwayson_scripts', None)
+
+        script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner)
+
+        send_images = args.pop('send_images', True)
+        args.pop('save_images', None)
 
         with self.queue_lock:
-            p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)
-
-            shared.state.begin()
-            if script is not None:
+            with closing(StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)) as p:
+                p.is_api = True
+                p.scripts = script_runner
                 p.outpath_grids = opts.outdir_txt2img_grids
                 p.outpath_samples = opts.outdir_txt2img_samples
-                p.script_args = [script_idx + 1] + [None] * (script.args_from - 1) + p.script_args
-                processed = scripts.scripts_txt2img.run(p, *p.script_args)
+
+                try:
+                    shared.state.begin(job="scripts_txt2img")
+                    if selectable_scripts is not None:
+                        p.script_args = script_args
+                        processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here
                     else:
+                        p.script_args = tuple(script_args) # Need to pass args as tuple here
                         processed = process_images(p)
+                finally:
                     shared.state.end()
+                    shared.total_tqdm.clear()
 
-        b64images = list(map(encode_pil_to_base64, processed.images))
+        b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else []
 
-        return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
+        return models.TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
-    def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
+    def img2imgapi(self, img2imgreq: models.StableDiffusionImg2ImgProcessingAPI):
         init_images = img2imgreq.init_images
         if init_images is None:
             raise HTTPException(status_code=404, detail="Init image not found")
 
-        script, script_idx = self.get_script(img2imgreq.script_name, scripts.scripts_img2img)
-
         mask = img2imgreq.mask
         if mask:
             mask = decode_base64_to_image(mask)
 
+        script_runner = scripts.scripts_img2img
+        if not script_runner.scripts:
+            script_runner.initialize_scripts(True)
+            ui.create_ui()
+        if not self.default_script_arg_img2img:
+            self.default_script_arg_img2img = self.init_default_script_args(script_runner)
+        selectable_scripts, selectable_script_idx = self.get_selectable_script(img2imgreq.script_name, script_runner)
+
         populate = img2imgreq.copy(update={  # Override __init__ params
             "sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index),
-            "do_not_save_samples": True,
-            "do_not_save_grid": True,
-            "mask": mask
-            }
-        )
+            "do_not_save_samples": not img2imgreq.save_images,
+            "do_not_save_grid": not img2imgreq.save_images,
+            "mask": mask,
+        })
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
         args = vars(populate)
         args.pop('include_init_images', None)  # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine.
         args.pop('script_name', None)
+        args.pop('script_args', None)  # will refeed them to the pipeline directly after initializing them
+        args.pop('alwayson_scripts', None)
+
+        script_args = self.init_script_args(img2imgreq, self.default_script_arg_img2img, selectable_scripts, selectable_script_idx, script_runner)
+
+        send_images = args.pop('send_images', True)
+        args.pop('save_images', None)
 
         with self.queue_lock:
-            p = StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)
+            with closing(StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)) as p:
                 p.init_images = [decode_base64_to_image(x) for x in init_images]
-
-            shared.state.begin()
-            if script is not None:
+                p.is_api = True
+                p.scripts = script_runner
                 p.outpath_grids = opts.outdir_img2img_grids
                 p.outpath_samples = opts.outdir_img2img_samples
-                p.script_args = [script_idx + 1] + [None] * (script.args_from - 1) + p.script_args
-                processed = scripts.scripts_img2img.run(p, *p.script_args)
-            else:
-                processed = process_images(p)
-            shared.state.end()
 
-        b64images = list(map(encode_pil_to_base64, processed.images))
+                try:
+                    shared.state.begin(job="scripts_img2img")
+                    if selectable_scripts is not None:
+                        p.script_args = script_args
+                        processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here
+                    else:
+                        p.script_args = tuple(script_args) # Need to pass args as tuple here
+                        processed = process_images(p)
+                finally:
+                    shared.state.end()
+                    shared.total_tqdm.clear()
+
+        b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else []
 
         if not img2imgreq.include_init_images:
             img2imgreq.init_images = None
             img2imgreq.mask = None
 
-        return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
+        return models.ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
 
-    def extras_single_image_api(self, req: ExtrasSingleImageRequest):
+    def extras_single_image_api(self, req: models.ExtrasSingleImageRequest):
         reqDict = setUpscalers(req)
 
         reqDict['image'] = decode_base64_to_image(reqDict['image'])
@@ -261,45 +460,38 @@ class Api:
         with self.queue_lock:
             result = postprocessing.run_extras(extras_mode=0, image_folder="", input_dir="", output_dir="", save_output=False, **reqDict)
 
-        return ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1])
+        return models.ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1])
 
-    def extras_batch_images_api(self, req: ExtrasBatchImagesRequest):
+    def extras_batch_images_api(self, req: models.ExtrasBatchImagesRequest):
         reqDict = setUpscalers(req)
 
-        def prepareFiles(file):
-            file = decode_base64_to_file(file.data, file_path=file.name)
-            file.orig_name = file.name
-            return file
-
-        reqDict['image_folder'] = list(map(prepareFiles, reqDict['imageList']))
-        reqDict.pop('imageList')
+        image_list = reqDict.pop('imageList', [])
+        image_folder = [decode_base64_to_image(x.data) for x in image_list]
 
         with self.queue_lock:
-            result = postprocessing.run_extras(extras_mode=1, image="", input_dir="", output_dir="", save_output=False, **reqDict)
+            result = postprocessing.run_extras(extras_mode=1, image_folder=image_folder, image="", input_dir="", output_dir="", save_output=False, **reqDict)
 
-        return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
-
-    def pnginfoapi(self, req: PNGInfoRequest):
-        if(not req.image.strip()):
-            return PNGInfoResponse(info="")
+        return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
 
+    def pnginfoapi(self, req: models.PNGInfoRequest):
         image = decode_base64_to_image(req.image.strip())
         if image is None:
-            return PNGInfoResponse(info="")
+            return models.PNGInfoResponse(info="")
 
         geninfo, items = images.read_info_from_image(image)
         if geninfo is None:
             geninfo = ""
 
-        items = {**{'parameters': geninfo}, **items}
+        params = generation_parameters_copypaste.parse_generation_parameters(geninfo)
+        script_callbacks.infotext_pasted_callback(geninfo, params)
 
-        return PNGInfoResponse(info=geninfo, items=items)
+        return models.PNGInfoResponse(info=geninfo, items=items, parameters=params)
 
-    def progressapi(self, req: ProgressRequest = Depends()):
+    def progressapi(self, req: models.ProgressRequest = Depends()):
         # copy from check_progress_call of ui.py
 
         if shared.state.job_count == 0:
-            return ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo)
+            return models.ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo)
 
         # avoid dividing zero
         progress = 0.01
@@ -321,9 +513,9 @@ class Api:
         if shared.state.current_image and not req.skip_current_image:
             current_image = encode_pil_to_base64(shared.state.current_image)
 
-        return ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
+        return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
 
-    def interrogateapi(self, interrogatereq: InterrogateRequest):
+    def interrogateapi(self, interrogatereq: models.InterrogateRequest):
         image_b64 = interrogatereq.image
         if image_b64 is None:
             raise HTTPException(status_code=404, detail="Image not found")
@@ -340,13 +532,23 @@ class Api:
             else:
                 raise HTTPException(status_code=404, detail="Model not found")
 
-        return InterrogateResponse(caption=processed)
+        return models.InterrogateResponse(caption=processed)
 
     def interruptapi(self):
         shared.state.interrupt()
 
         return {}
 
+    def unloadapi(self):
+        unload_model_weights()
+
+        return {}
+
+    def reloadapi(self):
+        reload_model_weights()
+
+        return {}
+
     def skip(self):
         shared.state.skip()
 
@@ -361,9 +563,13 @@ class Api:
 
         return options
 
-    def set_config(self, req: Dict[str, Any]):
+    def set_config(self, req: dict[str, Any]):
+        checkpoint_name = req.get("sd_model_checkpoint", None)
+        if checkpoint_name is not None and checkpoint_name not in checkpoint_aliases:
+            raise RuntimeError(f"model {checkpoint_name!r} not found")
+
         for k, v in req.items():
-            shared.opts.set(k, v)
+            shared.opts.set(k, v, is_api=True)
 
         shared.opts.save(shared.config_filename)
         return
@@ -386,8 +592,21 @@ class Api:
             for upscaler in shared.sd_upscalers
         ]
 
+    def get_latent_upscale_modes(self):
+        return [
+            {
+                "name": upscale_mode,
+            }
+            for upscale_mode in [*(shared.latent_upscale_modes or {})]
+        ]
+
     def get_sd_models(self):
-        return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config(x)} for x in checkpoints_list.values()]
+        import modules.sd_models as sd_models
+        return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config_near_filename(x)} for x in sd_models.checkpoints_list.values()]
+
+    def get_sd_vaes(self):
+        import modules.sd_vae as sd_vae
+        return [{"model_name": x, "filename": sd_vae.vae_dict[x]} for x in sd_vae.vae_dict.keys()]
 
     def get_hypernetworks(self):
         return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks]
@@ -427,48 +646,51 @@ class Api:
         }
 
     def refresh_checkpoints(self):
+        with self.queue_lock:
             shared.refresh_checkpoints()
 
+    def refresh_vae(self):
+        with self.queue_lock:
+            shared_items.refresh_vae_list()
+
     def create_embedding(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="create_embedding")
             filename = create_embedding(**args) # create empty embedding
             sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings() # reload embeddings so new one can be immediately used
-            shared.state.end()
-            return CreateResponse(info = "create embedding filename: {filename}".format(filename = filename))
+            return models.CreateResponse(info=f"create embedding filename: {filename}")
         except AssertionError as e:
+            return models.TrainResponse(info=f"create embedding error: {e}")
+        finally:
             shared.state.end()
-            return TrainResponse(info = "create embedding error: {error}".format(error = e))
+
 
     def create_hypernetwork(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="create_hypernetwork")
             filename = create_hypernetwork(**args) # create empty embedding
-            shared.state.end()
-            return CreateResponse(info = "create hypernetwork filename: {filename}".format(filename = filename))
+            return models.CreateResponse(info=f"create hypernetwork filename: {filename}")
         except AssertionError as e:
+            return models.TrainResponse(info=f"create hypernetwork error: {e}")
+        finally:
             shared.state.end()
-            return TrainResponse(info = "create hypernetwork error: {error}".format(error = e))
 
     def preprocess(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="preprocess")
             preprocess(**args) # quick operation unless blip/booru interrogation is enabled
             shared.state.end()
-            return PreprocessResponse(info = 'preprocess complete')
+            return models.PreprocessResponse(info='preprocess complete')
         except KeyError as e:
+            return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}")
+        except Exception as e:
+            return models.PreprocessResponse(info=f"preprocess error: {e}")
+        finally:
             shared.state.end()
-            return PreprocessResponse(info = "preprocess error: invalid token: {error}".format(error = e))
-        except AssertionError as e:
-            shared.state.end()
-            return PreprocessResponse(info = "preprocess error: {error}".format(error = e))
-        except FileNotFoundError as e:
-            shared.state.end()
-            return PreprocessResponse(info = 'preprocess error: {error}'.format(error = e))
 
