gradio 3.41.2 attempt

json.dump(ensure_ascii=False)

.eslintrc.js

@@ -74,6 +74,7 @@ module.exports = {
         create_submit_args: "readonly",
         restart_reload: "readonly",
         updateInput: "readonly",
+        onEdit: "readonly",
         //extraNetworks.js
         requestGet: "readonly",
         popup: "readonly",
@@ -87,5 +88,11 @@ module.exports = {
         modalNextImage: "readonly",
         // token-counters.js
         setupTokenCounters: "readonly",
+        // localStorage.js
+        localSet: "readonly",
+        localGet: "readonly",
+        localRemove: "readonly",
+        // resizeHandle.js
+        setupResizeHandle: "writable"
     }
 };

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,35 +1,55 @@
 name: Bug Report
-description: You think somethings is broken in the UI
+description: You think something is broken in the UI
 title: "[Bug]: "
 labels: ["bug-report"]
 
 body:
-  - type: checkboxes
-    attributes:
-      label: Is there an existing issue for this?
-      description: Please search to see if an issue already exists for the bug you encountered, and that it hasn't been fixed in a recent build/commit.
-      options:
-        - label: I have searched the existing issues and checked the recent builds/commits
-          required: true
   - type: markdown
     attributes:
       value: |
-        *Please fill this form with as much information as possible, don't forget to fill "What OS..." and "What browsers" and *provide screenshots if possible**
+        > The title of the bug report should be short and descriptive.
+        > Use relevant keywords for searchability.
+        > Do not leave it blank, but also do not put an entire error log in it.
+  - type: checkboxes
+    attributes:
+      label: Checklist
+      description: |
+        Please perform basic debugging to see if extensions or configuration is the cause of the issue.
+        Basic debug procedure
+        　1. Disable all third-party extensions - check if extension is the cause
+        　2. Update extensions and webui - sometimes things just need to be updated
+        　3. Backup and remove your config.json and ui-config.json - check if the issue is caused by bad configuration
+        　4. Delete venv with third-party extensions disabled - sometimes extensions might cause wrong libraries to be installed
+        　5. Try a fresh installation webui in a different directory - see if a clean installation solves the issue
+        Before making a issue report please, check that the issue hasn't been reported recently.
+      options:
+        - label: The issue exists after disabling all extensions
+        - label: The issue exists on a clean installation of webui
+        - label: The issue is caused by an extension, but I believe it is caused by a bug in the webui
+        - label: The issue exists in the current version of the webui
+        - label: The issue has not been reported before recently
+        - label: The issue has been reported before but has not been fixed yet
+  - type: markdown
+    attributes:
+      value: |
+        > Please fill this form with as much information as possible. Don't forget to "Upload Sysinfo" and "What browsers" and provide screenshots if possible
   - type: textarea
     id: what-did
     attributes:
       label: What happened?
       description: Tell us what happened in a very clear and simple way
+      placeholder: |
+        txt2img is not working as intended.
     validations:
       required: true
   - type: textarea
     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: |
+      placeholder: |
-        1. Go to .... 
+        1. Go to ...
-        2. Press ....
+        2. Press ...
         3. ...
     validations:
       required: true
@@ -37,64 +57,9 @@ 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:
+      placeholder: |
-      required: true
+        WebUI should ...
-  - type: input
-    id: commit
-    attributes:
-      label: Version or Commit where the problem happens
-      description: "Which webui version or 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 **Version: v1.2.3** link at the bottom of the UI, or from the cmd/terminal if you can't launch it.)"
-    validations:
-      required: true
-  - type: dropdown
-    id: py-version
-    attributes:
-      label: What Python version are you running on ?
-      multiple: false
-      options:
-        - Python 3.10.x
-        - Python 3.11.x (above, no supported yet)
-        - Python 3.9.x (below, no recommended)
-  - type: dropdown
-    id: platforms
-    attributes:
-      label: What platforms do you use to access the UI ?
-      multiple: true
-      options:
-        - Windows
-        - Linux
-        - MacOS
-        - iOS
-        - Android
-        - Other/Cloud
-  - type: dropdown
-    id: device
-    attributes:
-        label: What device are you running WebUI on?
-        multiple: true
-        options:
-        - Nvidia GPUs (RTX 20 above)
-        - Nvidia GPUs (GTX 16 below)
-        - AMD GPUs (RX 6000 above)
-        - AMD GPUs (RX 5000 below)
-        - CPU
-        - Other GPUs
-  - type: dropdown
-    id: cross_attention_opt
-    attributes:
-      label: Cross attention optimization
-      description: What cross attention optimization are you using, Settings -> Optimizations -> Cross attention optimization
-      multiple: false
-      options:
-        - Automatic
-        - xformers
-        - sdp-no-mem
-        - sdp
-        - Doggettx
-        - V1 
-        - InvokeAI
-        - "None "
     validations:
       required: true
   - type: dropdown
@@ -108,26 +73,25 @@ body:
         - Brave
         - Apple Safari
         - Microsoft Edge
+        - Android
+        - iOS
+        - Other
   - type: textarea
-    id: cmdargs
+    id: sysinfo
     attributes:
-      label: Command Line Arguments
+      label: Sysinfo
-      description: Are you using any launching parameters/command line arguments (modified webui-user .bat/.sh) ? If yes, please write them below. Write "No" otherwise.
+      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.
-      render: Shell
+      placeholder: |
-    validations:
+        1. Go to WebUI Settings -> Sysinfo -> Download system info.
-      required: true
+            If WebUI fails to launch, use --dump-sysinfo commandline argument to generate the file
-  - type: textarea
+        2. Upload the Sysinfo as a attached file, Do NOT paste it in as plain text.
-    id: extensions
-    attributes:
-      label: List of extensions
-      description: Are you using any extensions other than built-ins? If yes, provide a list, you can copy it at "Extensions" tab. Write "No" otherwise.
     validations:
       required: true
   - type: textarea
     id: logs
     attributes:
       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.
+      description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occured. If it's very long, provide a link to pastebin or similar service.
       render: Shell
     validations:
       required: true
@@ -135,4 +99,7 @@ body:
     id: misc
     attributes:
       label: Additional information
-      description: Please provide us with any relevant additional info or context.
+      description: | 
+        Please provide us with any relevant additional info or context.
+        Examples:
+        　I have updated my GPU driver recently.

.github/workflows/on_pull_request.yaml

@@ -1,4 +1,4 @@
-name: Run Linting/Formatting on Pull Requests
+name: Linter
 
 on:
   - push
@@ -6,7 +6,9 @@ on:
 
 jobs:
   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
@@ -18,11 +20,13 @@ jobs:
           #     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==0.0.265
+        run: pip install ruff==0.1.6
       - 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

.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
@@ -39,10 +41,11 @@ jobs:
           --skip-prepare-environment
           --skip-torch-cuda-test
           --test-server
+          --do-not-download-clip
           --no-half
           --disable-opt-split-attention
           --use-cpu all
-          --add-stop-route
+          --api-server-stop
           2>&1 | tee output.txt &
       - name: Run tests
         run: |
@@ -50,7 +53,7 @@ jobs:
           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/_stop && sleep 10
+        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*

.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

CHANGELOG.md

@@ -1,3 +1,258 @@
+## 1.6.1
+
+### Bug Fixes:
+ * fix an error causing the webui to fail to start ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))
+
+## 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:

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

@@ -78,7 +78,7 @@ 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
@@ -88,19 +88,23 @@ A browser interface based on Gradio library for Stable Diffusion.
 - [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
+- [Segmind Stable Diffusion](https://huggingface.co/segmind/SSD-1B) support
 
 ## 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 it's contents.
+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)
@@ -115,15 +119,17 @@ Alternatively, use online services (like Google Colab):
 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
+sudo dnf install wget git python3 gperftools-libs libglvnd-glx 
+# openSUSE-based:
+sudo zypper install wget git python3 libtcmalloc4 libglvnd
 # Arch-based:
 sudo pacman -S wget git python3
 ```
 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.
@@ -135,12 +141,15 @@ 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.
 
-- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
+- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
 - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
 - GFPGAN - https://github.com/TencentARC/GFPGAN.git
 - CodeFormer - https://github.com/sczhou/CodeFormer
@@ -165,5 +174,8 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - 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
+- Hypertile - tfernd - https://github.com/tfernd/HyperTile
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

configs/alt-diffusion-m18-inference.yaml

@@ -0,0 +1,73 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    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: [ 10000 ]
+        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: 4
+        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
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        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: modules.xlmr_m18.BertSeriesModelWithTransformation
+      params:
+        name: "XLMR-Large"

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
 
@@ -112,8 +112,7 @@ class LDSR:
 
 
         gc.collect()
-        if torch.cuda.is_available:
+        devices.torch_gc()
-            torch.cuda.empty_cache()
 
         im_og = image
         width_og, height_og = im_og.size
@@ -150,8 +149,7 @@ class LDSR:
 
         del model
         gc.collect()
-        if torch.cuda.is_available:
+        devices.torch_gc()
-            torch.cuda.empty_cache()
 
         return a
 

extensions-builtin/LDSR/scripts/ldsr_model.py

@@ -1,7 +1,6 @@
 import os
 
-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, errors
@@ -43,20 +42,17 @@ class UpscalerLDSR(Upscaler):
         if local_safetensors_path is not None and os.path.exists(local_safetensors_path):
             model = local_safetensors_path
         else:
-            model = local_ckpt_path if local_ckpt_path is not None else load_file_from_url(url=self.model_url, model_dir=self.model_download_path, file_name="model.ckpt", progress=True)
+            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 if local_yaml_path is not None else load_file_from_url(url=self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml", progress=True)
+        yaml = local_yaml_path or load_file_from_url(self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml")
 
-        try:
         return LDSR(model, yaml)
-        except Exception:
-            errors.report("Error importing LDSR", exc_info=True)
-        return None
 
     def do_upscale(self, img, path):
+        try:
             ldsr = self.load_model(path)
-        if ldsr is None:
+        except Exception:
-            print("NO LDSR!")
+            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/Lora/extra_networks_lora.py

@@ -1,32 +1,51 @@
 from modules import extra_networks, shared
-import lora
+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
 
-        if additional != "None" and additional in lora.available_loras and not any(x for x in params_list if x.items[0] == additional):
+        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 params.items
 
-            names.append(params.items[0])
+            names.append(params.positional[0])
-            multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
 
-        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:
-            lora_hashes = []
+            network_hashes = []
-            for item in lora.loaded_loras:
+            for item in networks.loaded_networks:
-                shorthash = item.lora_on_disk.shorthash
+                shorthash = item.network_on_disk.shorthash
                 if not shorthash:
                     continue
 
@@ -36,10 +55,13 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
 
                 alias = alias.replace(":", "").replace(",", "")
 
-                lora_hashes.append(f"{alias}: {shorthash}")
+                network_hashes.append(f"{alias}: {shorthash}")
 
-            if lora_hashes:
+            if network_hashes:
-                p.extra_generation_params["Lora hashes"] = ", ".join(lora_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

@@ -1,506 +1,9 @@
-import os
+import networks
-import re
-import torch
-from typing import Union
 
-from modules import shared, devices, sd_models, errors, scripts, sd_hijack, hashes
+list_available_loras = networks.list_available_networks
 
-metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
+available_loras = networks.available_networks
-
+available_lora_aliases = networks.available_network_aliases
-re_digits = re.compile(r"\d+")
+available_lora_hash_lookup = networks.available_network_hash_lookup
-re_x_proj = re.compile(r"(.*)_([qkv]_proj)$")
+forbidden_lora_aliases = networks.forbidden_network_aliases
-re_compiled = {}
+loaded_loras = networks.loaded_networks
-
-suffix_conversion = {
-    "attentions": {},
-    "resnets": {
-        "conv1": "in_layers_2",
-        "conv2": "out_layers_3",
-        "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_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]}"
-
-    return key
-
-
-class LoraOnDisk:
-    def __init__(self, name, filename):
-        self.name = name
-        self.filename = filename
-        self.metadata = {}
-        self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
-
-        if self.is_safetensors:
-            try:
-                self.metadata = sd_models.read_metadata_from_safetensors(filename)
-            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.ssmd_cover_images = self.metadata.pop('ssmd_cover_images', None)  # those are cover images and they are too big to display in UI as text
-        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
-            ''
-        )
-
-    def set_hash(self, v):
-        self.hash = v
-        self.shorthash = self.hash[0:12]
-
-        if self.shorthash:
-            available_lora_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):
-        if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in forbidden_lora_aliases:
-            return self.name
-        else:
-            return self.alias
-
-
-class LoraModule:
-    def __init__(self, name, lora_on_disk: LoraOnDisk):
-        self.name = name
-        self.lora_on_disk = lora_on_disk
-        self.multiplier = 1.0
-        self.modules = {}
-        self.mtime = None
-
-        self.mentioned_name = None
-        """the text that was used to add lora to prompt - can be either name or an alias"""
-
-
-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, lora_on_disk):
-    lora = LoraModule(name, lora_on_disk)
-    lora.mtime = os.path.getmtime(lora_on_disk.filename)
-
-    sd = sd_models.read_state_dict(lora_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, 'lora_layer_mapping'):
-        assign_lora_names_to_compvis_modules(shared.sd_model)
-
-    keys_failed_to_match = {}
-    is_sd2 = 'model_transformer_resblocks' in shared.sd_model.lora_layer_mapping
-
-    for key_diffusers, weight in sd.items():
-        key_diffusers_without_lora_parts, lora_key = key_diffusers.split(".", 1)
-        key = convert_diffusers_name_to_compvis(key_diffusers_without_lora_parts, is_sd2)
-
-        sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
-
-        if sd_module is None:
-            m = re_x_proj.match(key)
-            if m:
-                sd_module = shared.sd_model.lora_layer_mapping.get(m.group(1), None)
-
-        if sd_module is None:
-            keys_failed_to_match[key_diffusers] = key
-            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.modules.linear.NonDynamicallyQuantizableLinear:
-            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
-        elif type(sd_module) == torch.nn.MultiheadAttention:
-            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
-        elif type(sd_module) == torch.nn.Conv2d and weight.shape[2:] == (1, 1):
-            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
-        elif type(sd_module) == torch.nn.Conv2d and weight.shape[2:] == (3, 3):
-            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (3, 3), bias=False)
-        else:
-            print(f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}')
-            continue
-            raise AssertionError(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.cpu, dtype=devices.dtype)
-
-        if lora_key == "lora_up.weight":
-            lora_module.up = module
-        elif lora_key == "lora_down.weight":
-            lora_module.down = module
-        else:
-            raise AssertionError(f"Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha")
-
-    if keys_failed_to_match:
-        print(f"Failed to match keys when loading Lora {lora_on_disk.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_lora_aliases.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_lora_aliases.get(name, None) for name in names]
-
-    failed_to_load_loras = []
-
-    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:
-                try:
-                    lora = load_lora(name, lora_on_disk)
-                except Exception as e:
-                    errors.display(e, f"loading Lora {lora_on_disk.filename}")
-                    continue
-
-            lora.mentioned_name = name
-
-            lora_on_disk.read_hash()
-
-        if lora is None:
-            failed_to_load_loras.append(name)
-            print(f"Couldn't find Lora with name {name}")
-            continue
-
-        lora.multiplier = multipliers[i] if multipliers else 1.0
-        loaded_loras.append(lora)
-
-    if failed_to_load_loras:
-        sd_hijack.model_hijack.comments.append("Failed to find Loras: " + ", ".join(failed_to_load_loras))
-
-
-def lora_calc_updown(lora, module, target):
-    with torch.no_grad():
-        up = module.up.weight.to(target.device, dtype=target.dtype)
-        down = module.down.weight.to(target.device, dtype=target.dtype)
-
-        if up.shape[2:] == (1, 1) and down.shape[2:] == (1, 1):
-            updown = (up.squeeze(2).squeeze(2) @ down.squeeze(2).squeeze(2)).unsqueeze(2).unsqueeze(3)
-        elif up.shape[2:] == (3, 3) or down.shape[2:] == (3, 3):
-            updown = torch.nn.functional.conv2d(down.permute(1, 0, 2, 3), up).permute(1, 0, 2, 3)
-        else:
-            updown = up @ down
-
-        updown = updown * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
-
-        return updown
-
-
-def lora_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
-    weights_backup = getattr(self, "lora_weights_backup", None)
-
-    if weights_backup is None:
-        return
-
-    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)
-
-
-def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
-    """
-    Applies the currently selected set of Loras to the weights of torch layer self.
-    If weights already have this particular set of loras applied, does nothing.
-    If not, restores orginal weights from backup and alters weights according to loras.
-    """
-
-    lora_layer_name = getattr(self, 'lora_layer_name', None)
-    if lora_layer_name is None:
-        return
-
-    current_names = getattr(self, "lora_current_names", ())
-    wanted_names = tuple((x.name, x.multiplier) for x in loaded_loras)
-
-    weights_backup = getattr(self, "lora_weights_backup", None)
-    if weights_backup is None:
-        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.lora_weights_backup = weights_backup
-
-    if current_names != wanted_names:
-        lora_restore_weights_from_backup(self)
-
-        for lora in loaded_loras:
-            module = lora.modules.get(lora_layer_name, None)
-            if module is not None and hasattr(self, 'weight'):
-                self.weight += lora_calc_updown(lora, module, self.weight)
-                continue
-
-            module_q = lora.modules.get(lora_layer_name + "_q_proj", None)
-            module_k = lora.modules.get(lora_layer_name + "_k_proj", None)
-            module_v = lora.modules.get(lora_layer_name + "_v_proj", None)
-            module_out = lora.modules.get(lora_layer_name + "_out_proj", None)
-
-            if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
-                updown_q = lora_calc_updown(lora, module_q, self.in_proj_weight)
-                updown_k = lora_calc_updown(lora, module_k, self.in_proj_weight)
-                updown_v = lora_calc_updown(lora, module_v, self.in_proj_weight)
-                updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
-
-                self.in_proj_weight += updown_qkv
-                self.out_proj.weight += lora_calc_updown(lora, module_out, self.out_proj.weight)
-                continue
-
-            if module is None:
-                continue
-
-            print(f'failed to calculate lora weights for layer {lora_layer_name}')
-
-        self.lora_current_names = wanted_names
-
-
-def lora_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_loras) == 0:
-        return original_forward(module, input)
-
-    input = devices.cond_cast_unet(input)
-
-    lora_restore_weights_from_backup(module)
-    lora_reset_cached_weight(module)
-
-    res = original_forward(module, input)
-
-    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 None:
-            continue
-
-        module.up.to(device=devices.device)
-        module.down.to(device=devices.device)
-
-        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_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
-    self.lora_current_names = ()
-    self.lora_weights_backup = None
-
-
-def lora_Linear_forward(self, input):
-    if shared.opts.lora_functional:
-        return lora_forward(self, input, torch.nn.Linear_forward_before_lora)
-
-    lora_apply_weights(self)
-
-    return torch.nn.Linear_forward_before_lora(self, input)
-
-
-def lora_Linear_load_state_dict(self, *args, **kwargs):
-    lora_reset_cached_weight(self)
-
-    return torch.nn.Linear_load_state_dict_before_lora(self, *args, **kwargs)
-
-