     def train_embedding(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="train_embedding")
             apply_optimizations = shared.opts.training_xattention_optimizations
             error = None
             filename = ''
@@ -481,15 +703,15 @@ class Api:
             finally:
                 if not apply_optimizations:
                     sd_hijack.apply_optimizations()
+            return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
+        except Exception as msg:
+            return models.TrainResponse(info=f"train embedding error: {msg}")
+        finally:
             shared.state.end()
-            return TrainResponse(info = "train embedding complete: filename: {filename} error: {error}".format(filename = filename, error = error))
-        except AssertionError as msg:
-            shared.state.end()
-            return TrainResponse(info = "train embedding error: {msg}".format(msg = msg))
 
     def train_hypernetwork(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="train_hypernetwork")
             shared.loaded_hypernetworks = []
             apply_optimizations = shared.opts.training_xattention_optimizations
             error = None
@@ -497,7 +719,7 @@ class Api:
             if not apply_optimizations:
                 sd_hijack.undo_optimizations()
             try:
-                hypernetwork, filename = train_hypernetwork(*args)
+                hypernetwork, filename = train_hypernetwork(**args)
             except Exception as e:
                 error = e
             finally:
@@ -506,14 +728,16 @@ class Api:
                 if not apply_optimizations:
                     sd_hijack.apply_optimizations()
                 shared.state.end()
-            return TrainResponse(info="train embedding complete: filename: {filename} error: {error}".format(filename=filename, error=error))
-        except AssertionError as msg:
+            return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
+        except Exception as exc:
+            return models.TrainResponse(info=f"train embedding error: {exc}")
+        finally:
             shared.state.end()
-            return TrainResponse(info="train embedding error: {error}".format(error=error))
 
     def get_memory(self):
         try:
-            import os, psutil
+            import os
+            import psutil
             process = psutil.Process(os.getpid())
             res = process.memory_info() # only rss is cross-platform guaranteed so we dont rely on other values
             ram_total = 100 * res.rss / process.memory_percent() # and total memory is calculated as actual value is not cross-platform safe
@@ -543,8 +767,40 @@ class Api:
                 cuda = {'error': 'unavailable'}
         except Exception as err:
             cuda = {'error': f'{err}'}
-        return MemoryResponse(ram = ram, cuda = cuda)
+        return models.MemoryResponse(ram=ram, cuda=cuda)
 
-    def launch(self, server_name, port):
+    def get_extensions_list(self):
+        from modules import extensions
+        extensions.list_extensions()
+        ext_list = []
+        for ext in extensions.extensions:
+            ext: extensions.Extension
+            ext.read_info_from_repo()
+            if ext.remote is not None:
+                ext_list.append({
+                    "name": ext.name,
+                    "remote": ext.remote,
+                    "branch": ext.branch,
+                    "commit_hash":ext.commit_hash,
+                    "commit_date":ext.commit_date,
+                    "version":ext.version,
+                    "enabled":ext.enabled
+                })
+        return ext_list
+
+    def launch(self, server_name, port, root_path):
         self.app.include_router(self.router)
-        uvicorn.run(self.app, host=server_name, port=port)
+        uvicorn.run(self.app, host=server_name, port=port, timeout_keep_alive=shared.cmd_opts.timeout_keep_alive, root_path=root_path)
+
+    def kill_webui(self):
+        restart.stop_program()
+
+    def restart_webui(self):
+        if restart.is_restartable():
+            restart.restart_program()
+        return Response(status_code=501)
+
+    def stop_webui(request):
+        shared.state.server_command = "stop"
+        return Response("Stopping.")
+

modules/api/models.py

@@ -1,11 +1,10 @@
 import inspect
+
 from pydantic import BaseModel, Field, create_model
-from typing import Any, Optional
-from typing_extensions import Literal
+from typing import Any, Optional, Literal
 from inflection import underscore
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
 from modules.shared import sd_upscalers, opts, parser
-from typing import Dict, List
 
 API_NOT_ALLOWED = [
     "self",
@@ -14,8 +13,8 @@ API_NOT_ALLOWED = [
     "outpath_samples",
     "outpath_grids",
     "sampler_index",
-    "do_not_save_samples",
-    "do_not_save_grid",
+    # "do_not_save_samples",
+    # "do_not_save_grid",
     "extra_generation_params",
     "overlay_images",
     "do_not_reload_embeddings",
@@ -49,10 +48,12 @@ class PydanticModelGenerator:
         additional_fields = None,
     ):
         def field_type_generator(k, v):
-            # field_type = str if not overrides.get(k) else overrides[k]["type"]
-            # print(k, v.annotation, v.default)
             field_type = v.annotation
 
+            if field_type == 'Image':
+                # images are sent as base64 strings via API
+                field_type = 'str'
+
             return Optional[field_type]
 
         def merge_class_params(class_):
@@ -62,7 +63,6 @@ class PydanticModelGenerator:
                 parameters = {**parameters, **inspect.signature(classes.__init__).parameters}
             return parameters
 
-
         self._model_name = model_name
         self._class_data = merge_class_params(class_instance)
 
@@ -71,7 +71,7 @@ class PydanticModelGenerator:
                 field=underscore(k),
                 field_alias=k,
                 field_type=field_type_generator(k, v),
-                field_value=v.default
+                field_value=None if isinstance(v.default, property) else v.default
             )
             for (k,v) in self._class_data.items() if k not in API_NOT_ALLOWED
         ]
@@ -100,22 +100,40 @@ class PydanticModelGenerator:
 StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
     "StableDiffusionProcessingTxt2Img",
     StableDiffusionProcessingTxt2Img,
-    [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}]
+    [
+        {"key": "sampler_index", "type": str, "default": "Euler"},
+        {"key": "script_name", "type": str, "default": None},
+        {"key": "script_args", "type": list, "default": []},
+        {"key": "send_images", "type": bool, "default": True},
+        {"key": "save_images", "type": bool, "default": False},
+        {"key": "alwayson_scripts", "type": dict, "default": {}},
+    ]
 ).generate_model()
 
 StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
     "StableDiffusionProcessingImg2Img",
     StableDiffusionProcessingImg2Img,
-    [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}]
+    [
+        {"key": "sampler_index", "type": str, "default": "Euler"},
+        {"key": "init_images", "type": list, "default": None},
+        {"key": "denoising_strength", "type": float, "default": 0.75},
+        {"key": "mask", "type": str, "default": None},
+        {"key": "include_init_images", "type": bool, "default": False, "exclude" : True},
+        {"key": "script_name", "type": str, "default": None},
+        {"key": "script_args", "type": list, "default": []},
+        {"key": "send_images", "type": bool, "default": True},
+        {"key": "save_images", "type": bool, "default": False},
+        {"key": "alwayson_scripts", "type": dict, "default": {}},
+    ]
 ).generate_model()
 
 class TextToImageResponse(BaseModel):
-    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
     parameters: dict
     info: str
 
 class ImageToImageResponse(BaseModel):
-    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
     parameters: dict
     info: str
 
@@ -148,17 +166,18 @@ class FileData(BaseModel):
     name: str = Field(title="File name")
 
 class ExtrasBatchImagesRequest(ExtrasBaseRequest):
-    imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
+    imageList: list[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
 
 class ExtrasBatchImagesResponse(ExtraBaseResponse):
-    images: List[str] = Field(title="Images", description="The generated images in base64 format.")
+    images: list[str] = Field(title="Images", description="The generated images in base64 format.")
 
 class PNGInfoRequest(BaseModel):
     image: str = Field(title="Image", description="The base64 encoded PNG image")
 
 class PNGInfoResponse(BaseModel):
     info: str = Field(title="Image info", description="A string with the parameters used to generate the image")
-    items: dict = Field(title="Items", description="An object containing all the info the image had")
+    items: dict = Field(title="Items", description="A dictionary containing all the other fields the image had")
+    parameters: dict = Field(title="Parameters", description="A dictionary with parsed generation info fields")
 
 class ProgressRequest(BaseModel):
     skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization")
@@ -189,11 +208,10 @@ class PreprocessResponse(BaseModel):
 fields = {}
 for key, metadata in opts.data_labels.items():
     value = opts.data.get(key)
-    optType = opts.typemap.get(type(metadata.default), type(value))
+    optType = opts.typemap.get(type(metadata.default), type(metadata.default)) if metadata.default else Any
 
-    if (metadata is not None):
-        fields.update({key: (Optional[optType], Field(
-            default=metadata.default ,description=metadata.label))})
+    if metadata is not None:
+        fields.update({key: (Optional[optType], Field(default=metadata.default, description=metadata.label))})
     else:
         fields.update({key: (Optional[optType], Field())})
 
@@ -205,15 +223,16 @@ for key in _options:
     if(_options[key].dest != 'help'):
         flag = _options[key]
         _type = str
-        if _options[key].default is not None: _type = type(_options[key].default)
+        if _options[key].default is not None:
+            _type = type(_options[key].default)
         flags.update({flag.dest: (_type, Field(default=flag.default, description=flag.help))})
 
 FlagsModel = create_model("Flags", **flags)
 
 class SamplerItem(BaseModel):
     name: str = Field(title="Name")
-    aliases: List[str] = Field(title="Aliases")
-    options: Dict[str, str] = Field(title="Options")
+    aliases: list[str] = Field(title="Aliases")
+    options: dict[str, str] = Field(title="Options")
 
 class UpscalerItem(BaseModel):
     name: str = Field(title="Name")
@@ -222,13 +241,20 @@ class UpscalerItem(BaseModel):
     model_url: Optional[str] = Field(title="URL")
     scale: Optional[float] = Field(title="Scale")
 
+class LatentUpscalerModeItem(BaseModel):
+    name: str = Field(title="Name")
+
 class SDModelItem(BaseModel):
     title: str = Field(title="Title")
     model_name: str = Field(title="Model Name")
     hash: Optional[str] = Field(title="Short hash")
     sha256: Optional[str] = Field(title="sha256 hash")
     filename: str = Field(title="Filename")
-    config: str = Field(title="Config file")
+    config: Optional[str] = Field(title="Config file")
+
+class SDVaeItem(BaseModel):
+    model_name: str = Field(title="Model Name")
+    filename: str = Field(title="Filename")
 
 class HypernetworkItem(BaseModel):
     name: str = Field(title="Name")
@@ -248,10 +274,6 @@ class PromptStyleItem(BaseModel):
     prompt: Optional[str] = Field(title="Prompt")
     negative_prompt: Optional[str] = Field(title="Negative Prompt")
 