-def lora_Conv2d_forward(self, input):
-    if shared.opts.lora_functional:
-        return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora)
-
-    lora_apply_weights(self)
-
-    return torch.nn.Conv2d_forward_before_lora(self, input)
-
-
-def lora_Conv2d_load_state_dict(self, *args, **kwargs):
-    lora_reset_cached_weight(self)
-
-    return torch.nn.Conv2d_load_state_dict_before_lora(self, *args, **kwargs)
-
-
-def lora_MultiheadAttention_forward(self, *args, **kwargs):
-    lora_apply_weights(self)
-
-    return torch.nn.MultiheadAttention_forward_before_lora(self, *args, **kwargs)
-
-
-def lora_MultiheadAttention_load_state_dict(self, *args, **kwargs):
-    lora_reset_cached_weight(self)
-
-    return torch.nn.MultiheadAttention_load_state_dict_before_lora(self, *args, **kwargs)
-
-
-def list_available_loras():
-    available_loras.clear()
-    available_lora_aliases.clear()
-    forbidden_lora_aliases.clear()
-    available_lora_hash_lookup.clear()
-    forbidden_lora_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"]))
-    for filename in sorted(candidates, key=str.lower):
-        if os.path.isdir(filename):
-            continue
-
-        name = os.path.splitext(os.path.basename(filename))[0]
-        try:
-            entry = LoraOnDisk(name, filename)
-        except OSError:  # should catch FileNotFoundError and PermissionError etc.
-            errors.report(f"Failed to load LoRA {name} from {filename}", exc_info=True)
-            continue
-
-        available_loras[name] = entry
-
-        if entry.alias in available_lora_aliases:
-            forbidden_lora_aliases[entry.alias.lower()] = 1
-
-        available_lora_aliases[name] = entry
-        available_lora_aliases[entry.alias] = entry
-
-
-re_lora_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_lora_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)
-
-
-available_loras = {}
-available_lora_aliases = {}
-available_lora_hash_lookup = {}
-forbidden_lora_aliases = {}
-loaded_loras = []
-
-list_available_loras()

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 +1,68 @@
+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)
+
+
+# copied from https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/lokr.py
+def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
+    '''
+    return a tuple of two value of input dimension decomposed by the number closest to factor
+    second value is higher or equal than first value.
+
+    In LoRA with Kroneckor Product, first value is a value for weight scale.
+    secon value is a value for weight.
+
+    Becuase of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
+
+    examples)
+    factor
+        -1               2                4               8               16               ...
+    127 -> 1, 127   127 -> 1, 127    127 -> 1, 127   127 -> 1, 127   127 -> 1, 127
+    128 -> 8, 16    128 -> 2, 64     128 -> 4, 32    128 -> 8, 16    128 -> 8, 16
+    250 -> 10, 25   250 -> 2, 125    250 -> 2, 125   250 -> 5, 50    250 -> 10, 25
+    360 -> 8, 45    360 -> 2, 180    360 -> 4, 90    360 -> 8, 45    360 -> 12, 30
+    512 -> 16, 32   512 -> 2, 256    512 -> 4, 128   512 -> 8, 64    512 -> 16, 32
+    1024 -> 32, 32  1024 -> 2, 512   1024 -> 4, 256  1024 -> 8, 128  1024 -> 16, 64
+    '''
+
+    if factor > 0 and (dimension % factor) == 0:
+        m = factor
+        n = dimension // factor
+        if m > n:
+            n, m = m, n
+        return m, n
+    if factor < 0:
+        factor = dimension
+    m, n = 1, dimension
+    length = m + n
+    while m<n:
+        new_m = m + 1
+        while dimension%new_m != 0:
+            new_m += 1
+        new_n = dimension // new_m
+        if new_m + new_n > length or new_m>factor:
+            break
+        else:
+            m, n = new_m, new_n
+    if m > n:
+        n, m = m, n
+    return m, n
+

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_glora.py

@@ -0,0 +1,33 @@
+
+import network
+
+class ModuleTypeGLora(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["a1.weight", "a2.weight", "alpha", "b1.weight", "b2.weight"]):
+            return NetworkModuleGLora(net, weights)
+
+        return None
+
+# adapted from https://github.com/KohakuBlueleaf/LyCORIS
+class NetworkModuleGLora(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["a1.weight"]
+        self.w1b = weights.w["b1.weight"]
+        self.w2a = weights.w["a2.weight"]
+        self.w2b = weights.w["b2.weight"]
+
+    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)]
+        updown = ((w2b @ w1b) + ((orig_weight @ w2a) @ w1a))
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

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/network_oft.py

@@ -0,0 +1,97 @@
+import torch
+import network
+from lyco_helpers import factorization
+from einops import rearrange
+
+
+class ModuleTypeOFT(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["oft_blocks"]) or all(x in weights.w for x in ["oft_diag"]):
+            return NetworkModuleOFT(net, weights)
+
+        return None
+
+# Supports both kohya-ss' implementation of COFT  https://github.com/kohya-ss/sd-scripts/blob/main/networks/oft.py
+# and KohakuBlueleaf's implementation of OFT/COFT https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/diag_oft.py
+class NetworkModuleOFT(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+
+        super().__init__(net, weights)
+
+        self.lin_module = None
+        self.org_module: list[torch.Module] = [self.sd_module]
+
+        # kohya-ss
+        if "oft_blocks" in weights.w.keys():
+            self.is_kohya = True
+            self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size)
+            self.alpha = weights.w["alpha"] # alpha is constraint
+            self.dim = self.oft_blocks.shape[0] # lora dim
+        # LyCORIS
+        elif "oft_diag" in weights.w.keys():
+            self.is_kohya = False
+            self.oft_blocks = weights.w["oft_diag"]
+            # self.alpha is unused
+            self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
+
+        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear]
+        is_conv = type(self.sd_module) in [torch.nn.Conv2d]
+        is_other_linear = type(self.sd_module) in [torch.nn.MultiheadAttention] # unsupported
+
+        if is_linear:
+            self.out_dim = self.sd_module.out_features
+        elif is_conv:
+            self.out_dim = self.sd_module.out_channels
+        elif is_other_linear:
+            self.out_dim = self.sd_module.embed_dim
+
+        if self.is_kohya:
+            self.constraint = self.alpha * self.out_dim
+            self.num_blocks = self.dim
+            self.block_size = self.out_dim // self.dim
+        else:
+            self.constraint = None
+            self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
+
+    def calc_updown_kb(self, orig_weight, multiplier):
+        oft_blocks = self.oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
+        oft_blocks = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
+
+        R = oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
+        R = R * multiplier + torch.eye(self.block_size, device=orig_weight.device)
+
+        # This errors out for MultiheadAttention, might need to be handled up-stream
+        merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
+        merged_weight = torch.einsum(
+            'k n m, k n ... -> k m ...',
+            R,
+            merged_weight
+        )
+        merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
+
+        updown = merged_weight.to(orig_weight.device, dtype=orig_weight.dtype) - orig_weight
+        output_shape = orig_weight.shape
+        return self.finalize_updown(updown, orig_weight, output_shape)
+
+    def calc_updown(self, orig_weight):
+        # if alpha is a very small number as in coft, calc_scale() will return a almost zero number so we ignore it
+        multiplier = self.multiplier()
+        return self.calc_updown_kb(orig_weight, multiplier)
+
+    # override to remove the multiplier/scale factor; it's already multiplied in get_weight
+    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, ex_bias

extensions-builtin/Lora/networks.py

@@ -0,0 +1,628 @@
+import logging
+import os
+import re
+
+import lora_patches
+import network
+import network_lora
+import network_glora
+import network_hada
+import network_ia3
+import network_lokr
+import network_full
+import network_norm
+import network_oft
+
+import torch
+from typing import Union
+
+from modules import shared, devices, sd_models, errors, scripts, sd_hijack
+import modules.textual_inversion.textual_inversion as textual_inversion
+
+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(),
+    network_glora.ModuleTypeGLora(),
+    network_oft.ModuleTypeOFT(),
+]
+
+
+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)
+
+        # kohya_ss OFT module
+        elif sd_module is None and "oft_unet" in key_network_without_network_parts:
+            key = key_network_without_network_parts.replace("oft_unet", "diffusion_model")
+            sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+        # KohakuBlueLeaf OFT module
+        if sd_module is None and "oft_diag" in key:
+            key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
+            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)
+
+        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():
+        embedding = textual_inversion.create_embedding_from_data(data, emb_name, filename=network_on_disk.filename + "/" + emb_name)
+        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:
+                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

@@ -1,72 +1,53 @@
 import re
 
-import torch
 import gradio as gr
 from fastapi import FastAPI
 
-import lora
+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, shared
 
+
 def unload():
-    torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora
+    networks.originals.undo()
-    torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_lora
-    torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_lora
-    torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_lora
-    torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_lora
-    torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_lora
 
 
 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'):
+networks.originals = lora_patches.LoraPatches()
-    torch.nn.Linear_forward_before_lora = torch.nn.Linear.forward
 
-if not hasattr(torch.nn, 'Linear_load_state_dict_before_lora'):
+script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
-    torch.nn.Linear_load_state_dict_before_lora = torch.nn.Linear._load_from_state_dict
-
-if not hasattr(torch.nn, 'Conv2d_forward_before_lora'):
-    torch.nn.Conv2d_forward_before_lora = torch.nn.Conv2d.forward
-
-if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_lora'):
-    torch.nn.Conv2d_load_state_dict_before_lora = torch.nn.Conv2d._load_from_state_dict
-
-if not hasattr(torch.nn, 'MultiheadAttention_forward_before_lora'):
-    torch.nn.MultiheadAttention_forward_before_lora = torch.nn.MultiheadAttention.forward
-
-if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_lora'):
-    torch.nn.MultiheadAttention_load_state_dict_before_lora = torch.nn.MultiheadAttention._load_from_state_dict
-
-torch.nn.Linear.forward = lora.lora_Linear_forward
-torch.nn.Linear._load_from_state_dict = lora.lora_Linear_load_state_dict
-torch.nn.Conv2d.forward = lora.lora_Conv2d_forward
-torch.nn.Conv2d._load_from_state_dict = lora.lora_Conv2d_load_state_dict
-torch.nn.MultiheadAttention.forward = lora.lora_MultiheadAttention_forward
-torch.nn.MultiheadAttention._load_from_state_dict = lora.lora_MultiheadAttention_load_state_dict
-
-script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules)
 script_callbacks.on_script_unloaded(unload)
 script_callbacks.on_before_ui(before_ui)
-script_callbacks.on_infotext_pasted(lora.infotext_pasted)
+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 Lora to prompt", gr.Dropdown, lambda: {"choices": ["None", *lora.available_loras]}, refresh=lora.list_available_loras),
+    "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: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
+    "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: lora.LoraOnDisk):
+def create_lora_json(obj: network.NetworkOnDisk):
     return {
         "name": obj.name,
         "alias": obj.alias,
@@ -75,17 +56,17 @@ def create_lora_json(obj: lora.LoraOnDisk):
     }
 
 
-def api_loras(_: gr.Blocks, app: FastAPI):
+def api_networks(_: gr.Blocks, app: FastAPI):
     @app.get("/sdapi/v1/loras")
     async def get_loras():
-        return [create_lora_json(obj) for obj in lora.available_loras.values()]
+        return [create_lora_json(obj) for obj in networks.available_networks.values()]
 
     @app.post("/sdapi/v1/refresh-loras")
     async def refresh_loras():
-        return lora.list_available_loras()
+        return networks.list_available_networks()
 
 
-script_callbacks.on_app_started(api_loras)
+script_callbacks.on_app_started(api_networks)
 
 re_lora = re.compile("<lora:([^:]+):")
 
@@ -98,19 +79,21 @@ def infotext_pasted(infotext, d):
     hashes = [x.strip().split(':', 1) for x in hashes.split(",")]
     hashes = {x[0].strip().replace(",", ""): x[1].strip() for x in hashes}
 
-    def lora_replacement(m):
+    def network_replacement(m):
         alias = m.group(1)
         shorthash = hashes.get(alias)
         if shorthash is None:
             return m.group(0)
 
-        lora_on_disk = lora.available_lora_hash_lookup.get(shorthash)
+        network_on_disk = networks.available_network_hash_lookup.get(shorthash)
-        if lora_on_disk is None:
+        if network_on_disk is None:
             return m.group(0)
 
-        return f'<lora:{lora_on_disk.get_alias()}:'
+        return f'<lora:{network_on_disk.get_alias()}:'
 
-    d["Prompt"] = re.sub(re_lora, lora_replacement, d["Prompt"])
+    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 +13,70 @@ 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)
+        if lora_on_disk is None:
+            return
 
-    def list_items(self):
-        for index, (name, lora_on_disk) in enumerate(lora.available_loras.items()):
         path, ext = os.path.splitext(lora_on_disk.filename)
 
         alias = lora_on_disk.get_alias()
 
-            yield {
+        item = {
             "name": name,
-                "filename": path,
+            "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),