-class ArtistItem(BaseModel):
-    name: str = Field(title="Name")
-    score: float = Field(title="Score")
-    category: str = Field(title="Category")
 
 class EmbeddingItem(BaseModel):
     step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available")
@@ -261,9 +283,39 @@ class EmbeddingItem(BaseModel):
     vectors: int = Field(title="Vectors", description="The number of vectors in the embedding")
 
 class EmbeddingsResponse(BaseModel):
-    loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model")
-    skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
+    loaded: dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model")
+    skipped: dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
 
 class MemoryResponse(BaseModel):
     ram: dict = Field(title="RAM", description="System memory stats")
     cuda: dict = Field(title="CUDA", description="nVidia CUDA memory stats")
+
+
+class ScriptsList(BaseModel):
+    txt2img: list = Field(default=None, title="Txt2img", description="Titles of scripts (txt2img)")
+    img2img: list = Field(default=None, title="Img2img", description="Titles of scripts (img2img)")
+
+
+class ScriptArg(BaseModel):
+    label: str = Field(default=None, title="Label", description="Name of the argument in UI")
+    value: Optional[Any] = Field(default=None, title="Value", description="Default value of the argument")
+    minimum: Optional[Any] = Field(default=None, title="Minimum", description="Minimum allowed value for the argumentin UI")
+    maximum: Optional[Any] = Field(default=None, title="Minimum", description="Maximum allowed value for the argumentin UI")
+    step: Optional[Any] = Field(default=None, title="Minimum", description="Step for changing value of the argumentin UI")
+    choices: Optional[list[str]] = Field(default=None, title="Choices", description="Possible values for the argument")
+
+
+class ScriptInfo(BaseModel):
+    name: str = Field(default=None, title="Name", description="Script name")
+    is_alwayson: bool = Field(default=None, title="IsAlwayson", description="Flag specifying whether this script is an alwayson script")
+    is_img2img: bool = Field(default=None, title="IsImg2img", description="Flag specifying whether this script is an img2img script")
+    args: list[ScriptArg] = Field(title="Arguments", description="List of script's arguments")
+
+class ExtensionItem(BaseModel):
+    name: str = Field(title="Name", description="Extension name")
+    remote: str = Field(title="Remote", description="Extension Repository URL")
+    branch: str = Field(title="Branch", description="Extension Repository Branch")
+    commit_hash: str = Field(title="Commit Hash", description="Extension Repository Commit Hash")
+    version: str = Field(title="Version", description="Extension Version")
+    commit_date: str = Field(title="Commit Date", description="Extension Repository Commit Date")
+    enabled: bool = Field(title="Enabled", description="Flag specifying whether this extension is enabled")

modules/cache.py

@@ -0,0 +1,124 @@
+import json
+import os
+import os.path
+import threading
+import time
+
+from modules.paths import data_path, script_path
+
+cache_filename = os.environ.get('SD_WEBUI_CACHE_FILE', os.path.join(data_path, "cache.json"))
+cache_data = None
+cache_lock = threading.Lock()
+
+dump_cache_after = None
+dump_cache_thread = None
+
+
+def dump_cache():
+    """
+    Marks cache for writing to disk. 5 seconds after no one else flags the cache for writing, it is written.
+    """
+
+    global dump_cache_after
+    global dump_cache_thread
+
+    def thread_func():
+        global dump_cache_after
+        global dump_cache_thread
+
+        while dump_cache_after is not None and time.time() < dump_cache_after:
+            time.sleep(1)
+
+        with cache_lock:
+            cache_filename_tmp = cache_filename + "-"
+            with open(cache_filename_tmp, "w", encoding="utf8") as file:
+                json.dump(cache_data, file, indent=4)
+
+            os.replace(cache_filename_tmp, cache_filename)
+
+            dump_cache_after = None
+            dump_cache_thread = None
+
+    with cache_lock:
+        dump_cache_after = time.time() + 5
+        if dump_cache_thread is None:
+            dump_cache_thread = threading.Thread(name='cache-writer', target=thread_func)
+            dump_cache_thread.start()
+
+
+def cache(subsection):
+    """
+    Retrieves or initializes a cache for a specific subsection.
+
+    Parameters:
+        subsection (str): The subsection identifier for the cache.
+
+    Returns:
+        dict: The cache data for the specified subsection.
+    """
+
+    global cache_data
+
+    if cache_data is None:
+        with cache_lock:
+            if cache_data is None:
+                if not os.path.isfile(cache_filename):
+                    cache_data = {}
+                else:
+                    try:
+                        with open(cache_filename, "r", encoding="utf8") as file:
+                            cache_data = json.load(file)
+                    except Exception:
+                        os.replace(cache_filename, os.path.join(script_path, "tmp", "cache.json"))
+                        print('[ERROR] issue occurred while trying to read cache.json, move current cache to tmp/cache.json and create new cache')
+                        cache_data = {}
+
+    s = cache_data.get(subsection, {})
+    cache_data[subsection] = s
+
+    return s
+
+
+def cached_data_for_file(subsection, title, filename, func):
+    """
+    Retrieves or generates data for a specific file, using a caching mechanism.
+
+    Parameters:
+        subsection (str): The subsection of the cache to use.
+        title (str): The title of the data entry in the subsection of the cache.
+        filename (str): The path to the file to be checked for modifications.
+        func (callable): A function that generates the data if it is not available in the cache.
+
+    Returns:
+        dict or None: The cached or generated data, or None if data generation fails.
+
+    The `cached_data_for_file` function implements a caching mechanism for data stored in files.
+    It checks if the data associated with the given `title` is present in the cache and compares the
+    modification time of the file with the cached modification time. If the file has been modified,
+    the cache is considered invalid and the data is regenerated using the provided `func`.
+    Otherwise, the cached data is returned.
+
+    If the data generation fails, None is returned to indicate the failure. Otherwise, the generated
+    or cached data is returned as a dictionary.
+    """
+
+    existing_cache = cache(subsection)
+    ondisk_mtime = os.path.getmtime(filename)
+
+    entry = existing_cache.get(title)
+    if entry:
+        cached_mtime = entry.get("mtime", 0)
+        if ondisk_mtime > cached_mtime:
+            entry = None
+
+    if not entry or 'value' not in entry:
+        value = func()
+        if value is None:
+            return None
+
+        entry = {'mtime': ondisk_mtime, 'value': value}
+        existing_cache[title] = entry
+
+        dump_cache()
+
+    return entry['value']

modules/call_queue.py

@@ -1,12 +1,10 @@
+from functools import wraps
 import html
-import sys
-import threading
-import traceback
 import time
 
-from modules import shared, progress
+from modules import shared, progress, errors, devices, fifo_lock
 
-queue_lock = threading.Lock()
+queue_lock = fifo_lock.FIFOLock()
 
 
 def wrap_queued_call(func):
@@ -20,21 +18,23 @@ def wrap_queued_call(func):
 
 
 def wrap_gradio_gpu_call(func, extra_outputs=None):
+    @wraps(func)
     def f(*args, **kwargs):
 
         # if the first argument is a string that says "task(...)", it is treated as a job id
-        if len(args) > 0 and type(args[0]) == str and args[0][0:5] == "task(" and args[0][-1] == ")":
+        if args and type(args[0]) == str and args[0].startswith("task(") and args[0].endswith(")"):
             id_task = args[0]
             progress.add_task_to_queue(id_task)
         else:
             id_task = None
 
         with queue_lock:
-            shared.state.begin()
+            shared.state.begin(job=id_task)
             progress.start_task(id_task)
 
             try:
                 res = func(*args, **kwargs)
+                progress.record_results(id_task, res)
             finally:
                 progress.finish_task(id_task)
 
@@ -46,6 +46,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
 
 
 def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
+    @wraps(func)
     def f(*args, extra_outputs_array=extra_outputs, **kwargs):
         run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats
         if run_memmon:
@@ -55,16 +56,14 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
         try:
             res = list(func(*args, **kwargs))
         except Exception as e:
-            # When printing out our debug argument list, do not print out more than a MB of text
-            max_debug_str_len = 131072 # (1024*1024)/8
-
-            print("Error completing request", file=sys.stderr)
-            argStr = f"Arguments: {str(args)} {str(kwargs)}"
-            print(argStr[:max_debug_str_len], file=sys.stderr)
-            if len(argStr) > max_debug_str_len:
-                print(f"(Argument list truncated at {max_debug_str_len}/{len(argStr)} characters)", file=sys.stderr)
-
-            print(traceback.format_exc(), file=sys.stderr)
+            # When printing out our debug argument list,
+            # do not print out more than a 100 KB of text
+            max_debug_str_len = 131072
+            message = "Error completing request"
+            arg_str = f"Arguments: {args} {kwargs}"[:max_debug_str_len]
+            if len(arg_str) > max_debug_str_len:
+                arg_str += f" (Argument list truncated at {max_debug_str_len}/{len(arg_str)} characters)"
+            errors.report(f"{message}\n{arg_str}", exc_info=True)
 
             shared.state.job = ""
             shared.state.job_count = 0
@@ -72,7 +71,10 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
             if extra_outputs_array is None:
                 extra_outputs_array = [None, '']
 
-            res = extra_outputs_array + [f"<div class='error'>{html.escape(type(e).__name__+': '+str(e))}</div>"]
+            error_message = f'{type(e).__name__}: {e}'
+            res = extra_outputs_array + [f"<div class='error'>{html.escape(error_message)}</div>"]
+
+        devices.torch_gc()
 
         shared.state.skipped = False
         shared.state.interrupted = False
@@ -84,9 +86,9 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
         elapsed = time.perf_counter() - t
         elapsed_m = int(elapsed // 60)
         elapsed_s = elapsed % 60
-        elapsed_text = f"{elapsed_s:.2f}s"
+        elapsed_text = f"{elapsed_s:.1f} sec."
         if elapsed_m > 0:
-            elapsed_text = f"{elapsed_m}m "+elapsed_text
+            elapsed_text = f"{elapsed_m} min. "+elapsed_text
 
         if run_memmon:
             mem_stats = {k: -(v//-(1024*1024)) for k, v in shared.mem_mon.stop().items()}
@@ -94,16 +96,23 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
             reserved_peak = mem_stats['reserved_peak']
             sys_peak = mem_stats['system_peak']
             sys_total = mem_stats['total']
-            sys_pct = round(sys_peak/max(sys_total, 1) * 100, 2)
+            sys_pct = sys_peak/max(sys_total, 1) * 100
 
-            vram_html = f"<p class='vram'>Torch active/reserved: {active_peak}/{reserved_peak} MiB, <wbr>Sys VRAM: {sys_peak}/{sys_total} MiB ({sys_pct}%)</p>"
+            toltip_a = "Active: peak amount of video memory used during generation (excluding cached data)"
+            toltip_r = "Reserved: total amout of video memory allocated by the Torch library "
+            toltip_sys = "System: peak amout of video memory allocated by all running programs, out of total capacity"
+
+            text_a = f"<abbr title='{toltip_a}'>A</abbr>: <span class='measurement'>{active_peak/1024:.2f} GB</span>"
+            text_r = f"<abbr title='{toltip_r}'>R</abbr>: <span class='measurement'>{reserved_peak/1024:.2f} GB</span>"
+            text_sys = f"<abbr title='{toltip_sys}'>Sys</abbr>: <span class='measurement'>{sys_peak/1024:.1f}/{sys_total/1024:g} GB</span> ({sys_pct:.1f}%)"
+
+            vram_html = f"<p class='vram'>{text_a}, <wbr>{text_r}, <wbr>{text_sys}</p>"
         else:
             vram_html = ''
 