+            "search_term": self.search_terms_from_path(lora_on_disk.filename) + " " + (lora_on_disk.hash or ""),
-                "prompt": json.dumps(f"<lora:{alias}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
             "local_preview": f"{path}.{shared.opts.samples_format}",
-                "metadata": json.dumps(lora_on_disk.metadata, indent=4) if lora_on_disk.metadata else None,
+            "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):
+        self.read_user_metadata(item)
-        return [shared.cmd_opts.lora_dir]
+        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):
+        # instantiate a list to protect against concurrent modification
+        names = list(networks.available_networks)
+        for index, name in enumerate(names):
+            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

@@ -1,4 +1,3 @@
-import os.path
 import sys
 
 import PIL.Image
@@ -6,12 +5,11 @@ import numpy as np
 import torch
 from tqdm import tqdm
 
-from basicsr.utils.download_util import load_file_from_url
-
 import modules.upscaler
 from modules import devices, modelloader, script_callbacks, errors
-from scunet_model_arch import SCUNet as net
+from scunet_model_arch import SCUNet
 
+from modules.modelloader import load_file_from_url
 from modules.shared import opts
 
 
@@ -28,7 +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)
@@ -87,11 +85,12 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
 
     def do_upscale(self, img: PIL.Image.Image, selected_file):
 
-        torch.cuda.empty_cache()
+        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}", file=sys.stderr)
+            print(f"ScuNET: Unable to load model from {selected_file}: {e}", file=sys.stderr)
             return img
 
         device = devices.get_device_for('scunet')
@@ -111,7 +110,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         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
-        torch.cuda.empty_cache()
+        devices.torch_gc()
 
         output = np_output.transpose((1, 2, 0))  # CHW to HWC
         output = output[:, :, ::-1]  # BGR to RGB
@@ -119,15 +118,12 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
 
     def load_model(self, path: str):
         device = devices.get_device_for('scunet')
-        if "http" in path:
+        if path.startswith("http"):
-            filename = load_file_from_url(url=self.model_url, model_dir=self.model_download_path, file_name="%s.pth" % self.name, progress=True)
+            # 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:
+        model = SCUNet(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
-            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.load_state_dict(torch.load(filename), strict=True)
         model.eval()
         for _, v in model.named_parameters():

extensions-builtin/SwinIR/scripts/swinir_model.py

@@ -1,34 +1,35 @@
-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 opts, state
-from swinir_model_arch import SwinIR as net
+from swinir_model_arch import SwinIR
-from swinir_model_arch_v2 import Swin2SR as net2
+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" \
+        self.model_url = SWINIR_MODEL_URL
-                         "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \
-                         "-L_x4_GAN.pth "
         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)
@@ -37,27 +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:
+        devices.torch_gc()
-            torch.cuda.empty_cache()
-        except Exception:
-            pass
         return img
 
     def load_model(self, path, scale=4):
-        if "http" in path:
+        if path.startswith("http"):
-            dl_name = "%s%s" % (self.model_name.replace(" ", "_"), ".pth")
+            filename = modelloader.load_file_from_url(
-            filename = load_file_from_url(url=path, model_dir=self.model_download_path, file_name=dl_name, progress=True)
+                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,
@@ -72,7 +85,7 @@ class UpscalerSwinIR(Upscaler):
             )
             params = None
         else:
-            model = net(
+            model = SwinIR(
                 upscale=scale,
                 in_chans=3,
                 img_size=64,
@@ -172,6 +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/canvas-zoom-and-pan/javascript/zoom.js

@@ -4,16 +4,30 @@ onUiLoaded(async() => {
         inpaint: "#img2maskimg",
         inpaintSketch: "#inpaint_sketch",
         rangeGroup: "#img2img_column_size",
-        sketch: "#img2img_sketch",
+        sketch: "#img2img_sketch"
     };
     const tabNameToElementId = {
         "Inpaint sketch": elementIDs.inpaintSketch,
         "Inpaint": elementIDs.inpaint,
-        "Sketch": elementIDs.sketch,
+        "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");
 
@@ -42,43 +56,115 @@ onUiLoaded(async() => {
         }
     }
 
-    // Check is hotkey valid
+    // Detect whether the element has a horizontal scroll bar
-    function isSingleLetter(value) {
+    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)
+            (typeof value === "string" &&
+                value.length === 1 &&
+                /[a-z]/i.test(value)) ||
+            specialKeys.includes(value)
         );
     }
 
-    // Create hotkeyConfig from opts
+    // 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 = {};
+        const result = {}; // Resulting hotkey configuration
-        const usedKeys = new Set();
+        const usedKeys = new Set(); // Set of used hotkeys
 
+        // Iterate through defaultHotkeysConfig keys
         for (const key in defaultHotkeysConfig) {
-            if (typeof hotkeysConfigOpts[key] === "boolean") {
+            const userValue = hotkeysConfigOpts[key]; // User-provided hotkey value
-                result[key] = hotkeysConfigOpts[key];
+            const defaultValue = defaultHotkeysConfig[key]; // Default hotkey value
-                continue;
+
-            }
+            // Apply appropriate value for undefined, boolean, or object userValue
             if (
-                hotkeysConfigOpts[key] &&
+                userValue === undefined ||
-                isSingleLetter(hotkeysConfigOpts[key]) &&
+                typeof userValue === "boolean" ||
-                !usedKeys.has(hotkeysConfigOpts[key].toUpperCase())
+                typeof userValue === "object" ||
+                userValue === "disable"
             ) {
-                // If the property passed the test and has not yet been used, add 'Key' before it and save it
+                result[key] =
-                result[key] = "Key" + hotkeysConfigOpts[key].toUpperCase();
+                    userValue === undefined ? defaultValue : userValue;
-                usedKeys.add(hotkeysConfigOpts[key].toUpperCase());
+            } else if (isValidHotkey(userValue)) {
+                const normalizedUserValue = normalizeHotkey(userValue);
+
+                // Check for conflicting hotkeys
+                if (!usedKeys.has(normalizedUserValue)) {
+                    usedKeys.add(normalizedUserValue);
+                    result[key] = normalizedUserValue;
                 } else {
-                // If the property does not pass the test or has already been used, we keep the default value
                     console.error(
-                    `Hotkey: ${hotkeysConfigOpts[key]} for ${key} is repeated and conflicts with another hotkey or is not 1 letter. The default hotkey is used: ${defaultHotkeysConfig[key][3]}`
+                        `Hotkey: ${formatHotkeyForDisplay(
+                            userValue
+                        )} for ${key} is repeated and conflicts with another hotkey. The default hotkey is used: ${formatHotkeyForDisplay(
+                            defaultValue
+                        )}`
                     );
-                result[key] = defaultHotkeysConfig[key];
+                    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
@@ -100,7 +186,9 @@ onUiLoaded(async() => {
         imageARPreview.style.transform = "";
         if (parseFloat(mainTab.style.width) > 865) {
             const transformString = mainTab.style.transform;
-            const scaleMatch = transformString.match(/scale\(([-+]?[0-9]*\.?[0-9]+)\)/);
+            const scaleMatch = transformString.match(
+                /scale\(([-+]?[0-9]*\.?[0-9]+)\)/
+            );
             let zoom = 1; // default zoom
 
             if (scaleMatch && scaleMatch[1]) {
@@ -124,31 +212,54 @@ onUiLoaded(async() => {
 
     // 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_swap_controls: false
+        canvas_auto_expand: true,
+        canvas_blur_prompt: false,
     };
-    // swap the actions for ctr + wheel and shift + wheel
+
-    const hotkeysConfig = createHotkeyConfig(
+    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) => [
+    const elements = Object.fromEntries(
+        Object.keys(elementIDs).map(id => [
             id,
-        gradioApp().querySelector(elementIDs[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")) :
+    const rangeInputs = elements.rangeGroup ?
+        Array.from(elements.rangeGroup.querySelectorAll("input")) :
         [
             gradioApp().querySelector("#img2img_width input[type='range']"),
             gradioApp().querySelector("#img2img_height input[type='range']")
@@ -158,7 +269,7 @@ onUiLoaded(async() => {
         input?.addEventListener("input", () => restoreImgRedMask(elements));
     }
 
-    function applyZoomAndPan(elemId) {
+    function applyZoomAndPan(elemId, isExtension = true) {
         const targetElement = gradioApp().querySelector(elemId);
 
         if (!targetElement) {
@@ -180,38 +291,56 @@ onUiLoaded(async() => {
             const toolTipElemnt =
                 targetElement.querySelector(".image-container");
             const tooltip = document.createElement("div");
-            tooltip.className = "tooltip";
+            tooltip.className = "canvas-tooltip";
 
             // Creating an item of information
             const info = document.createElement("i");
-            info.className = "tooltip-info";
+            info.className = "canvas-tooltip-info";
             info.textContent = "";
 
             // Create a container for the contents of the tooltip
             const tooltipContent = document.createElement("div");
-            tooltipContent.className = "tooltip-content";
+            tooltipContent.className = "canvas-tooltip-content";
 
-            // Add info about hotkeys
+            // Define an array with hotkey information and their actions
-            const zoomKey = hotkeysConfig.canvas_swap_controls ? "Ctrl" : "Shift";
+            const hotkeysInfo = [
-            const adjustKey = hotkeysConfig.canvas_swap_controls ? "Shift" : "Ctrl";
-
-            const hotkeys = [
-                {key: `${zoomKey} + wheel`, action: "Zoom canvas"},
-                {key: `${adjustKey} + wheel`, action: "Adjust brush size"},
                 {
-                    key: hotkeysConfig.canvas_hotkey_reset.charAt(hotkeysConfig.canvas_hotkey_reset.length - 1),
+                    configKey: "canvas_hotkey_zoom",
-                    action: "Reset zoom"
+                    action: "Zoom canvas",
+                    keySuffix: " + wheel"
                 },
                 {
-                    key: hotkeysConfig.canvas_hotkey_fullscreen.charAt(hotkeysConfig.canvas_hotkey_fullscreen.length - 1),
+                    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"},
-                    key: hotkeysConfig.canvas_hotkey_move.charAt(hotkeysConfig.canvas_hotkey_move.length - 1),
+                {configKey: "canvas_hotkey_overlap", action: "Overlap"}
-                    action: "Move canvas"
-                }
             ];
+
+            // 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);
@@ -252,6 +381,12 @@ onUiLoaded(async() => {
                 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)`;
 
@@ -262,8 +397,27 @@ onUiLoaded(async() => {
             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
             ) {
@@ -272,9 +426,6 @@ onUiLoaded(async() => {
             }
 
             targetElement.style.width = "";
-            if (canvas) {
-                targetElement.style.height = canvas.style.height;
-            }
         }
 
         // Toggle the zIndex of the target element between two values, allowing it to overlap or be overlapped by other elements
@@ -330,7 +481,7 @@ onUiLoaded(async() => {
 
         // 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(0.5, Math.min(newZoomLevel, 15));
+            newZoomLevel = Math.max(0.1, Math.min(newZoomLevel, 15));
 
             elemData[elemId].panX +=
                 mouseX - (mouseX * newZoomLevel) / elemData[elemId].zoomLevel;
@@ -341,15 +492,16 @@ onUiLoaded(async() => {
             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 (
+            if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
-                (!hotkeysConfig.canvas_swap_controls && e.shiftKey) ||
-                (hotkeysConfig.canvas_swap_controls && e.ctrlKey)
-            ) {
                 e.preventDefault();
 
                 let zoomPosX, zoomPosY;
@@ -370,6 +522,8 @@ onUiLoaded(async() => {
                     zoomPosX - targetElement.getBoundingClientRect().left,
                     zoomPosY - targetElement.getBoundingClientRect().top
                 );
+
+                targetElement.isZoomed = true;
             }
         }
 
@@ -383,10 +537,19 @@ onUiLoaded(async() => {
             //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 parentElement = targetElement.parentElement;
+
             const screenWidth = parentElement.clientWidth;
             const screenHeight = parentElement.clientHeight;
 
@@ -439,8 +602,12 @@ onUiLoaded(async() => {
 
             if (!canvas) return;
 
-            if (canvas.offsetWidth > 862) {
+            if (canvas.offsetWidth > 862 || isExtension) {
-                targetElement.style.width = canvas.offsetWidth + "px";
+                targetElement.style.width = (canvas.offsetWidth + 2) + "px";
+            }
+
+            if (isExtension) {
+                targetElement.style.overflow = "visible";
             }
 
             if (fullScreenMode) {
@@ -503,6 +670,19 @@ onUiLoaded(async() => {
 
         // 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,
@@ -514,6 +694,13 @@ onUiLoaded(async() => {
                 event.preventDefault();
                 action(event);
             }
+
+            if (
+                isModifierKey(event, hotkeysConfig.canvas_hotkey_zoom) ||
+                isModifierKey(event, hotkeysConfig.canvas_hotkey_adjust)
+            ) {
+                event.preventDefault();
+            }
         }
 
         // Get Mouse position
@@ -522,8 +709,48 @@ onUiLoaded(async() => {
             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;
 
@@ -564,11 +791,7 @@ onUiLoaded(async() => {
             changeZoomLevel(operation, e);
 
             // Handle brush size adjustment with ctrl key pressed
-            if (
+            if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
-                (hotkeysConfig.canvas_swap_controls && e.shiftKey) ||
-                (!hotkeysConfig.canvas_swap_controls &&
-                    (e.ctrlKey || e.metaKey))
-            ) {
                 e.preventDefault();
 
                 // Increase or decrease brush size based on scroll direction
@@ -578,6 +801,20 @@ onUiLoaded(async() => {
 
         // 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();
@@ -618,6 +855,11 @@ onUiLoaded(async() => {
             if (isMoving && elemId === activeElement) {
                 updatePanPosition(e.movementX, e.movementY);
                 targetElement.style.pointerEvents = "none";
+
+                if (isExtension) {
+                    targetElement.style.overflow = "visible";
+                }
+
             } else {
                 targetElement.style.pointerEvents = "auto";
             }
@@ -628,13 +870,93 @@ onUiLoaded(async() => {
             isMoving = false;
         };
 
-        gradioApp().addEventListener("mousemove", handleMoveByKey);
+        // Checks for extension
+        function checkForOutBox() {
+            const parentElement = targetElement.closest('[id^="component-"]');
+            if (parentElement.offsetWidth < targetElement.offsetWidth && !targetElement.isExpanded) {
+                resetZoom();
+                targetElement.isExpanded = true;
             }
 
-    applyZoomAndPan(elementIDs.sketch);
+            if (parentElement.offsetWidth < targetElement.offsetWidth && elemData[elemId].zoomLevel == 1) {
-    applyZoomAndPan(elementIDs.inpaint);
+                resetZoom();
-    applyZoomAndPan(elementIDs.inpaintSketch);
+            }
+
+            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
-    window.applyZoomAndPan = applyZoomAndPan;
+    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

@@ -1,10 +1,15 @@
+import gradio as gr
 from modules import shared
 
 shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas Hotkeys"), {
-    "canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas"),
+    "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 ( Technical button, neededs for testing )"),
+    "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_swap_controls": shared.OptionInfo(False, "Swap hotkey combinations for Zoom and Adjust brush resize"),
+    "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

@@ -1,4 +1,4 @@
-.tooltip-info {
+.canvas-tooltip-info {
   position: absolute;
   top: 10px;
   left: 10px;
@@ -15,7 +15,7 @@
   z-index: 100;
 }
 
-.tooltip-info::after {
+.canvas-tooltip-info::after {
   content: '';
   display: block;
   width: 2px;
@@ -24,7 +24,7 @@
   margin-top: 2px; 
 }
 
-.tooltip-info::before {
+.canvas-tooltip-info::before {
   content: '';
   display: block;
   width: 2px;
@@ -32,7 +32,7 @@
   background-color: white;
 }
 
-.tooltip-content {
+.canvas-tooltip-content {
   display: none;
   background-color: #f9f9f9; 
   color: #333; 
@@ -50,7 +50,7 @@
   z-index: 100;
 }
 
-.tooltip:hover .tooltip-content {
+.canvas-tooltip:hover .canvas-tooltip-content {
   display: block;
   animation: fadeIn 0.5s; 
   opacity: 1;
@@ -61,3 +61,6 @@
   to {opacity: 1;}
 }
 
+.styler {
+  overflow:inherit !important;
+}

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

@@ -1,5 +1,7 @@
+import math
+
 import gradio as gr
-from modules import scripts, shared, ui_components, ui_settings
+from modules import scripts, shared, ui_components, ui_settings, generation_parameters_copypaste
 from modules.ui_components import FormColumn
 
 
@@ -19,18 +21,38 @@ class ExtraOptionsSection(scripts.Script):
     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 shared.opts.extra_options else gr.Group(), gr.Row():
+            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
-                for setting_name in shared.opts.extra_options:
+
+                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():
-            return [ui_settings.get_value_for_setting(key) for key in self.setting_names]
+            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)
 
@@ -43,6 +65,10 @@ class ExtraOptionsSection(scripts.Script):
 
 
 shared.options_templates.update(shared.options_section(('ui', "User interface"), {
-    "extra_options": shared.OptionInfo([], "Options in main UI", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img/img2img interfaces").needs_restart(),
+    "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_accordion": shared.OptionInfo(False, "Place options in main UI into an accordion")
+    "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/hypertile/hypertile.py

@@ -0,0 +1,345 @@
+"""
+Hypertile module for splitting attention layers in SD-1.5 U-Net and SD-1.5 VAE
+Warn: The patch works well only if the input image has a width and height that are multiples of 128
+Original author: @tfernd Github: https://github.com/tfernd/HyperTile
+"""
+
+from __future__ import annotations
+
+import functools
+from dataclasses import dataclass
+from typing import Callable
+
+from functools import wraps, cache
+
+import math
+import torch.nn as nn
+import random
+
+from einops import rearrange
+
+
+@dataclass
+class HypertileParams:
+    depth = 0
+    layer_name = ""
+    tile_size: int = 0
+    swap_size: int = 0
+    aspect_ratio: float = 1.0
+    forward = None
+    enabled = False
+
+
+
+# TODO add SD-XL layers
+DEPTH_LAYERS = {
+    0: [
+        # SD 1.5 U-Net (diffusers)
+        "down_blocks.0.attentions.0.transformer_blocks.0.attn1",
+        "down_blocks.0.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.3.attentions.0.transformer_blocks.0.attn1",
+        "up_blocks.3.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.3.attentions.2.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "input_blocks.1.1.transformer_blocks.0.attn1",
+        "input_blocks.2.1.transformer_blocks.0.attn1",
+        "output_blocks.9.1.transformer_blocks.0.attn1",
+        "output_blocks.10.1.transformer_blocks.0.attn1",
+        "output_blocks.11.1.transformer_blocks.0.attn1",
+        # SD 1.5 VAE
+        "decoder.mid_block.attentions.0",
+        "decoder.mid.attn_1",
+    ],
+    1: [
+        # SD 1.5 U-Net (diffusers)
+        "down_blocks.1.attentions.0.transformer_blocks.0.attn1",
+        "down_blocks.1.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.2.attentions.0.transformer_blocks.0.attn1",
+        "up_blocks.2.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.2.attentions.2.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "input_blocks.4.1.transformer_blocks.0.attn1",
+        "input_blocks.5.1.transformer_blocks.0.attn1",
+        "output_blocks.6.1.transformer_blocks.0.attn1",
+        "output_blocks.7.1.transformer_blocks.0.attn1",
+        "output_blocks.8.1.transformer_blocks.0.attn1",
+    ],
+    2: [
+        # SD 1.5 U-Net (diffusers)
+        "down_blocks.2.attentions.0.transformer_blocks.0.attn1",
+        "down_blocks.2.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.1.attentions.0.transformer_blocks.0.attn1",
+        "up_blocks.1.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.1.attentions.2.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "input_blocks.7.1.transformer_blocks.0.attn1",
+        "input_blocks.8.1.transformer_blocks.0.attn1",
+        "output_blocks.3.1.transformer_blocks.0.attn1",
+        "output_blocks.4.1.transformer_blocks.0.attn1",
+        "output_blocks.5.1.transformer_blocks.0.attn1",
+    ],
+    3: [
+        # SD 1.5 U-Net (diffusers)
+        "mid_block.attentions.0.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "middle_block.1.transformer_blocks.0.attn1",
+    ],
+}
+# XL layers, thanks for GitHub@gel-crabs for the help
+DEPTH_LAYERS_XL = {
+    0: [
+        # SD 1.5 U-Net (diffusers)
+        "down_blocks.0.attentions.0.transformer_blocks.0.attn1",
+        "down_blocks.0.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.3.attentions.0.transformer_blocks.0.attn1",
+        "up_blocks.3.attentions.1.transformer_blocks.0.attn1",
+        "up_blocks.3.attentions.2.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "input_blocks.4.1.transformer_blocks.0.attn1",
+        "input_blocks.5.1.transformer_blocks.0.attn1",
+        "output_blocks.3.1.transformer_blocks.0.attn1",
+        "output_blocks.4.1.transformer_blocks.0.attn1",
+        "output_blocks.5.1.transformer_blocks.0.attn1",
+        # SD 1.5 VAE
+        "decoder.mid_block.attentions.0",
+        "decoder.mid.attn_1",
+    ],
+    1: [
+        # SD 1.5 U-Net (diffusers)
+        #"down_blocks.1.attentions.0.transformer_blocks.0.attn1",
+        #"down_blocks.1.attentions.1.transformer_blocks.0.attn1",
+        #"up_blocks.2.attentions.0.transformer_blocks.0.attn1",
+        #"up_blocks.2.attentions.1.transformer_blocks.0.attn1",
+        #"up_blocks.2.attentions.2.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "input_blocks.4.1.transformer_blocks.1.attn1",
+        "input_blocks.5.1.transformer_blocks.1.attn1",
+        "output_blocks.3.1.transformer_blocks.1.attn1",
+        "output_blocks.4.1.transformer_blocks.1.attn1",
+        "output_blocks.5.1.transformer_blocks.1.attn1",
+        "input_blocks.7.1.transformer_blocks.0.attn1",
+        "input_blocks.8.1.transformer_blocks.0.attn1",
+        "output_blocks.0.1.transformer_blocks.0.attn1",
+        "output_blocks.1.1.transformer_blocks.0.attn1",
+        "output_blocks.2.1.transformer_blocks.0.attn1",
+        "input_blocks.7.1.transformer_blocks.1.attn1",
+        "input_blocks.8.1.transformer_blocks.1.attn1",
+        "output_blocks.0.1.transformer_blocks.1.attn1",
+        "output_blocks.1.1.transformer_blocks.1.attn1",
+        "output_blocks.2.1.transformer_blocks.1.attn1",
+        "input_blocks.7.1.transformer_blocks.2.attn1",
+        "input_blocks.8.1.transformer_blocks.2.attn1",
+        "output_blocks.0.1.transformer_blocks.2.attn1",
+        "output_blocks.1.1.transformer_blocks.2.attn1",
+        "output_blocks.2.1.transformer_blocks.2.attn1",
+        "input_blocks.7.1.transformer_blocks.3.attn1",
+        "input_blocks.8.1.transformer_blocks.3.attn1",
+        "output_blocks.0.1.transformer_blocks.3.attn1",
+        "output_blocks.1.1.transformer_blocks.3.attn1",
+        "output_blocks.2.1.transformer_blocks.3.attn1",
+        "input_blocks.7.1.transformer_blocks.4.attn1",
+        "input_blocks.8.1.transformer_blocks.4.attn1",
+        "output_blocks.0.1.transformer_blocks.4.attn1",
+        "output_blocks.1.1.transformer_blocks.4.attn1",
+        "output_blocks.2.1.transformer_blocks.4.attn1",
+        "input_blocks.7.1.transformer_blocks.5.attn1",
+        "input_blocks.8.1.transformer_blocks.5.attn1",
+        "output_blocks.0.1.transformer_blocks.5.attn1",
+        "output_blocks.1.1.transformer_blocks.5.attn1",
+        "output_blocks.2.1.transformer_blocks.5.attn1",
+        "input_blocks.7.1.transformer_blocks.6.attn1",
+        "input_blocks.8.1.transformer_blocks.6.attn1",
+        "output_blocks.0.1.transformer_blocks.6.attn1",
+        "output_blocks.1.1.transformer_blocks.6.attn1",
+        "output_blocks.2.1.transformer_blocks.6.attn1",
+        "input_blocks.7.1.transformer_blocks.7.attn1",
+        "input_blocks.8.1.transformer_blocks.7.attn1",
+        "output_blocks.0.1.transformer_blocks.7.attn1",
+        "output_blocks.1.1.transformer_blocks.7.attn1",
+        "output_blocks.2.1.transformer_blocks.7.attn1",
+        "input_blocks.7.1.transformer_blocks.8.attn1",
+        "input_blocks.8.1.transformer_blocks.8.attn1",
+        "output_blocks.0.1.transformer_blocks.8.attn1",
+        "output_blocks.1.1.transformer_blocks.8.attn1",
+        "output_blocks.2.1.transformer_blocks.8.attn1",
+        "input_blocks.7.1.transformer_blocks.9.attn1",
+        "input_blocks.8.1.transformer_blocks.9.attn1",
+        "output_blocks.0.1.transformer_blocks.9.attn1",
+        "output_blocks.1.1.transformer_blocks.9.attn1",
+        "output_blocks.2.1.transformer_blocks.9.attn1",
+    ],
+    2: [
+        # SD 1.5 U-Net (diffusers)
+        "mid_block.attentions.0.transformer_blocks.0.attn1",
+        # SD 1.5 U-Net (ldm)
+        "middle_block.1.transformer_blocks.0.attn1",
+        "middle_block.1.transformer_blocks.1.attn1",
+        "middle_block.1.transformer_blocks.2.attn1",
+        "middle_block.1.transformer_blocks.3.attn1",
+        "middle_block.1.transformer_blocks.4.attn1",
+        "middle_block.1.transformer_blocks.5.attn1",
+        "middle_block.1.transformer_blocks.6.attn1",
+        "middle_block.1.transformer_blocks.7.attn1",
+        "middle_block.1.transformer_blocks.8.attn1",
+        "middle_block.1.transformer_blocks.9.attn1",
+    ],
+    3 : [] # TODO - separate layers for SD-XL
+}
+
+
+RNG_INSTANCE = random.Random()
+
+
+def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
+    """
+    Returns a random divisor of value that
+        x * min_value <= value
+    if max_options is 1, the behavior is deterministic
+    """
+    min_value = min(min_value, value)
+
+    # All big divisors of value (inclusive)
+    divisors = [i for i in range(min_value, value + 1) if value % i == 0] # divisors in small -> big order
+
+    ns = [value // i for i in divisors[:max_options]]  # has at least 1 element # big -> small order
+
+    idx = RNG_INSTANCE.randint(0, len(ns) - 1)
+
+    return ns[idx]
+
+
+def set_hypertile_seed(seed: int) -> None:
+    RNG_INSTANCE.seed(seed)
+
+
+@functools.cache
+def largest_tile_size_available(width: int, height: int) -> int:
+    """
+    Calculates the largest tile size available for a given width and height
+    Tile size is always a power of 2
+    """
+    gcd = math.gcd(width, height)
+    largest_tile_size_available = 1
+    while gcd % (largest_tile_size_available * 2) == 0:
+        largest_tile_size_available *= 2
+    return largest_tile_size_available
+
+
+def iterative_closest_divisors(hw:int, aspect_ratio:float) -> tuple[int, int]:
+    """
+    Finds h and w such that h*w = hw and h/w = aspect_ratio