         # last item is always HTML
-        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"
+        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr><span class='measurement'>{elapsed_text}</span></p>{vram_html}</div>"
 
         return tuple(res)
 
     return f
-

modules/cmd_args.py

@@ -0,0 +1,120 @@
+import argparse
+import json
+import os
+from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file  # noqa: F401
+
+parser = argparse.ArgumentParser()
+
+parser.add_argument("-f", action='store_true', help=argparse.SUPPRESS)  # allows running as root; implemented outside of webui
+parser.add_argument("--update-all-extensions", action='store_true', help="launch.py argument: download updates for all extensions when starting the program")
+parser.add_argument("--skip-python-version-check", action='store_true', help="launch.py argument: do not check python version")
+parser.add_argument("--skip-torch-cuda-test", action='store_true', help="launch.py argument: do not check if CUDA is able to work properly")
+parser.add_argument("--reinstall-xformers", action='store_true', help="launch.py argument: install the appropriate version of xformers even if you have some version already installed")
+parser.add_argument("--reinstall-torch", action='store_true', help="launch.py argument: install the appropriate version of torch even if you have some version already installed")
+parser.add_argument("--update-check", action='store_true', help="launch.py argument: check for updates at startup")
+parser.add_argument("--test-server", action='store_true', help="launch.py argument: configure server for testing")
+parser.add_argument("--log-startup", action='store_true', help="launch.py argument: print a detailed log of what's happening at startup")
+parser.add_argument("--skip-prepare-environment", action='store_true', help="launch.py argument: skip all environment preparation")
+parser.add_argument("--skip-install", action='store_true', help="launch.py argument: skip installation of packages")
+parser.add_argument("--dump-sysinfo", action='store_true', help="launch.py argument: dump limited sysinfo file (without information about extensions, options) to disk and quit")
+parser.add_argument("--loglevel", type=str, help="log level; one of: CRITICAL, ERROR, WARNING, INFO, DEBUG", default=None)
+parser.add_argument("--do-not-download-clip", action='store_true', help="do not download CLIP model even if it's not included in the checkpoint")
+parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
+parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
+parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
+parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
+parser.add_argument("--vae-dir", type=str, default=None, help="Path to directory with VAE files")
+parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
+parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default=None)
+parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")
+parser.add_argument("--no-half-vae", action='store_true', help="do not switch the VAE model to 16-bit floats")
+parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
+parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
+parser.add_argument("--embeddings-dir", type=str, default=os.path.join(data_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
+parser.add_argument("--textual-inversion-templates-dir", type=str, default=os.path.join(script_path, 'textual_inversion_templates'), help="directory with textual inversion templates")
+parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
+parser.add_argument("--localizations-dir", type=str, default=os.path.join(script_path, 'localizations'), help="localizations directory")
+parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
+parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
+parser.add_argument("--medvram-sdxl", action='store_true', help="enable --medvram optimization just for SDXL models")
+parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage")
+parser.add_argument("--lowram", action='store_true', help="load stable diffusion checkpoint weights to VRAM instead of RAM")
+parser.add_argument("--always-batch-cond-uncond", action='store_true', help="does not do anything")
+parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
+parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
+parser.add_argument("--upcast-sampling", action='store_true', help="upcast sampling. No effect with --no-half. Usually produces similar results to --no-half with better performance while using less memory.")
+parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site")
+parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)
+parser.add_argument("--ngrok-region", type=str, help="does not do anything.", default="")
+parser.add_argument("--ngrok-options", type=json.loads, help='The options to pass to ngrok in JSON format, e.g.: \'{"authtoken_from_env":true, "basic_auth":"user:password", "oauth_provider":"google", "oauth_allow_emails":"user@asdf.com"}\'', default=dict())
+parser.add_argument("--enable-insecure-extension-access", action='store_true', help="enable extensions tab regardless of other options")
+parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
+parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
+parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
+parser.add_argument("--bsrgan-models-path", type=str, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN'))
+parser.add_argument("--realesrgan-models-path", type=str, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN'))
+parser.add_argument("--clip-models-path", type=str, help="Path to directory with CLIP model file(s).", default=None)
+parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
+parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
+parser.add_argument("--xformers-flash-attention", action='store_true', help="enable xformers with Flash Attention to improve reproducibility (supported for SD2.x or variant only)")
+parser.add_argument("--deepdanbooru", action='store_true', help="does not do anything")
+parser.add_argument("--opt-split-attention", action='store_true', help="prefer Doggettx's cross-attention layer optimization for automatic choice of optimization")
+parser.add_argument("--opt-sub-quad-attention", action='store_true', help="prefer memory efficient sub-quadratic cross-attention layer optimization for automatic choice of optimization")
+parser.add_argument("--sub-quad-q-chunk-size", type=int, help="query chunk size for the sub-quadratic cross-attention layer optimization to use", default=1024)
+parser.add_argument("--sub-quad-kv-chunk-size", type=int, help="kv chunk size for the sub-quadratic cross-attention layer optimization to use", default=None)
+parser.add_argument("--sub-quad-chunk-threshold", type=int, help="the percentage of VRAM threshold for the sub-quadratic cross-attention layer optimization to use chunking", default=None)
+parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="prefer InvokeAI's cross-attention layer optimization for automatic choice of optimization")
+parser.add_argument("--opt-split-attention-v1", action='store_true', help="prefer older version of split attention optimization for automatic choice of optimization")
+parser.add_argument("--opt-sdp-attention", action='store_true', help="prefer scaled dot product cross-attention layer optimization for automatic choice of optimization; requires PyTorch 2.*")
+parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="prefer scaled dot product cross-attention layer optimization without memory efficient attention for automatic choice of optimization, makes image generation deterministic; requires PyTorch 2.*")
+parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
+parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
+parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--disable-model-loading-ram-optimization", action='store_true', help="disable an optimization that reduces RAM use when loading a model")
+parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
+parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
+parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
+parser.add_argument("--ui-config-file", type=str, help="filename to use for ui configuration", default=os.path.join(data_path, 'ui-config.json'))
+parser.add_argument("--hide-ui-dir-config", action='store_true', help="hide directory configuration from webui", default=False)
+parser.add_argument("--freeze-settings", action='store_true', help="disable editing settings", default=False)
+parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default=os.path.join(data_path, 'config.json'))
+parser.add_argument("--gradio-debug",  action='store_true', help="launch gradio with --debug option")
+parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
+parser.add_argument("--gradio-auth-path", type=str, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
+parser.add_argument("--gradio-img2img-tool", type=str, help='does not do anything')
+parser.add_argument("--gradio-inpaint-tool", type=str, help="does not do anything")
+parser.add_argument("--gradio-allowed-path", action='append', help="add path to gradio's allowed_paths, make it possible to serve files from it", default=[data_path])
+parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
+parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(data_path, 'styles.csv'))
+parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
+parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
+parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
+parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
+parser.add_argument("--enable-console-prompts", action='store_true', help="does not do anything", default=False)  # Legacy compatibility, use as default value shared.opts.enable_console_prompts
+parser.add_argument('--vae-path', type=str, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
+parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
+parser.add_argument("--api", action='store_true', help="use api=True to launch the API together with the webui (use --nowebui instead for only the API)")
+parser.add_argument("--api-auth", type=str, help='Set authentication for API like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
+parser.add_argument("--api-log", action='store_true', help="use api-log=True to enable logging of all API requests")
+parser.add_argument("--nowebui", action='store_true', help="use api=True to launch the API instead of the webui")
+parser.add_argument("--ui-debug-mode", action='store_true', help="Don't load model to quickly launch UI")
+parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)
+parser.add_argument("--administrator", action='store_true', help="Administrator rights", default=False)
+parser.add_argument("--cors-allow-origins", type=str, help="Allowed CORS origin(s) in the form of a comma-separated list (no spaces)", default=None)
+parser.add_argument("--cors-allow-origins-regex", type=str, help="Allowed CORS origin(s) in the form of a single regular expression", default=None)
+parser.add_argument("--tls-keyfile", type=str, help="Partially enables TLS, requires --tls-certfile to fully function", default=None)
+parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, requires --tls-keyfile to fully function", default=None)
+parser.add_argument("--disable-tls-verify", action="store_false", help="When passed, enables the use of self-signed certificates.", default=None)
+parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
+parser.add_argument("--gradio-queue", action='store_true', help="does not do anything", default=True)
+parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the defaul in earlier versions")
+parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
+parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
+parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)
+parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
+parser.add_argument('--add-stop-route', action='store_true', help='does not do anything')
+parser.add_argument('--api-server-stop', action='store_true', help='enable server stop/restart/kill via api')
+parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')
+parser.add_argument("--disable-all-extensions", action='store_true', help="prevent all extensions from running regardless of any other settings", default=False)
+parser.add_argument("--disable-extra-extensions", action='store_true', help="prevent all extensions except built-in from running regardless of any other settings", default=False)
+parser.add_argument("--skip-load-model-at-start", action='store_true', help="if load a model at web start, only take effect when --nowebui", )

modules/codeformer/codeformer_arch.py

@@ -1,14 +1,12 @@
 # this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py
 
 import math
-import numpy as np
 import torch
 from torch import nn, Tensor
 import torch.nn.functional as F
-from typing import Optional, List
+from typing import Optional
 
-from modules.codeformer.vqgan_arch import *
-from basicsr.utils import get_root_logger
+from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock
 from basicsr.utils.registry import ARCH_REGISTRY
 
 def calc_mean_std(feat, eps=1e-5):
@@ -163,8 +161,8 @@ class Fuse_sft_block(nn.Module):
 class CodeFormer(VQAutoEncoder):
     def __init__(self, dim_embd=512, n_head=8, n_layers=9,
                 codebook_size=1024, latent_size=256,
-                connect_list=['32', '64', '128', '256'],
-                fix_modules=['quantize','generator']):
+                connect_list=('32', '64', '128', '256'),
+                fix_modules=('quantize', 'generator')):
         super(CodeFormer, self).__init__(512, 64, [1, 2, 2, 4, 4, 8], 'nearest',2, [16], codebook_size)
 
         if fix_modules is not None:

modules/codeformer/vqgan_arch.py

@@ -5,11 +5,9 @@ VQGAN code, adapted from the original created by the Unleashing Transformers aut
 https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py
 
 '''
-import numpy as np
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-import copy
 from basicsr.utils import get_root_logger
 from basicsr.utils.registry import ARCH_REGISTRY
 
@@ -328,7 +326,7 @@ class Generator(nn.Module):
 
 @ARCH_REGISTRY.register()
 class VQAutoEncoder(nn.Module):
-    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=[16], codebook_size=1024, emb_dim=256,
+    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256,
                 beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None):
         super().__init__()
         logger = get_root_logger()
@@ -339,7 +337,7 @@ class VQAutoEncoder(nn.Module):
         self.embed_dim = emb_dim
         self.ch_mult = ch_mult
         self.resolution = img_size
-        self.attn_resolutions = attn_resolutions
+        self.attn_resolutions = attn_resolutions or [16]
         self.quantizer_type = quantizer
         self.encoder = Encoder(
             self.in_channels,

modules/codeformer_model.py

@@ -1,14 +1,12 @@
 import os
-import sys
-import traceback
 
 import cv2
 import torch
 
 import modules.face_restoration
 import modules.shared
-from modules import shared, devices, modelloader
-from modules.paths import script_path, models_path
+from modules import shared, devices, modelloader, errors
+from modules.paths import models_path
 
 # codeformer people made a choice to include modified basicsr library to their project which makes
 # it utterly impossible to use it alongside with other libraries that also use basicsr, like GFPGAN.
@@ -17,14 +15,11 @@ model_dir = "Codeformer"
 model_path = os.path.join(models_path, model_dir)
 model_url = 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth'
 
-have_codeformer = False
 codeformer = None
 
 
 def setup_model(dirname):
-    global model_path
-    if not os.path.exists(model_path):
-        os.makedirs(model_path)
+    os.makedirs(model_path, exist_ok=True)
 
     path = modules.paths.paths.get("CodeFormer", None)
     if path is None:
@@ -33,11 +28,9 @@ def setup_model(dirname):
     try:
         from torchvision.transforms.functional import normalize
         from modules.codeformer.codeformer_arch import CodeFormer
-        from basicsr.utils.download_util import load_file_from_url
-        from basicsr.utils import imwrite, img2tensor, tensor2img
+        from basicsr.utils import img2tensor, tensor2img
         from facelib.utils.face_restoration_helper import FaceRestoreHelper
         from facelib.detection.retinaface import retinaface
-        from modules.shared import cmd_opts
 
         net_class = CodeFormer
 
@@ -55,7 +48,7 @@ def setup_model(dirname):
                 if self.net is not None and self.face_helper is not None:
                     self.net.to(devices.device_codeformer)
                     return self.net, self.face_helper
-                model_paths = modelloader.load_models(model_path, model_url, self.cmd_dir, download_name='codeformer-v0.1.0.pth')
+                model_paths = modelloader.load_models(model_path, model_url, self.cmd_dir, download_name='codeformer-v0.1.0.pth', ext_filter=['.pth'])
                 if len(model_paths) != 0:
                     ckpt_path = model_paths[0]
                 else:
@@ -96,7 +89,7 @@ def setup_model(dirname):
                 self.face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
                 self.face_helper.align_warp_face()
 