+    We check all possible divisors of hw and return the closest to the aspect ratio
+    """
+    divisors = [i for i in range(2, hw + 1) if hw % i == 0] # all divisors of hw
+    pairs = [(i, hw // i) for i in divisors] # all pairs of divisors of hw
+    ratios = [w/h for h, w in pairs] # all ratios of pairs of divisors of hw
+    closest_ratio = min(ratios, key=lambda x: abs(x - aspect_ratio)) # closest ratio to aspect_ratio
+    closest_pair = pairs[ratios.index(closest_ratio)] # closest pair of divisors to aspect_ratio
+    return closest_pair
+
+
+@cache
+def find_hw_candidates(hw:int, aspect_ratio:float) -> tuple[int, int]:
+    """
+    Finds h and w such that h*w = hw and h/w = aspect_ratio
+    """
+    h, w = round(math.sqrt(hw * aspect_ratio)), round(math.sqrt(hw / aspect_ratio))
+    # find h and w such that h*w = hw and h/w = aspect_ratio
+    if h * w != hw:
+        w_candidate = hw / h
+        # check if w is an integer
+        if not w_candidate.is_integer():
+            h_candidate = hw / w
+            # check if h is an integer
+            if not h_candidate.is_integer():
+                return iterative_closest_divisors(hw, aspect_ratio)
+            else:
+                h = int(h_candidate)
+        else:
+            w = int(w_candidate)
+    return h, w
+
+
+def self_attn_forward(params: HypertileParams, scale_depth=True) -> Callable:
+
+    @wraps(params.forward)
+    def wrapper(*args, **kwargs):
+        if not params.enabled:
+            return params.forward(*args, **kwargs)
+
+        latent_tile_size = max(128, params.tile_size) // 8
+        x = args[0]
+
+        # VAE
+        if x.ndim == 4:
+            b, c, h, w = x.shape
+
+            nh = random_divisor(h, latent_tile_size, params.swap_size)
+            nw = random_divisor(w, latent_tile_size, params.swap_size)
+
+            if nh * nw > 1:
+                x = rearrange(x, "b c (nh h) (nw w) -> (b nh nw) c h w", nh=nh, nw=nw)  # split into nh * nw tiles
+
+            out = params.forward(x, *args[1:], **kwargs)
+
+            if nh * nw > 1:
+                out = rearrange(out, "(b nh nw) c h w -> b c (nh h) (nw w)", nh=nh, nw=nw)
+
+        # U-Net
+        else:
+            hw: int = x.size(1)
+            h, w = find_hw_candidates(hw, params.aspect_ratio)
+            assert h * w == hw, f"Invalid aspect ratio {params.aspect_ratio} for input of shape {x.shape}, hw={hw}, h={h}, w={w}"
+
+            factor = 2 ** params.depth if scale_depth else 1
+            nh = random_divisor(h, latent_tile_size * factor, params.swap_size)
+            nw = random_divisor(w, latent_tile_size * factor, params.swap_size)
+
+            if nh * nw > 1:
+                x = rearrange(x, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw)
+
+            out = params.forward(x, *args[1:], **kwargs)
+
+            if nh * nw > 1:
+                out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw)
+                out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw)
+
+        return out
+
+    return wrapper
+
+
+def hypertile_hook_model(model: nn.Module, width, height, *, enable=False, tile_size_max=128, swap_size=1, max_depth=3, is_sdxl=False):
+    hypertile_layers = getattr(model, "__webui_hypertile_layers", None)
+    if hypertile_layers is None:
+        if not enable:
+            return
+
+        hypertile_layers = {}
+        layers = DEPTH_LAYERS_XL if is_sdxl else DEPTH_LAYERS
+
+        for depth in range(4):
+            for layer_name, module in model.named_modules():
+                if any(layer_name.endswith(try_name) for try_name in layers[depth]):
+                    params = HypertileParams()
+                    module.__webui_hypertile_params = params
+                    params.forward = module.forward
+                    params.depth = depth
+                    params.layer_name = layer_name
+                    module.forward = self_attn_forward(params)
+
+                    hypertile_layers[layer_name] = 1
+
+        model.__webui_hypertile_layers = hypertile_layers
+
+    aspect_ratio = width / height
+    tile_size = min(largest_tile_size_available(width, height), tile_size_max)
+
+    for layer_name, module in model.named_modules():
+        if layer_name in hypertile_layers:
+            params = module.__webui_hypertile_params
+
+            params.tile_size = tile_size
+            params.swap_size = swap_size
+            params.aspect_ratio = aspect_ratio
+            params.enabled = enable and params.depth <= max_depth

extensions-builtin/hypertile/scripts/hypertile_script.py

@@ -0,0 +1,73 @@
+import hypertile
+from modules import scripts, script_callbacks, shared
+
+
+class ScriptHypertile(scripts.Script):
+    name = "Hypertile"
+
+    def title(self):
+        return self.name
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def process(self, p, *args):
+        hypertile.set_hypertile_seed(p.all_seeds[0])
+
+        configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
+
+    def before_hr(self, p, *args):
+        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet)
+
+
+def configure_hypertile(width, height, enable_unet=True):
+    hypertile.hypertile_hook_model(
+        shared.sd_model.first_stage_model,
+        width,
+        height,
+        swap_size=shared.opts.hypertile_swap_size_vae,
+        max_depth=shared.opts.hypertile_max_depth_vae,
+        tile_size_max=shared.opts.hypertile_max_tile_vae,
+        enable=shared.opts.hypertile_enable_vae,
+    )
+
+    hypertile.hypertile_hook_model(
+        shared.sd_model.model,
+        width,
+        height,
+        swap_size=shared.opts.hypertile_swap_size_unet,
+        max_depth=shared.opts.hypertile_max_depth_unet,
+        tile_size_max=shared.opts.hypertile_max_tile_unet,
+        enable=enable_unet,
+        is_sdxl=shared.sd_model.is_sdxl
+    )
+
+
+def on_ui_settings():
+    import gradio as gr
+
+    options = {
+        "hypertile_explanation": shared.OptionHTML("""
+    <a href='https://github.com/tfernd/HyperTile'>Hypertile</a> optimizes the self-attention layer within U-Net and VAE models,
+    resulting in a reduction in computation time ranging from 1 to 4 times. The larger the generated image is, the greater the
+    benefit.
+    """),
+
+        "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net").info("noticeable change in details of the generated picture; if enabled, overrides the setting below"),
+        "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass"),
+        "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
+        "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+        "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-net swap size", gr.Slider, {"minimum": 0, "maximum": 6, "step": 1}),
+
+        "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE").info("minimal change in the generated picture"),
+        "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
+        "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+        "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 6, "step": 1}),
+    }
+
+    for name, opt in options.items():
+        opt.section = ('hypertile', "Hypertile")
+        shared.opts.add_option(name, opt)
+
+
+script_callbacks.on_ui_settings(on_ui_settings)

extensions-builtin/mobile/javascript/mobile.js

@@ -0,0 +1,34 @@
+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() {
+    if (gradioApp().querySelector('.toprow-compact-tools')) return; // not applicable for compact prompt layout
+
+    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();
+});

html/extra-networks-card.html

@@ -1,11 +1,11 @@
-<div class='card' style={style} onclick={card_clicked} {sort_keys}>
+<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>

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>

javascript/dragdrop.js

@@ -119,7 +119,7 @@ window.addEventListener('paste', e => {
     }
 
     const firstFreeImageField = visibleImageFields
-        .filter(el => el.querySelector('input[type=file]'))?.[0];
+        .filter(el => !el.querySelector('img'))?.[0];
 
     dropReplaceImage(
         firstFreeImageField ?

javascript/edit-attention.js

@@ -18,37 +18,43 @@ 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) {
+        let beforeClosingParen = before.lastIndexOf(CLOSE);
-            beforeParen = before.lastIndexOf(OPEN, beforeParen - 1);
+        if (beforeClosingParen != -1 && beforeClosingParen > beforeParen) return false;
-            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) {
+        let afterOpeningParen = after.indexOf(OPEN);
-            afterParen = after.indexOf(CLOSE, afterParen + 1);
+        if (afterOpeningParen != -1 && afterOpeningParen < afterParen) return false;
-            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);
+        if (/.*:-?[\d.]+/s.test(parenContent)) {
             const lastColon = parenContent.lastIndexOf(":");
             selectionStart = beforeParen + 1;
             selectionEnd = selectionStart + lastColon;
+        } else {
+            selectionStart = beforeParen + 1;
+            selectionEnd = selectionStart + parenContent.length;
+        }
+
         target.setSelectionRange(selectionStart, selectionEnd);
         return true;
     }
 
     function selectCurrentWord() {
         if (selectionStart !== selectionEnd) return false;
-        const delimiters = opts.keyedit_delimiters + " \r\n\t";
+        const whitespace_delimiters = {"Tab": "\t", "Carriage Return": "\r", "Line Feed": "\n"};
+        let delimiters = opts.keyedit_delimiters;
 
-        // seek backward until to find beggining
+        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--;
         }
@@ -63,7 +69,7 @@ function keyupEditAttention(event) {
     }
 
     // If the user hasn't selected anything, let's select their current parenthesis block or word
-    if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) {
+    if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')') && !selectCurrentParenthesisBlock('[', ']')) {
         selectCurrentWord();
     }
 
@@ -71,40 +77,62 @@ function keyupEditAttention(event) {
 
     var closeCharacter = ')';
     var delta = opts.keyedit_precision_attention;
+    var start = selectionStart > 0 ? text[selectionStart - 1] : "";
+    var end = text[selectionEnd];
 
-    if (selectionStart > 0 && text[selectionStart - 1] == '<') {
+    if (start == '<') {
         closeCharacter = '>';
         delta = opts.keyedit_precision_extra;
-    } else if (selectionStart == 0 || text[selectionStart - 1] != "(") {
+    } else if (start == '(' && end == ')' || start == '[' && end == ']') { // convert old-style (((emphasis)))
+        let numParen = 0;
 
+        while (text[selectionStart - numParen - 1] == start && text[selectionEnd + numParen] == end) {
+            numParen++;
+        }
+
+        if (start == "[") {
+            weight = (1 / 1.1) ** numParen;
+        } else {
+            weight = 1.1 ** numParen;
+        }
+
+        weight = Math.round(weight / opts.keyedit_precision_attention) * opts.keyedit_precision_attention;
+
+        text = text.slice(0, selectionStart - numParen) + "(" + text.slice(selectionStart, selectionEnd) + ":" + weight + ")" + text.slice(selectionEnd + numParen);
+        selectionStart -= numParen - 1;
+        selectionEnd -= numParen - 1;
+    } else if (start != '(') {
         // do not include spaces at the end
         while (selectionEnd > selectionStart && text[selectionEnd - 1] == ' ') {
-            selectionEnd -= 1;
+            selectionEnd--;
         }
+
         if (selectionStart == selectionEnd) {
             return;
         }
 
         text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
 
-        selectionStart += 1;
+        selectionStart++;
-        selectionEnd += 1;
+        selectionEnd++;
     }
 
-    var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
+    if (text[selectionEnd] != ':') return;
-    var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end));
+    var weightLength = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
+    var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + weightLength));
     if (isNaN(weight)) return;
 
     weight += isPlus ? delta : -delta;
     weight = parseFloat(weight.toPrecision(12));
-    if (String(weight).length == 1) weight += ".0";
+    if (Number.isInteger(weight)) weight += ".0";
 
     if (closeCharacter == ')' && weight == 1) {
-        text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + 5);
+        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 + 1 + end - 1);
+        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + weightLength);
     }
 
     target.focus();

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

@@ -33,7 +33,7 @@ function extensions_check() {
 
 
     var id = randomId();
-    requestProgress(id, gradioApp().getElementById('extensions_installed_top'), null, function() {
+    requestProgress(id, gradioApp().getElementById('extensions_installed_html'), null, function() {
 
     });
 
@@ -72,3 +72,21 @@ function config_state_confirm_restore(_, config_state_name, config_restore_type)
     }
     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

@@ -1,20 +1,39 @@
+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 search = gradioApp().querySelector('#' + tabname + '_extra_search textarea');
+    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');
+    var promptContainer = gradioApp().querySelector('.prompt-container-compact#' + tabname + '_prompt_container');
+    var negativePrompt = gradioApp().querySelector('#' + tabname + '_neg_prompt');
 
-    search.classList.add('search');
+    tabs.appendChild(searchDiv);
-    sort.classList.add('sort');
-    sortOrder.classList.add('sortorder');
-    sort.dataset.sortkey = 'sortDefault';
-    tabs.appendChild(search);
     tabs.appendChild(sort);
     tabs.appendChild(sortOrder);
     tabs.appendChild(refresh);
+    tabs.appendChild(showDirsDiv);
 
     var applyFilter = function() {
         var searchTerm = search.value.toLowerCase();
@@ -31,20 +50,23 @@ function setupExtraNetworksForTab(tabname) {
 
             elem.style.display = visible ? "" : "none";
         });
+
+        applySort();
     };
 
     var applySort = function() {
+        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
+
         var reverse = sortOrder.classList.contains("sortReverse");
-        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim();
+        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim() || "name";