-                for idx, cropped_face in enumerate(self.face_helper.cropped_faces):
+                for cropped_face in self.face_helper.cropped_faces:
                     cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
                     normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
                     cropped_face_t = cropped_face_t.unsqueeze(0).to(devices.device_codeformer)
@@ -106,9 +99,9 @@ def setup_model(dirname):
                             output = self.net(cropped_face_t, w=w if w is not None else shared.opts.code_former_weight, adain=True)[0]
                             restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
                         del output
-                        torch.cuda.empty_cache()
-                    except Exception as error:
-                        print(f'\tFailed inference for CodeFormer: {error}', file=sys.stderr)
+                        devices.torch_gc()
+                    except Exception:
+                        errors.report('Failed inference for CodeFormer', exc_info=True)
                         restored_face = tensor2img(cropped_face_t, rgb2bgr=True, min_max=(-1, 1))
 
                     restored_face = restored_face.astype('uint8')
@@ -129,15 +122,11 @@ def setup_model(dirname):
 
                 return restored_img
 
-        global have_codeformer
-        have_codeformer = True
-
         global codeformer
         codeformer = FaceRestorerCodeFormer(dirname)
         shared.face_restorers.append(codeformer)
 
     except Exception:
-        print("Error setting up CodeFormer:", file=sys.stderr)
-        print(traceback.format_exc(), file=sys.stderr)
+        errors.report("Error setting up CodeFormer", exc_info=True)
 
    # sys.path = stored_sys_path

modules/config_states.py

@@ -0,0 +1,198 @@
+"""
+Supports saving and restoring webui and extensions from a known working set of commits
+"""
+
+import os
+import json
+import tqdm
+
+from datetime import datetime
+import git
+
+from modules import shared, extensions, errors
+from modules.paths_internal import script_path, config_states_dir
+
+all_config_states = {}
+
+
+def list_config_states():
+    global all_config_states
+
+    all_config_states.clear()
+    os.makedirs(config_states_dir, exist_ok=True)
+
+    config_states = []
+    for filename in os.listdir(config_states_dir):
+        if filename.endswith(".json"):
+            path = os.path.join(config_states_dir, filename)
+            try:
+                with open(path, "r", encoding="utf-8") as f:
+                    j = json.load(f)
+                    assert "created_at" in j, '"created_at" does not exist'
+                    j["filepath"] = path
+                    config_states.append(j)
+            except Exception as e:
+                print(f'[ERROR]: Config states {path}, {e}')
+
+    config_states = sorted(config_states, key=lambda cs: cs["created_at"], reverse=True)
+
+    for cs in config_states:
+        timestamp = datetime.fromtimestamp(cs["created_at"]).strftime('%Y-%m-%d %H:%M:%S')
+        name = cs.get("name", "Config")
+        full_name = f"{name}: {timestamp}"
+        all_config_states[full_name] = cs
+
+    return all_config_states
+
+
+def get_webui_config():
+    webui_repo = None
+
+    try:
+        if os.path.exists(os.path.join(script_path, ".git")):
+            webui_repo = git.Repo(script_path)
+    except Exception:
+        errors.report(f"Error reading webui git info from {script_path}", exc_info=True)
+
+    webui_remote = None
+    webui_commit_hash = None
+    webui_commit_date = None
+    webui_branch = None
+    if webui_repo and not webui_repo.bare:
+        try:
+            webui_remote = next(webui_repo.remote().urls, None)
+            head = webui_repo.head.commit
+            webui_commit_date = webui_repo.head.commit.committed_date
+            webui_commit_hash = head.hexsha
+            webui_branch = webui_repo.active_branch.name
+
+        except Exception:
+            webui_remote = None
+
+    return {
+        "remote": webui_remote,
+        "commit_hash": webui_commit_hash,
+        "commit_date": webui_commit_date,
+        "branch": webui_branch,
+    }
+
+
+def get_extension_config():
+    ext_config = {}
+
+    for ext in extensions.extensions:
+        ext.read_info_from_repo()
+
+        entry = {
+            "name": ext.name,
+            "path": ext.path,
+            "enabled": ext.enabled,
+            "is_builtin": ext.is_builtin,
+            "remote": ext.remote,
+            "commit_hash": ext.commit_hash,
+            "commit_date": ext.commit_date,
+            "branch": ext.branch,
+            "have_info_from_repo": ext.have_info_from_repo
+        }
+
+        ext_config[ext.name] = entry
+
+    return ext_config
+
+
+def get_config():
+    creation_time = datetime.now().timestamp()
+    webui_config = get_webui_config()
+    ext_config = get_extension_config()
+
+    return {
+        "created_at": creation_time,
+        "webui": webui_config,
+        "extensions": ext_config
+    }
+
+
+def restore_webui_config(config):
+    print("* Restoring webui state...")
+
+    if "webui" not in config:
+        print("Error: No webui data saved to config")
+        return
+
+    webui_config = config["webui"]
+
+    if "commit_hash" not in webui_config:
+        print("Error: No commit saved to webui config")
+        return
+
+    webui_commit_hash = webui_config.get("commit_hash", None)
+    webui_repo = None
+
+    try:
+        if os.path.exists(os.path.join(script_path, ".git")):
+            webui_repo = git.Repo(script_path)
+    except Exception:
+        errors.report(f"Error reading webui git info from {script_path}", exc_info=True)
+        return
+
+    try:
+        webui_repo.git.fetch(all=True)
+        webui_repo.git.reset(webui_commit_hash, hard=True)
+        print(f"* Restored webui to commit {webui_commit_hash}.")
+    except Exception:
+        errors.report(f"Error restoring webui to commit{webui_commit_hash}")
+
+
+def restore_extension_config(config):
+    print("* Restoring extension state...")
+
+    if "extensions" not in config:
+        print("Error: No extension data saved to config")
+        return
+
+    ext_config = config["extensions"]
+
+    results = []
+    disabled = []
+
+    for ext in tqdm.tqdm(extensions.extensions):
+        if ext.is_builtin:
+            continue
+
+        ext.read_info_from_repo()
+        current_commit = ext.commit_hash
+
+        if ext.name not in ext_config:
+            ext.disabled = True
+            disabled.append(ext.name)
+            results.append((ext, current_commit[:8], False, "Saved extension state not found in config, marking as disabled"))
+            continue
+
+        entry = ext_config[ext.name]
+
+        if "commit_hash" in entry and entry["commit_hash"]:
+            try:
+                ext.fetch_and_reset_hard(entry["commit_hash"])
+                ext.read_info_from_repo()
+                if current_commit != entry["commit_hash"]:
+                    results.append((ext, current_commit[:8], True, entry["commit_hash"][:8]))
+            except Exception as ex:
+                results.append((ext, current_commit[:8], False, ex))
+        else:
+            results.append((ext, current_commit[:8], False, "No commit hash found in config"))
+
+        if not entry.get("enabled", False):
+            ext.disabled = True
+            disabled.append(ext.name)
+        else:
+            ext.disabled = False
+
+    shared.opts.disabled_extensions = disabled
+    shared.opts.save(shared.config_filename)
+
+    print("* Finished restoring extensions. Results:")
+    for ext, prev_commit, success, result in results:
+        if success:
+            print(f"  + {ext.name}: {prev_commit} -> {result}")
+        else:
+            print(f"  ! {ext.name}: FAILURE ({result})")

modules/deepbooru.py

@@ -2,7 +2,6 @@ import os
 import re
 
 import torch
-from PIL import Image
 import numpy as np
 
 from modules import modelloader, paths, deepbooru_model, devices, images, shared
@@ -79,7 +78,7 @@ class DeepDanbooru:
 
         res = []
 
-        filtertags = set([x.strip().replace(' ', '_') for x in shared.opts.deepbooru_filter_tags.split(",")])
+        filtertags = {x.strip().replace(' ', '_') for x in shared.opts.deepbooru_filter_tags.split(",")}
 
         for tag in [x for x in tags if x not in filtertags]:
             probability = probability_dict[tag]

modules/deepbooru_model.py

@@ -2,6 +2,8 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
+from modules import devices
+
 # see https://github.com/AUTOMATIC1111/TorchDeepDanbooru for more
 
 
@@ -196,7 +198,7 @@ class DeepDanbooruModel(nn.Module):
         t_358, = inputs
         t_359 = t_358.permute(*[0, 3, 1, 2])
         t_359_padded = F.pad(t_359, [2, 3, 2, 3], value=0)
-        t_360 = self.n_Conv_0(t_359_padded)
+        t_360 = self.n_Conv_0(t_359_padded.to(self.n_Conv_0.bias.dtype) if devices.unet_needs_upcast else t_359_padded)
         t_361 = F.relu(t_360)
         t_361 = F.pad(t_361, [0, 1, 0, 1], value=float('-inf'))
         t_362 = self.n_MaxPool_0(t_361)

modules/devices.py

@@ -1,52 +1,43 @@
-import sys, os, shlex
+import sys
 import contextlib
+from functools import lru_cache
+
 import torch
-from modules import errors
-from packaging import version
+from modules import errors, shared
+
+if sys.platform == "darwin":
+    from modules import mac_specific
 
 
-# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
-# check `getattr` and try it for compatibility
 def has_mps() -> bool:
-    if not getattr(torch, 'has_mps', False):
+    if sys.platform != "darwin":
         return False
-    try:
-        torch.zeros(1).to(torch.device("mps"))
-        return True
-    except Exception:
-        return False
-
-
-def extract_device_id(args, name):
-    for x in range(len(args)):
-        if name in args[x]:
-            return args[x + 1]
-
-    return None
+    else:
+        return mac_specific.has_mps
 
 
 def get_cuda_device_string():
-    from modules import shared
-
     if shared.cmd_opts.device_id is not None:
         return f"cuda:{shared.cmd_opts.device_id}"
 
     return "cuda"
 
 
-def get_optimal_device():
+def get_optimal_device_name():
     if torch.cuda.is_available():
-        return torch.device(get_cuda_device_string())
+        return get_cuda_device_string()
 
     if has_mps():
-        return torch.device("mps")
+        return "mps"
 
-    return cpu
+    return "cpu"
+
+
+def get_optimal_device():
+    return torch.device(get_optimal_device_name())
 
 
 def get_device_for(task):
-    from modules import shared
-
     if task in shared.cmd_opts.use_cpu:
         return cpu
 
@@ -54,49 +45,55 @@ def get_device_for(task):
 
 
 def torch_gc():
+
     if torch.cuda.is_available():
         with torch.cuda.device(get_cuda_device_string()):
             torch.cuda.empty_cache()
             torch.cuda.ipc_collect()
 
+    if has_mps():
+        mac_specific.torch_mps_gc()
+
 
 def enable_tf32():
     if torch.cuda.is_available():
 
         # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
         # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
-        if any([torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())]):
+        device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()
+        if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"):
             torch.backends.cudnn.benchmark = True
 
         torch.backends.cuda.matmul.allow_tf32 = True
         torch.backends.cudnn.allow_tf32 = True
 
 
-
 errors.run(enable_tf32, "Enabling TF32")
 
-cpu = torch.device("cpu")
-device = device_interrogate = device_gfpgan = device_esrgan = device_codeformer = None
-dtype = torch.float16
-dtype_vae = torch.float16
+cpu: torch.device = torch.device("cpu")
+device: torch.device = None
+device_interrogate: torch.device = None
+device_gfpgan: torch.device = None
+device_esrgan: torch.device = None
+device_codeformer: torch.device = None
+dtype: torch.dtype = torch.float16
+dtype_vae: torch.dtype = torch.float16
+dtype_unet: torch.dtype = torch.float16
+unet_needs_upcast = False
 
 
-def randn(seed, shape):
-    torch.manual_seed(seed)
-    if device.type == 'mps':
-        return torch.randn(shape, device=cpu).to(device)
-    return torch.randn(shape, device=device)
+def cond_cast_unet(input):
+    return input.to(dtype_unet) if unet_needs_upcast else input
 
 
-def randn_without_seed(shape):
-    if device.type == 'mps':
-        return torch.randn(shape, device=cpu).to(device)
-    return torch.randn(shape, device=device)
+def cond_cast_float(input):
+    return input.float() if unet_needs_upcast else input
+
+
+nv_rng = None
 
 
 def autocast(disable=False):
-    from modules import shared
-
     if disable:
         return contextlib.nullcontext()
 
@@ -106,13 +103,15 @@ def autocast(disable=False):
     return torch.autocast("cuda")
 
 
+def without_autocast(disable=False):
+    return torch.autocast("cuda", enabled=False) if torch.is_autocast_enabled() and not disable else contextlib.nullcontext()
+
+
 class NansException(Exception):
     pass
 
 
 def test_for_nans(x, where):
-    from modules import shared
-
     if shared.cmd_opts.disable_nan_check:
         return
 
@@ -123,7 +122,7 @@ def test_for_nans(x, where):
         message = "A tensor with all NaNs was produced in Unet."
 
         if not shared.cmd_opts.no_half:
-            message += " This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try using --no-half commandline argument to fix this."
+            message += " This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the \"Upcast cross attention layer to float32\" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this."
 
     elif where == "vae":
         message = "A tensor with all NaNs was produced in VAE."
@@ -133,60 +132,23 @@ def test_for_nans(x, where):
     else:
         message = "A tensor with all NaNs was produced."
 
+    message += " Use --disable-nan-check commandline argument to disable this check."
+
     raise NansException(message)
 
 
-# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
-orig_tensor_to = torch.Tensor.to
-def tensor_to_fix(self, *args, **kwargs):
-    if self.device.type != 'mps' and \
-       ((len(args) > 0 and isinstance(args[0], torch.device) and args[0].type == 'mps') or \
-       (isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')):
-        self = self.contiguous()
-    return orig_tensor_to(self, *args, **kwargs)
+@lru_cache
+def first_time_calculation():
+    """
+    just do any calculation with pytorch layers - the first time this is done it allocaltes about 700MB of memory and
+    spends about 2.7 seconds doing that, at least wih NVidia.
+    """
 
+    x = torch.zeros((1, 1)).to(device, dtype)
+    linear = torch.nn.Linear(1, 1).to(device, dtype)
+    linear(x)
 
-# MPS workaround for https://github.com/pytorch/pytorch/issues/80800 
-orig_layer_norm = torch.nn.functional.layer_norm
-def layer_norm_fix(*args, **kwargs):
-    if len(args) > 0 and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps':
-        args = list(args)
-        args[0] = args[0].contiguous()
-    return orig_layer_norm(*args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
-orig_tensor_numpy = torch.Tensor.numpy
-def numpy_fix(self, *args, **kwargs):
-    if self.requires_grad:
-        self = self.detach()
-    return orig_tensor_numpy(self, *args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/89784
-orig_cumsum = torch.cumsum
-orig_Tensor_cumsum = torch.Tensor.cumsum
-def cumsum_fix(input, cumsum_func, *args, **kwargs):
-    if input.device.type == 'mps':
-        output_dtype = kwargs.get('dtype', input.dtype)
-        if output_dtype == torch.int64:
-            return cumsum_func(input.cpu(), *args, **kwargs).to(input.device)
-        elif cumsum_needs_bool_fix and output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16):
-            return cumsum_func(input.to(torch.int32), *args, **kwargs).to(torch.int64)
-    return cumsum_func(input, *args, **kwargs)
-
-
-if has_mps():
-    if version.parse(torch.__version__) < version.parse("1.13"):
-        # PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
-        torch.Tensor.to = tensor_to_fix
-        torch.nn.functional.layer_norm = layer_norm_fix
-        torch.Tensor.numpy = numpy_fix
-    elif version.parse(torch.__version__) > version.parse("1.13.1"):
-        cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0))
-        cumsum_needs_bool_fix = not torch.BoolTensor([True,True]).to(device=torch.device("mps"), dtype=torch.int64).equal(torch.BoolTensor([True,False]).to(torch.device("mps")).cumsum(0))
-        torch.cumsum = lambda input, *args, **kwargs: ( cumsum_fix(input, orig_cumsum, *args, **kwargs) )
-        torch.Tensor.cumsum = lambda self, *args, **kwargs: ( cumsum_fix(self, orig_Tensor_cumsum, *args, **kwargs) )
-        orig_narrow = torch.narrow
-        torch.narrow = lambda *args, **kwargs: ( orig_narrow(*args, **kwargs).clone() )
+    x = torch.zeros((1, 1, 3, 3)).to(device, dtype)
+    conv2d = torch.nn.Conv2d(1, 1, (3, 3)).to(device, dtype)
+    conv2d(x)
 

modules/errors.py

@@ -1,8 +1,43 @@
 import sys
+import textwrap
 import traceback
 
 
+exception_records = []
+
+
+def record_exception():
+    _, e, tb = sys.exc_info()
+    if e is None:
+        return
+
+    if exception_records and exception_records[-1] == e:
+        return
+
+    from modules import sysinfo
+    exception_records.append(sysinfo.format_exception(e, tb))
+
+    if len(exception_records) > 5:
+        exception_records.pop(0)
+
+
+def report(message: str, *, exc_info: bool = False) -> None:
+    """
+    Print an error message to stderr, with optional traceback.
+    """
+
+    record_exception()
+
+    for line in message.splitlines():
+        print("***", line, file=sys.stderr)
+    if exc_info:
+        print(textwrap.indent(traceback.format_exc(), "    "), file=sys.stderr)
+        print("---", file=sys.stderr)
+
+
 def print_error_explanation(message):
+    record_exception()
+
     lines = message.strip().split("\n")
     max_len = max([len(x) for x in lines])
 
@@ -12,9 +47,15 @@ def print_error_explanation(message):
     print('=' * max_len, file=sys.stderr)
 
 
-def display(e: Exception, task):
+def display(e: Exception, task, *, full_traceback=False):
+    record_exception()
+
     print(f"{task or 'error'}: {type(e).__name__}", file=sys.stderr)
-    print(traceback.format_exc(), file=sys.stderr)
+    te = traceback.TracebackException.from_exception(e)
+    if full_traceback:
+        # include frames leading up to the try-catch block
+        te.stack = traceback.StackSummary(traceback.extract_stack()[:-2] + te.stack)
+    print(*te.format(), sep="", file=sys.stderr)
 
     message = str(e)
     if "copying a param with shape torch.Size([640, 1024]) from checkpoint, the shape in current model is torch.Size([640, 768])" in message:
@@ -28,6 +69,8 @@ already_displayed = {}
 
 
 def display_once(e: Exception, task):
+    record_exception()
+
     if task in already_displayed:
         return
 
@@ -41,3 +84,53 @@ def run(code, task):
         code()
     except Exception as e:
         display(task, e)
+
+
+def check_versions():
+    from packaging import version
+    from modules import shared
+
+    import torch
+    import gradio
+
+    expected_torch_version = "2.0.0"
+    expected_xformers_version = "0.0.20"
+    expected_gradio_version = "3.41.2"
+
+    if version.parse(torch.__version__) < version.parse(expected_torch_version):
+        print_error_explanation(f"""
+You are running torch {torch.__version__}.
+The program is tested to work with torch {expected_torch_version}.
+To reinstall the desired version, run with commandline flag --reinstall-torch.
+Beware that this will cause a lot of large files to be downloaded, as well as
+there are reports of issues with training tab on the latest version.
+
+Use --skip-version-check commandline argument to disable this check.
+        """.strip())
+
+    if shared.xformers_available:
+        import xformers
+
+        if version.parse(xformers.__version__) < version.parse(expected_xformers_version):
+            print_error_explanation(f"""
+You are running xformers {xformers.__version__}.
+The program is tested to work with xformers {expected_xformers_version}.
+To reinstall the desired version, run with commandline flag --reinstall-xformers.
+
+Use --skip-version-check commandline argument to disable this check.
+            """.strip())
+
+    if gradio.__version__ != expected_gradio_version:
+        print_error_explanation(f"""
+You are running gradio {gradio.__version__}.
+The program is designed to work with gradio {expected_gradio_version}.
+Using a different version of gradio is extremely likely to break the program.
+
+Reasons why you have the mismatched gradio version can be:
+  - you use --skip-install flag.
+  - you use webui.py to start the program instead of launch.py.
+  - an extension installs the incompatible gradio version.
+
+Use --skip-version-check commandline argument to disable this check.
+        """.strip())
+

modules/esrgan_model.py

@@ -1,24 +1,20 @@
-import os
+import sys
 
 import numpy as np
 import torch
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 
 import modules.esrgan_model_arch as arch
-from modules import shared, modelloader, images, devices
-from modules.upscaler import Upscaler, UpscalerData
+from modules import modelloader, images, devices
 from modules.shared import opts
-
+from modules.upscaler import Upscaler, UpscalerData
 
 
 def mod2normal(state_dict):
     # this code is copied from https://github.com/victorca25/iNNfer
     if 'conv_first.weight' in state_dict:
         crt_net = {}
-        items = []
-        for k, v in state_dict.items():
-            items.append(k)
+        items = list(state_dict)
 
         crt_net['model.0.weight'] = state_dict['conv_first.weight']
         crt_net['model.0.bias'] = state_dict['conv_first.bias']
@@ -52,9 +48,7 @@ def resrgan2normal(state_dict, nb=23):
     if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict:
         re8x = 0
         crt_net = {}
-        items = []
-        for k, v in state_dict.items():
-            items.append(k)
+        items = list(state_dict)
 
         crt_net['model.0.weight'] = state_dict['conv_first.weight']
         crt_net['model.0.bias'] = state_dict['conv_first.bias']
@@ -138,7 +132,7 @@ class UpscalerESRGAN(Upscaler):
             scaler_data = UpscalerData(self.model_name, self.model_url, self, 4)
             scalers.append(scaler_data)
         for file in model_paths:
-            if "http" in file:
+            if file.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
@@ -147,23 +141,25 @@ class UpscalerESRGAN(Upscaler):
             self.scalers.append(scaler_data)
 
     def do_upscale(self, img, selected_model):
+        try:
             model = self.load_model(selected_model)
-        if model is None:
+        except Exception as e:
+            print(f"Unable to load ESRGAN model {selected_model}: {e}", file=sys.stderr)
             return img
         model.to(devices.device_esrgan)
         img = esrgan_upscale(model, img)
         return img
 
     def load_model(self, path: str):
-        if "http" in path:
-            filename = load_file_from_url(url=self.model_url, model_dir=self.model_path,
-                                          file_name="%s.pth" % self.model_name,
-                                          progress=True)
+        if path.startswith("http"):
+            # TODO: this doesn't use `path` at all?
+            filename = modelloader.load_file_from_url(
+                url=self.model_url,
+                model_dir=self.model_download_path,
+                file_name=f"{self.model_name}.pth",
+            )
         else:
             filename = path
-        if not os.path.exists(filename) or filename is None:
-            print("Unable to load %s from %s" % (self.model_path, filename))
-            return None
 
         state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
 

modules/esrgan_model_arch.py

@@ -1,7 +1,7 @@
 # this file is adapted from https://github.com/victorca25/iNNfer
 