-        sortKey = sortKey ? "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1) : "";
+        sortKey = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
-        var sortKeyStore = sortKey ? sortKey + (reverse ? "Reverse" : "") : "";
+        var sortKeyStore = sortKey + "-" + (reverse ? "Descending" : "Ascending") + "-" + cards.length;
-        if (!sortKey || sortKeyStore == sort.dataset.sortkey) {
+
+        if (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;
         });
@@ -70,23 +92,70 @@ function setupExtraNetworksForTab(tabname) {
     };
 
     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();
     });
+    applyFilter();
 
+    extraNetworksApplySort[tabname] = 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 extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt) {
+    if (!gradioApp().querySelector('.toprow-compact-tools')) return; // only applicable for compact prompt layout
+
+    var promptContainer = gradioApp().getElementById(tabname + '_prompt_container');
+    var prompt = gradioApp().getElementById(tabname + '_prompt_row');
+    var negPrompt = gradioApp().getElementById(tabname + '_neg_prompt_row');
+    var elem = id ? gradioApp().getElementById(id) : null;
+
+    if (showNegativePrompt && elem) {
+        elem.insertBefore(negPrompt, elem.firstChild);
+    } else {
+        promptContainer.insertBefore(negPrompt, promptContainer.firstChild);
+    }
+
+    if (showPrompt && elem) {
+        elem.insertBefore(prompt, elem.firstChild);
+    } else {
+        promptContainer.insertBefore(prompt, promptContainer.firstChild);
+    }
+
+    if (elem) {
+        elem.classList.toggle('extra-page-prompts-active', showNegativePrompt || showPrompt);
+    }
+}
+
+
+function extraNetworksUrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
+    extraNetworksMovePromptToTab(tabname, '', false, false);
+}
+
+function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt) { // called from python when user selects an extra networks tab
+    extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt);
+
 }
 
 function applyExtraNetworkFilter(tabname) {
     setTimeout(extraNetworksApplyFilter[tabname], 1);
 }
 
+function applyExtraNetworkSort(tabname) {
+    setTimeout(extraNetworksApplySort[tabname], 1);
+}
+
 var extraNetworksApplyFilter = {};
+var extraNetworksApplySort = {};
 var activePromptTextarea = {};
 
 function setupExtraNetworks() {
@@ -113,23 +182,36 @@ function setupExtraNetworks() {
 
 onUiLoaded(setupExtraNetworks);
 
-var re_extranet = /<([^:]+:[^:]+):[\d.]+>/;
+var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
-var re_extranet_g = /\s+<([^:]+:[^:]+):[\d.]+>/g;
+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];
-        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found) {
+        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) {
@@ -172,7 +254,7 @@ function saveCardPreview(event, tabname, filename) {
 }
 
 function extraNetworksSearchButton(tabs_id, event) {
-    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > div > textarea');
+    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > label > textarea');
     var button = event.target;
     var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
 
@@ -182,30 +264,28 @@ function extraNetworksSearchButton(tabs_id, event) {
 
 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.onclick = function() {
-            globalPopup.style.display = "none";
-        };
         globalPopup.classList.add('global-popup');
 
         var close = document.createElement('div');
         close.classList.add('global-popup-close');
-        close.onclick = function() {
+        close.addEventListener("click", closePopup);
-            globalPopup.style.display = "none";
-        };
         close.title = "Close";
         globalPopup.appendChild(close);
 
         globalPopupInner = document.createElement('div');
-        globalPopupInner.onclick = function(event) {
-            event.stopPropagation(); return false;
-        };
         globalPopupInner.classList.add('global-popup-inner');
         globalPopup.appendChild(globalPopupInner);
 
-        gradioApp().appendChild(globalPopup);
+        gradioApp().querySelector('.main').appendChild(globalPopup);
     }
 
     globalPopupInner.innerHTML = '';
@@ -214,6 +294,15 @@ function popup(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');
@@ -263,3 +352,43 @@ function extraNetworksRequestMetadata(event, extraPage, cardName) {
 
     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/hints.js

@@ -15,7 +15,7 @@ var titles = {
     "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",
@@ -84,8 +84,6 @@ var 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.",
 
     "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.",
@@ -110,9 +108,8 @@ var 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."
 };
 
@@ -193,3 +190,14 @@ onUiUpdate(function(mutationRecords) {
         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/imageviewer.js

@@ -33,8 +33,11 @@ function updateOnBackgroundChange() {
     const modalImage = gradioApp().getElementById("modalImage");
     if (modalImage && modalImage.offsetParent) {
         let currentButton = selected_gallery_button();
-
+        let preview = gradioApp().querySelectorAll('.livePreview > img');
-        if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
+        if (preview.length > 0) {
+            // show preview image if available
+            modalImage.src = preview[preview.length - 1].src;
+        } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
             modalImage.src = currentButton.children[0].src;
             if (modalImage.style.display === 'none') {
                 const modal = gradioApp().getElementById("lightboxModal");
@@ -136,6 +139,11 @@ function setupImageForLightbox(e) {
     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);

javascript/inputAccordion.js

@@ -0,0 +1,68 @@
+function inputAccordionChecked(id, checked) {
+    var accordion = gradioApp().getElementById(id);
+    accordion.visibleCheckbox.checked = checked;
+    accordion.onVisibleCheckboxChange();
+}
+
+function setupAccordion(accordion) {
+    var labelWrap = accordion.querySelector('.label-wrap');
+    var gradioCheckbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input");
+    var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
+    var span = labelWrap.querySelector('span');
+    var linked = true;
+
+    var isOpen = function() {
+        return labelWrap.classList.contains('open');
+    };
+
+    var observerAccordionOpen = new MutationObserver(function(mutations) {
+        mutations.forEach(function(mutationRecord) {
+            accordion.classList.toggle('input-accordion-open', isOpen());
+
+            if (linked) {
+                accordion.visibleCheckbox.checked = isOpen();
+                accordion.onVisibleCheckboxChange();
+            }
+        });
+    });
+    observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']});
+
+    if (extra) {
+        labelWrap.insertBefore(extra, labelWrap.lastElementChild);
+    }
+
+    accordion.onChecked = function(checked) {
+        if (isOpen() != checked) {
+            labelWrap.click();
+        }
+    };
+
+    var visibleCheckbox = document.createElement('INPUT');
+    visibleCheckbox.type = 'checkbox';
+    visibleCheckbox.checked = isOpen();
+    visibleCheckbox.id = accordion.id + "-visible-checkbox";
+    visibleCheckbox.className = gradioCheckbox.className + " input-accordion-checkbox";
+    span.insertBefore(visibleCheckbox, span.firstChild);
+
+    accordion.visibleCheckbox = visibleCheckbox;
+    accordion.onVisibleCheckboxChange = function() {
+        if (linked && isOpen() != visibleCheckbox.checked) {
+            labelWrap.click();
+        }
+
+        gradioCheckbox.checked = visibleCheckbox.checked;
+        updateInput(gradioCheckbox);
+    };
+
+    visibleCheckbox.addEventListener('click', function(event) {
+        linked = false;
+        event.stopPropagation();
+    });
+    visibleCheckbox.addEventListener('input', accordion.onVisibleCheckboxChange);
+}
+
+onUiLoaded(function() {
+    for (var accordion of gradioApp().querySelectorAll('.input-accordion')) {
+        setupAccordion(accordion);
+    }
+});

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

@@ -11,11 +11,11 @@ var ignore_ids_for_localization = {
     train_hypernetwork: 'OPTION',
     txt2img_styles: 'OPTION',
     img2img_styles: 'OPTION',
-    setting_random_artist_categories: 'SPAN',
+    setting_random_artist_categories: 'OPTION',
-    setting_face_restoration_model: 'SPAN',
+    setting_face_restoration_model: 'OPTION',
-    setting_realesrgan_enabled_models: 'SPAN',
+    setting_realesrgan_enabled_models: 'OPTION',
-    extras_upscaler_1: 'SPAN',
+    extras_upscaler_1: 'OPTION',
-    extras_upscaler_2: 'SPAN',
+    extras_upscaler_2: 'OPTION',
 };
 
 var re_num = /^[.\d]+$/;
@@ -107,12 +107,41 @@ function processNode(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() {
     if (!hasLocalization()) {
         // If we don't have any localization,
         // we will not have traversed the app to find
         // original_lines, so do that now.
-        processNode(gradioApp());
+        localizeWholePage();
     }
     var dumped = {};
     if (localization.rtl) {
@@ -154,7 +183,7 @@ 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

javascript/notification.js

@@ -15,7 +15,7 @@ onAfterUiUpdate(function() {
         }
     }
 
-    const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"][style*="display: block"] div[id$="_results"] .thumbnail-item > img');
+    const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"] div[id$="_results"] .thumbnail-item > img');
 
     if (galleryPreviews == null) return;
 
@@ -26,7 +26,11 @@ onAfterUiUpdate(function() {
     lastHeadImg = headImg;
 
     // play notification sound if available
-    gradioApp().querySelector('#audio_notification audio')?.play();
+    const notificationAudio = gradioApp().querySelector('#audio_notification audio');
+    if (notificationAudio) {
+        notificationAudio.volume = opts.notification_volume / 100.0 || 1.0;
+        notificationAudio.play();
+    }
 
     if (document.hasFocus()) return;
 

javascript/progressbar.js

@@ -69,7 +69,6 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     var dateStart = new Date();
     var wasEverActive = false;
     var parentProgressbar = progressbarContainer.parentNode;
-    var parentGallery = gallery ? gallery.parentNode : null;
 
     var divProgress = document.createElement('div');
     divProgress.className = 'progressDiv';
@@ -80,32 +79,26 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     divProgress.appendChild(divInner);
     parentProgressbar.insertBefore(divProgress, progressbarContainer);
 
-    if (parentGallery) {
+    var livePreview = null;
-        var livePreview = document.createElement('div');
-        livePreview.className = 'livePreview';
-        parentGallery.insertBefore(livePreview, gallery);
-    }
 
     var removeProgressBar = function() {
+        if (!divProgress) return;
+
         setTitle("");
         parentProgressbar.removeChild(divProgress);
-        if (parentGallery) parentGallery.removeChild(livePreview);
+        if (gallery && livePreview) gallery.removeChild(livePreview);
         atEnd();
+
+        divProgress = null;
     };
 
-    var fun = function(id_task, id_live_preview) {
+    var funProgress = function(id_task) {
-        request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) {
+        request("./internal/progress", {id_task: id_task, live_preview: false}, function(res) {
             if (res.completed) {
                 removeProgressBar();
                 return;
             }
 
-            var rect = progressbarContainer.getBoundingClientRect();
-
-            if (rect.width) {
-                divProgress.style.width = rect.width + "px";
-            }
-
             let progressText = "";
 
             divInner.style.width = ((res.progress || 0) * 100.0) + '%';
@@ -119,7 +112,6 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
                 progressText += " ETA: " + formatTime(res.eta);
             }
 
-
             setTitle(progressText);
 
             if (res.textinfo && res.textinfo.indexOf("\n") == -1) {
@@ -142,16 +134,33 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
                 return;
             }
 
-
+            if (onProgress) {
-            if (res.live_preview && gallery) {
+                onProgress(res);
-                rect = gallery.getBoundingClientRect();
-                if (rect.width) {
-                    livePreview.style.width = rect.width + "px";
-                    livePreview.style.height = rect.height + "px";
             }
 
+            setTimeout(() => {
+                funProgress(id_task, res.id_live_preview);
+            }, opts.live_preview_refresh_period || 500);
+        }, function() {
+            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);
@@ -160,18 +169,18 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
                 img.src = res.live_preview;
             }
 
-
-            if (onProgress) {
-                onProgress(res);
-            }
-
             setTimeout(() => {
-                fun(id_task, res.id_live_preview);
+                funLivePreview(id_task, res.id_live_preview);
             }, opts.live_preview_refresh_period || 500);
         }, function() {
             removeProgressBar();
         });
     };
 
-    fun(id_task, 0);
+    funProgress(id_task, 0);
+
+    if (gallery) {
+        funLivePreview(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 +1,71 @@
+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);
+});
+
+
+onOptionsChanged(function() {
+    if (gradioApp().querySelector('#settings .settings-category')) return;
+
+    var sectionMap = {};
+    gradioApp().querySelectorAll('#settings > div > button').forEach(function(x) {
+        sectionMap[x.textContent.trim()] = x;
+    });
+
+    opts._categories.forEach(function(x) {
+        var section = x[0];
+        var category = x[1];
+
+        var span = document.createElement('SPAN');
+        span.textContent = category;
+        span.className = 'settings-category';
+
+        var sectionElem = sectionMap[section];
+        if (!sectionElem) return;
+
+        sectionElem.parentElement.insertBefore(span, sectionElem);
+    });
+});
+

javascript/token-counters.js

@@ -1,10 +1,9 @@
-let promptTokenCountDebounceTime = 800;