+from collections import OrderedDict
 import math
-import functools
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -37,7 +37,7 @@ class RRDBNet(nn.Module):
         elif upsample_mode == 'pixelshuffle':
             upsample_block = pixelshuffle_block
         else:
-            raise NotImplementedError('upsample mode [{:s}] is not found'.format(upsample_mode))
+            raise NotImplementedError(f'upsample mode [{upsample_mode}] is not found')
         if upscale == 3:
             upsampler = upsample_block(nf, nf, 3, act_type=act_type, convtype=convtype)
         else:
@@ -260,10 +260,10 @@ class Upsample(nn.Module):
 
     def extra_repr(self):
         if self.scale_factor is not None:
-            info = 'scale_factor=' + str(self.scale_factor)
+            info = f'scale_factor={self.scale_factor}'
         else:
-            info = 'size=' + str(self.size)
-        info += ', mode=' + self.mode
+            info = f'size={self.size}'
+        info += f', mode={self.mode}'
         return info
 
 
@@ -349,7 +349,7 @@ def act(act_type, inplace=True, neg_slope=0.2, n_prelu=1, beta=1.0):
     elif act_type == 'sigmoid':  # [0, 1] range output
         layer = nn.Sigmoid()
     else:
-        raise NotImplementedError('activation layer [{:s}] is not found'.format(act_type))
+        raise NotImplementedError(f'activation layer [{act_type}] is not found')
     return layer
 
 
@@ -371,7 +371,7 @@ def norm(norm_type, nc):
     elif norm_type == 'none':
         def norm_layer(x): return Identity()
     else:
-        raise NotImplementedError('normalization layer [{:s}] is not found'.format(norm_type))
+        raise NotImplementedError(f'normalization layer [{norm_type}] is not found')
     return layer
 
 
@@ -387,7 +387,7 @@ def pad(pad_type, padding):
     elif pad_type == 'zero':
         layer = nn.ZeroPad2d(padding)
     else:
-        raise NotImplementedError('padding layer [{:s}] is not implemented'.format(pad_type))
+        raise NotImplementedError(f'padding layer [{pad_type}] is not implemented')
     return layer
 
 
@@ -431,15 +431,17 @@ def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias=
                pad_type='zero', norm_type=None, act_type='relu', mode='CNA', convtype='Conv2D',
                spectral_norm=False):
     """ Conv layer with padding, normalization, activation """
-    assert mode in ['CNA', 'NAC', 'CNAC'], 'Wrong conv mode [{:s}]'.format(mode)
+    assert mode in ['CNA', 'NAC', 'CNAC'], f'Wrong conv mode [{mode}]'
     padding = get_valid_padding(kernel_size, dilation)
     p = pad(pad_type, padding) if pad_type and pad_type != 'zero' else None
     padding = padding if pad_type == 'zero' else 0
 
     if convtype=='PartialConv2D':
+        from torchvision.ops import PartialConv2d  # this is definitely not going to work, but PartialConv2d doesn't work anyway and this shuts up static analyzer
         c = PartialConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
                dilation=dilation, bias=bias, groups=groups)
     elif convtype=='DeformConv2D':
+        from torchvision.ops import DeformConv2d  # not tested
         c = DeformConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
                dilation=dilation, bias=bias, groups=groups)
     elif convtype=='Conv3D':

modules/extensions.py

@@ -1,21 +1,28 @@
 import os
-import sys
-import traceback
+import threading
 
-import git
-
-from modules import paths, shared
+from modules import shared, errors, cache, scripts
+from modules.gitpython_hack import Repo
+from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path  # noqa: F401
 
 extensions = []
-extensions_dir = os.path.join(paths.script_path, "extensions")
-extensions_builtin_dir = os.path.join(paths.script_path, "extensions-builtin")
+
+os.makedirs(extensions_dir, exist_ok=True)
 
 
 def active():
+    if shared.cmd_opts.disable_all_extensions or shared.opts.disable_all_extensions == "all":
+        return []
+    elif shared.cmd_opts.disable_extra_extensions or shared.opts.disable_all_extensions == "extra":
+        return [x for x in extensions if x.enabled and x.is_builtin]
+    else:
         return [x for x in extensions if x.enabled]
 
 
 class Extension:
+    lock = threading.Lock()
+    cached_fields = ['remote', 'commit_date', 'branch', 'commit_hash', 'version']
+
     def __init__(self, name, path, enabled=True, is_builtin=False):
         self.name = name
         self.path = path
@@ -23,27 +30,66 @@ class Extension:
         self.status = ''
         self.can_update = False
         self.is_builtin = is_builtin
+        self.commit_hash = ''
+        self.commit_date = None
+        self.version = ''
+        self.branch = None
+        self.remote = None
+        self.have_info_from_repo = False
 
+    def to_dict(self):
+        return {x: getattr(self, x) for x in self.cached_fields}
+
+    def from_dict(self, d):
+        for field in self.cached_fields:
+            setattr(self, field, d[field])
+
+    def read_info_from_repo(self):
+        if self.is_builtin or self.have_info_from_repo:
+            return
+
+        def read_from_repo():
+            with self.lock:
+                if self.have_info_from_repo:
+                    return
+
+                self.do_read_info_from_repo()
+
+                return self.to_dict()
+        try:
+            d = cache.cached_data_for_file('extensions-git', self.name, os.path.join(self.path, ".git"), read_from_repo)
+            self.from_dict(d)
+        except FileNotFoundError:
+            pass
+        self.status = 'unknown' if self.status == '' else self.status
+
+    def do_read_info_from_repo(self):
         repo = None
         try:
-            if os.path.exists(os.path.join(path, ".git")):
-                repo = git.Repo(path)
+            if os.path.exists(os.path.join(self.path, ".git")):
+                repo = Repo(self.path)
         except Exception:
-            print(f"Error reading github repository info from {path}:", file=sys.stderr)
-            print(traceback.format_exc(), file=sys.stderr)
+            errors.report(f"Error reading github repository info from {self.path}", exc_info=True)
 
         if repo is None or repo.bare:
             self.remote = None
         else:
             try:
                 self.remote = next(repo.remote().urls, None)
-                self.status = 'unknown'
+                commit = repo.head.commit
+                self.commit_date = commit.committed_date
+                if repo.active_branch:
+                    self.branch = repo.active_branch.name
+                self.commit_hash = commit.hexsha
+                self.version = self.commit_hash[:8]
+
             except Exception:
+                errors.report(f"Failed reading extension data from Git repository ({self.name})", exc_info=True)
                 self.remote = None
 
-    def list_files(self, subdir, extension):
-        from modules import scripts
+        self.have_info_from_repo = True
 
+    def list_files(self, subdir, extension):
         dirpath = os.path.join(self.path, subdir)
         if not os.path.isdir(dirpath):
             return []
@@ -57,22 +103,34 @@ class Extension:
         return res
 
     def check_updates(self):
-        repo = git.Repo(self.path)
-        for fetch in repo.remote().fetch("--dry-run"):
+        repo = Repo(self.path)
+        for fetch in repo.remote().fetch(dry_run=True):
             if fetch.flags != fetch.HEAD_UPTODATE:
                 self.can_update = True
-                self.status = "behind"
+                self.status = "new commits"
+                return
+
+        try:
+            origin = repo.rev_parse('origin')
+            if repo.head.commit != origin:
+                self.can_update = True
+                self.status = "behind HEAD"
+                return
+        except Exception:
+            self.can_update = False
+            self.status = "unknown (remote error)"
             return
 
         self.can_update = False
         self.status = "latest"
 
-    def fetch_and_reset_hard(self):
-        repo = git.Repo(self.path)
+    def fetch_and_reset_hard(self, commit='origin'):
+        repo = Repo(self.path)
         # Fix: `error: Your local changes to the following files would be overwritten by merge`,
         # because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
-        repo.git.fetch('--all')
-        repo.git.reset('--hard', 'origin')
+        repo.git.fetch(all=True)
+        repo.git.reset(commit, hard=True)
+        self.have_info_from_repo = False
 
 
 def list_extensions():
@@ -81,7 +139,16 @@ def list_extensions():
     if not os.path.isdir(extensions_dir):
         return
 
-    paths = []
+    if shared.cmd_opts.disable_all_extensions:
+        print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
+    elif shared.opts.disable_all_extensions == "all":
+        print("*** \"Disable all extensions\" option was set, will not load any extensions ***")
+    elif shared.cmd_opts.disable_extra_extensions:
+        print("*** \"--disable-extra-extensions\" arg was used, will only load built-in extensions ***")
+    elif shared.opts.disable_all_extensions == "extra":
+        print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
+
+    extension_paths = []
     for dirname in [extensions_dir, extensions_builtin_dir]:
         if not os.path.isdir(dirname):
             return
@@ -91,9 +158,8 @@ def list_extensions():
             if not os.path.isdir(path):
                 continue
 
-            paths.append((extension_dirname, path, dirname == extensions_builtin_dir))
+            extension_paths.append((extension_dirname, path, dirname == extensions_builtin_dir))
 
-    for dirname, path, is_builtin in paths:
+    for dirname, path, is_builtin in extension_paths:
         extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)
         extensions.append(extension)
-

modules/extra_networks.py

@@ -1,22 +1,48 @@
+import json
+import os
 import re
+import logging
 from collections import defaultdict
 
 from modules import errors
 
 extra_network_registry = {}
+extra_network_aliases = {}
 
 
 def initialize():
     extra_network_registry.clear()
+    extra_network_aliases.clear()
 
 
 def register_extra_network(extra_network):
     extra_network_registry[extra_network.name] = extra_network
 
 
+def register_extra_network_alias(extra_network, alias):
+    extra_network_aliases[alias] = extra_network
+
+
+def register_default_extra_networks():
+    from modules.extra_networks_hypernet import ExtraNetworkHypernet
+    register_extra_network(ExtraNetworkHypernet())
+
+
 class ExtraNetworkParams:
     def __init__(self, items=None):
         self.items = items or []
+        self.positional = []
+        self.named = {}
+
+        for item in self.items:
+            parts = item.split('=', 2) if isinstance(item, str) else [item]
+            if len(parts) == 2:
+                self.named[parts[0]] = parts[1]
+            else:
+                self.positional.append(item)
+
+    def __eq__(self, other):
+        return self.items == other.items
 
 
 class ExtraNetwork:
@@ -61,24 +87,58 @@ class ExtraNetwork:
         raise NotImplementedError
 
 
+def lookup_extra_networks(extra_network_data):
+    """returns a dict mapping ExtraNetwork objects to lists of arguments for those extra networks.
+
+    Example input:
+    {
+        'lora': [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58310>],
+        'lyco': [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58F70>],
+        'hypernet': [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D5A800>]
+    }
+
+    Example output:
+
+    {
+        <extra_networks_lora.ExtraNetworkLora object at 0x0000020581BEECE0>: [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58310>, <modules.extra_networks.ExtraNetworkParams object at 0x0000020690D58F70>],
+        <modules.extra_networks_hypernet.ExtraNetworkHypernet object at 0x0000020581BEEE60>: [<modules.extra_networks.ExtraNetworkParams object at 0x0000020690D5A800>]
+    }
+    """
+
+    res = {}
+
+    for extra_network_name, extra_network_args in list(extra_network_data.items()):
+        extra_network = extra_network_registry.get(extra_network_name, None)
+        alias = extra_network_aliases.get(extra_network_name, None)
+
+        if alias is not None and extra_network is None:
+            extra_network = alias
+
+        if extra_network is None:
+            logging.info(f"Skipping unknown extra network: {extra_network_name}")
+            continue
+
+        res.setdefault(extra_network, []).extend(extra_network_args)
+
+    return res
+
+
 def activate(p, extra_network_data):
     """call activate for extra networks in extra_network_data in specified order, then call
     activate for all remaining registered networks with an empty argument list"""
 
-    for extra_network_name, extra_network_args in extra_network_data.items():
-        extra_network = extra_network_registry.get(extra_network_name, None)
-        if extra_network is None:
-            print(f"Skipping unknown extra network: {extra_network_name}")
-            continue
+    activated = []
+
+    for extra_network, extra_network_args in lookup_extra_networks(extra_network_data).items():
 
         try:
             extra_network.activate(p, extra_network_args)
+            activated.append(extra_network)
         except Exception as e:
-            errors.display(e, f"activating extra network {extra_network_name} with arguments {extra_network_args}")
+            errors.display(e, f"activating extra network {extra_network.name} with arguments {extra_network_args}")
 
     for extra_network_name, extra_network in extra_network_registry.items():
-        args = extra_network_data.get(extra_network_name, None)
-        if args is not None:
+        if extra_network in activated:
             continue
 
         try:
@@ -86,24 +146,24 @@ def activate(p, extra_network_data):
         except Exception as e:
             errors.display(e, f"activating extra network {extra_network_name}")
 
+    if p.scripts is not None:
+        p.scripts.after_extra_networks_activate(p, batch_number=p.iteration, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds, extra_network_data=extra_network_data)
+
 
 def deactivate(p, extra_network_data):
     """call deactivate for extra networks in extra_network_data in specified order, then call
     deactivate for all remaining registered networks"""
 
-    for extra_network_name, extra_network_args in extra_network_data.items():
-        extra_network = extra_network_registry.get(extra_network_name, None)
-        if extra_network is None:
-            continue
+    data = lookup_extra_networks(extra_network_data)
 
+    for extra_network in data:
         try:
             extra_network.deactivate(p)
         except Exception as e:
-            errors.display(e, f"deactivating extra network {extra_network_name}")
+            errors.display(e, f"deactivating extra network {extra_network.name}")
 
     for extra_network_name, extra_network in extra_network_registry.items():
-        args = extra_network_data.get(extra_network_name, None)
-        if args is not None:
+        if extra_network in data:
             continue
 
         try:
@@ -145,3 +205,20 @@ def parse_prompts(prompts):
 
     return res, extra_data
 
+
+def get_user_metadata(filename):
+    if filename is None:
+        return {}
+
+    basename, ext = os.path.splitext(filename)
+    metadata_filename = basename + '.json'
+
+    metadata = {}
+    try:
+        if os.path.isfile(metadata_filename):
+            with open(metadata_filename, "r", encoding="utf8") as file:
+                metadata = json.load(file)
+    except Exception as e:
+        errors.display(e, f"reading extra network user metadata from {metadata_filename}")
+
+    return metadata

modules/extra_networks_hypernet.py

@@ -1,4 +1,4 @@
-from modules import extra_networks
+from modules import extra_networks, shared
 from modules.hypernetworks import hypernetwork
 
 
@@ -7,10 +7,17 @@ class ExtraNetworkHypernet(extra_networks.ExtraNetwork):
         super().__init__('hypernet')
 
     def activate(self, p, params_list):
+        additional = shared.opts.sd_hypernetwork
+
+        if additional != "None" and additional in shared.hypernetworks and not any(x for x in params_list if x.items[0] == additional):
+            hypernet_prompt_text = f"<hypernet:{additional}:{shared.opts.extra_networks_default_multiplier}>"
+            p.all_prompts = [f"{prompt}{hypernet_prompt_text}" for prompt in p.all_prompts]
+            params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
+
         names = []
         multipliers = []
         for params in params_list:
-            assert len(params.items) > 0
+            assert params.items
 
             names.append(params.items[0])
             multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)

modules/extras.py

@@ -1,12 +1,13 @@
 import os
 import re
 import shutil
+import json
 
 
 import torch
 import tqdm
 
-from modules import shared, images, sd_models, sd_vae
+from modules import shared, images, sd_models, sd_vae, sd_models_config, errors
 from modules.ui_common import plaintext_to_html
 import gradio as gr
 import safetensors.torch
@@ -37,7 +38,7 @@ def run_pnginfo(image):
 
 def create_config(ckpt_result, config_source, a, b, c):
     def config(x):
-        res = sd_models.find_checkpoint_config(x) if x else None
+        res = sd_models_config.find_checkpoint_config_near_filename(x) if x else None
         return res if res != shared.sd_default_config else None
 
     if config_source == 0:
@@ -71,9 +72,21 @@ def to_half(tensor, enable):
     return tensor
 
 
-def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights):
-    shared.state.begin()
-    shared.state.job = 'model-merge'
+def read_metadata(primary_model_name, secondary_model_name, tertiary_model_name):
+    metadata = {}
+
+    for checkpoint_name in [primary_model_name, secondary_model_name, tertiary_model_name]:
+        checkpoint_info = sd_models.checkpoints_list.get(checkpoint_name, None)
+        if checkpoint_info is None:
+            continue
+
+        metadata.update(checkpoint_info.metadata)
+
+    return json.dumps(metadata, indent=4, ensure_ascii=False)
+
+
+def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata, add_merge_recipe, copy_metadata_fields, metadata_json):
+    shared.state.begin(job="model-merge")
 
     def fail(message):
         shared.state.textinfo = message
@@ -132,16 +145,17 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
     tertiary_model_info = sd_models.checkpoints_list[tertiary_model_name] if theta_func1 else None
 
     result_is_inpainting_model = False
+    result_is_instruct_pix2pix_model = False
 
     if theta_func2:
-        shared.state.textinfo = f"Loading B"
+        shared.state.textinfo = "Loading B"
         print(f"Loading {secondary_model_info.filename}...")
         theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
     else:
         theta_1 = None
 
     if theta_func1:
-        shared.state.textinfo = f"Loading C"
+        shared.state.textinfo = "Loading C"
         print(f"Loading {tertiary_model_info.filename}...")
         theta_2 = sd_models.read_state_dict(tertiary_model_info.filename, map_location='cpu')
 
@@ -185,9 +199,14 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
             if a.shape != b.shape and a.shape[0:1] + a.shape[2:] == b.shape[0:1] + b.shape[2:]:
                 if a.shape[1] == 4 and b.shape[1] == 9:
                     raise RuntimeError("When merging inpainting model with a normal one, A must be the inpainting model.")
+                if a.shape[1] == 4 and b.shape[1] == 8:
+                    raise RuntimeError("When merging instruct-pix2pix model with a normal one, A must be the instruct-pix2pix model.")
 
+                if a.shape[1] == 8 and b.shape[1] == 4:#If we have an Instruct-Pix2Pix model...
+                    theta_0[key][:, 0:4, :, :] = theta_func2(a[:, 0:4, :, :], b, multiplier)#Merge only the vectors the models have in common.  Otherwise we get an error due to dimension mismatch.
+                    result_is_instruct_pix2pix_model = True
+                else:
                     assert a.shape[1] == 9 and b.shape[1] == 4, f"Bad dimensions for merged layer {key}: A={a.shape}, B={b.shape}"
-
                     theta_0[key][:, 0:4, :, :] = theta_func2(a[:, 0:4, :, :], b, multiplier)
                     result_is_inpainting_model = True
             else:
@@ -226,6 +245,7 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
 
     filename = filename_generator() if custom_name == '' else custom_name
     filename += ".inpainting" if result_is_inpainting_model else ""
+    filename += ".instruct-pix2pix" if result_is_instruct_pix2pix_model else ""
     filename += "." + checkpoint_format
 
     output_modelname = os.path.join(ckpt_dir, filename)
@@ -234,13 +254,72 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
     shared.state.textinfo = "Saving"
     print(f"Saving to {output_modelname}...")
 
+    metadata = {}
+
+    if save_metadata and copy_metadata_fields:
+        if primary_model_info:
+            metadata.update(primary_model_info.metadata)
+        if secondary_model_info:
+            metadata.update(secondary_model_info.metadata)
+        if tertiary_model_info:
+            metadata.update(tertiary_model_info.metadata)
+
+    if save_metadata:
+        try:
+            metadata.update(json.loads(metadata_json))
+        except Exception as e:
+            errors.display(e, "readin metadata from json")
+
+        metadata["format"] = "pt"
+
+    if save_metadata and add_merge_recipe:
+        merge_recipe = {
+            "type": "webui", # indicate this model was merged with webui's built-in merger
+            "primary_model_hash": primary_model_info.sha256,
+            "secondary_model_hash": secondary_model_info.sha256 if secondary_model_info else None,
+            "tertiary_model_hash": tertiary_model_info.sha256 if tertiary_model_info else None,
+            "interp_method": interp_method,
+            "multiplier": multiplier,
+            "save_as_half": save_as_half,
+            "custom_name": custom_name,
+            "config_source": config_source,
+            "bake_in_vae": bake_in_vae,
+            "discard_weights": discard_weights,
+            "is_inpainting": result_is_inpainting_model,
+            "is_instruct_pix2pix": result_is_instruct_pix2pix_model
+        }
+
+        sd_merge_models = {}
+
+        def add_model_metadata(checkpoint_info):
+            checkpoint_info.calculate_shorthash()
+            sd_merge_models[checkpoint_info.sha256] = {
+                "name": checkpoint_info.name,
+                "legacy_hash": checkpoint_info.hash,
+                "sd_merge_recipe": checkpoint_info.metadata.get("sd_merge_recipe", None)
+            }
+
+            sd_merge_models.update(checkpoint_info.metadata.get("sd_merge_models", {}))
+
+        add_model_metadata(primary_model_info)
+        if secondary_model_info:
+            add_model_metadata(secondary_model_info)
+        if tertiary_model_info:
+            add_model_metadata(tertiary_model_info)
+
+        metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
+        metadata["sd_merge_models"] = json.dumps(sd_merge_models)
+
     _, extension = os.path.splitext(output_modelname)
     if extension.lower() == ".safetensors":
-        safetensors.torch.save_file(theta_0, output_modelname, metadata={"format": "pt"})
+        safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata if len(metadata)>0 else None)
     else:
         torch.save(theta_0, output_modelname)
 
     sd_models.list_models()
+    created_model = next((ckpt for ckpt in sd_models.checkpoints_list.values() if ckpt.name == filename), None)
+    if created_model:
+        created_model.calculate_shorthash()
 
     create_config(output_modelname, config_source, primary_model_info, secondary_model_info, tertiary_model_info)