+let promptTokenCountUpdateFunctions = {};
-let promptTokenCountTimeouts = {};
-var 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];
     }
@@ -14,6 +13,7 @@ function update_txt2img_tokens(...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];
     }
@@ -21,16 +21,7 @@ function update_img2img_tokens(...args) {
 }
 
 function update_token_counter(button_id) {
-    if (opts.disable_token_counters) {
+    promptTokenCountUpdateFunctions[button_id]?.();
-        return;
-    }
-    if (promptTokenCountTimeouts[button_id]) {
-        clearTimeout(promptTokenCountTimeouts[button_id]);
-    }
-    promptTokenCountTimeouts[button_id] = setTimeout(
-        () => gradioApp().getElementById(button_id)?.click(),
-        promptTokenCountDebounceTime,
-    );
 }
 
 
@@ -69,10 +60,11 @@ function setupTokenCounting(id, id_counter, id_button) {
     prompt.parentElement.insertBefore(counter, prompt);
     prompt.parentElement.style.position = "relative";
 
-    promptTokenCountUpdateFunctions[id] = function() {
+    var func = onEdit(id, textarea, 800, function() {
-        update_token_counter(id_button);
+        gradioApp().getElementById(id_button)?.click();
-    };
+    });
-    textarea.addEventListener("input", promptTokenCountUpdateFunctions[id]);
+    promptTokenCountUpdateFunctions[id] = func;
+    promptTokenCountUpdateFunctions[id_button] = func;
 }
 
 function setupTokenCounters() {

javascript/ui.js

@@ -19,28 +19,11 @@ function all_gallery_buttons() {
 }
 
 function selected_gallery_button() {
-    var allCurrentButtons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery].gradio-gallery .thumbnail-item.thumbnail-small.selected');
+    return all_gallery_buttons().find(elem => elem.classList.contains('selected')) ?? null;
-    var visibleCurrentButton = null;
-    allCurrentButtons.forEach(function(elem) {
-        if (elem.parentElement.offsetParent) {
-            visibleCurrentButton = elem;
-        }
-    });
-    return visibleCurrentButton;
 }
 
 function selected_gallery_index() {
-    var buttons = all_gallery_buttons();
+    return all_gallery_buttons().findIndex(elem => elem.classList.contains('selected'));
-    var button = selected_gallery_button();
-
-    var result = -1;
-    buttons.forEach(function(v, i) {
-        if (v == button) {
-            result = i;
-        }
-    });
-
-    return result;
 }
 
 function extract_image_from_gallery(gallery) {
@@ -152,11 +135,11 @@ function submit() {
     showSubmitButtons('txt2img', false);
 
     var id = randomId();
-    localStorage.setItem("txt2img_task_id", id);
+    localSet("txt2img_task_id", id);
 
     requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
         showSubmitButtons('txt2img', true);
-        localStorage.removeItem("txt2img_task_id");
+        localRemove("txt2img_task_id");
         showRestoreProgressButton('txt2img', false);
     });
 
@@ -171,11 +154,11 @@ function submit_img2img() {
     showSubmitButtons('img2img', false);
 
     var id = randomId();
-    localStorage.setItem("img2img_task_id", id);
+    localSet("img2img_task_id", id);
 
     requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
         showSubmitButtons('img2img', true);
-        localStorage.removeItem("img2img_task_id");
+        localRemove("img2img_task_id");
         showRestoreProgressButton('img2img', false);
     });
 
@@ -189,9 +172,7 @@ function submit_img2img() {
 
 function restoreProgressTxt2img() {
     showRestoreProgressButton("txt2img", false);
-    var id = localStorage.getItem("txt2img_task_id");
+    var id = localGet("txt2img_task_id");
-
-    id = localStorage.getItem("txt2img_task_id");
 
     if (id) {
         requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
@@ -205,7 +186,7 @@ function restoreProgressTxt2img() {
 function restoreProgressImg2img() {
     showRestoreProgressButton("img2img", false);
 
-    var id = localStorage.getItem("img2img_task_id");
+    var id = localGet("img2img_task_id");
 
     if (id) {
         requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
@@ -218,8 +199,8 @@ function restoreProgressImg2img() {
 
 
 onUiLoaded(function() {
-    showRestoreProgressButton('txt2img', localStorage.getItem("txt2img_task_id"));
+    showRestoreProgressButton('txt2img', localGet("txt2img_task_id"));
-    showRestoreProgressButton('img2img', localStorage.getItem("img2img_task_id"));
+    showRestoreProgressButton('img2img', localGet("img2img_task_id"));
 });
 
 
@@ -282,21 +263,6 @@ onAfterUiUpdate(function() {
     json_elem.parentElement.style.display = "none";
 
     setupTokenCounters();
-
-    var show_all_pages = gradioApp().getElementById('settings_show_all_pages');
-    var 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) {
-                if (elem.id == "settings_tab_licenses") {
-                    return;
-                }
-
-                elem.style.display = "block";
-            });
-        };
-    }
 });
 
 onOptionsChanged(function() {
@@ -385,3 +351,20 @@ function switchWidthHeight(tabname) {
     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;
+}

launch.py

@@ -1,6 +1,5 @@
 from modules import launch_utils
 
-
 args = launch_utils.args
 python = launch_utils.python
 git = launch_utils.git
@@ -18,6 +17,7 @@ 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
@@ -25,6 +25,16 @@ start = launch_utils.start
 
 
 def main():
+    if args.dump_sysinfo:
+        filename = launch_utils.dump_sysinfo()
+
+        print(f"Sysinfo saved as {filename}. Exiting...")
+
+        exit(0)
+
+    launch_utils.startup_timer.record("initial startup")
+
+    with launch_utils.startup_timer.subcategory("prepare environment"):
         if not args.skip_prepare_environment:
             prepare_environment()
 

modules/api/api.py

@@ -1,8 +1,11 @@
 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
@@ -14,7 +17,7 @@ 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, errors
+from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, generation_parameters_copypaste, sd_models
 from modules.api import models
 from modules.shared import opts
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
@@ -22,21 +25,13 @@ from modules.textual_inversion.textual_inversion import create_embedding, train_
 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, unload_model_weights, reload_model_weights
-from modules.sd_vae import vae_dict
 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 Dict, List, Any
+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 Exception as e:
-        raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in shared.sd_upscalers])}") from e
 
 
 def script_name_to_index(name, scripts):
@@ -61,7 +56,41 @@ def setUpscalers(req: dict):
     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:
@@ -73,7 +102,8 @@ def decode_base64_to_image(encoding):
 
 def encode_pil_to_base64(image):
     with io.BytesIO() as output_bytes:
-
+        if isinstance(image, str):
+            return image
         if opts.samples_format.lower() == 'png':
             use_metadata = False
             metadata = PngImagePlugin.PngInfo()
@@ -84,6 +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") }
@@ -102,14 +134,16 @@ def encode_pil_to_base64(image):
 
 
 def api_middleware(app: FastAPI):
-    rich_available = True
+    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:
-        rich_available = False
+        pass
 
     @app.middleware("http")
     async def log_and_time(req: Request, call_next):
@@ -187,17 +221,18 @@ class Api:
         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=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/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/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/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-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/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/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/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/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/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/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)
@@ -207,7 +242,13 @@ class Api:
         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/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 = []
@@ -324,19 +365,23 @@ class Api:
         args.pop('save_images', None)
 
         with self.queue_lock:
-            p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)
+            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
 
-            shared.state.begin()
+                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)) if send_images else []
 
@@ -380,20 +425,24 @@ class Api:
         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]
+                p.is_api = True
                 p.scripts = script_runner
                 p.outpath_grids = opts.outdir_img2img_grids
                 p.outpath_samples = opts.outdir_img2img_samples
 
-            shared.state.begin()
+                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 []
 
@@ -425,9 +474,6 @@ class Api:
         return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
 
     def pnginfoapi(self, req: models.PNGInfoRequest):
-        if(not req.image.strip()):
-            return models.PNGInfoResponse(info="")
-
         image = decode_base64_to_image(req.image.strip())
         if image is None:
             return models.PNGInfoResponse(info="")
@@ -436,9 +482,10 @@ class Api:
         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 models.PNGInfoResponse(info=geninfo, items=items)
+        return models.PNGInfoResponse(info=geninfo, items=items, parameters=params)
 
     def progressapi(self, req: models.ProgressRequest = Depends()):
         # copy from check_progress_call of ui.py
@@ -493,12 +540,12 @@ class Api:
         return {}
 
     def unloadapi(self):
-        unload_model_weights()
+        sd_models.unload_model_weights()
 
         return {}
 
     def reloadapi(self):
-        reload_model_weights()
+        sd_models.send_model_to_device(shared.sd_model)
 
         return {}
 
@@ -516,9 +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 sd_models.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
@@ -550,10 +601,12 @@ class Api:
         ]
 
     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_near_filename(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):
-        return [{"model_name": x, "filename": vae_dict[x]} for x in vae_dict.keys()]
+        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]
@@ -593,48 +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 models.CreateResponse(info=f"create embedding filename: {filename}")
         except AssertionError as e:
-            shared.state.end()
             return models.TrainResponse(info=f"create embedding error: {e}")
+        finally:
+            shared.state.end()
+
 
     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 models.CreateResponse(info=f"create hypernetwork filename: {filename}")
         except AssertionError as e:
-            shared.state.end()
             return models.TrainResponse(info=f"create hypernetwork error: {e}")
+        finally:
+            shared.state.end()
 
     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 models.PreprocessResponse(info='preprocess complete')
         except KeyError as e:
-            shared.state.end()
             return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}")
-        except AssertionError as e:
+        except Exception as e:
-            shared.state.end()
             return models.PreprocessResponse(info=f"preprocess error: {e}")
-        except FileNotFoundError as e:
+        finally:
             shared.state.end()
-            return models.PreprocessResponse(info=f'preprocess 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 = ''
@@ -647,15 +703,15 @@ class Api:
             finally:
                 if not apply_optimizations:
                     sd_hijack.apply_optimizations()
-                shared.state.end()
             return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
-        except AssertionError as msg:
+        except Exception as msg:
-            shared.state.end()
             return models.TrainResponse(info=f"train embedding error: {msg}")
+        finally:
+            shared.state.end()
 
     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
@@ -673,9 +729,10 @@ class Api:
                     sd_hijack.apply_optimizations()
                 shared.state.end()
             return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
-        except AssertionError:
+        except Exception as exc:
+            return models.TrainResponse(info=f"train embedding error: {exc}")
+        finally:
             shared.state.end()
-            return models.TrainResponse(info=f"train embedding error: {error}")
 
     def get_memory(self):
         try:
@@ -712,6 +769,38 @@ class Api:
             cuda = {'error': f'{err}'}
         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, timeout_keep_alive=0)
+        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 import Any, Optional, Literal
-from typing_extensions import 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",
@@ -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
         ]
@@ -93,8 +93,8 @@ class PydanticModelGenerator:
             d.field: (d.field_type, Field(default=d.field_value, alias=d.field_alias, exclude=d.field_exclude)) for d in self._model_def
         }
         DynamicModel = create_model(self._model_name, **fields)
-        DynamicModel.__config__.allow_population_by_field_name = True
+        DynamicModel.model_config['populate_by_name'] = True
-        DynamicModel.__config__.allow_mutation = True
+        DynamicModel.model_config['frozen'] = True
         return DynamicModel
 
 StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
@@ -128,12 +128,12 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
 ).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
 
@@ -166,17 +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")
@@ -207,11 +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):
+    if metadata is not None:
-        fields.update({key: (Optional[optType], Field(
+        fields.update({key: (Optional[optType], Field(default=metadata.default, description=metadata.label))})
-            default=metadata.default ,description=metadata.label))})
     else:
         fields.update({key: (Optional[optType], Field())})
 
@@ -231,8 +231,8 @@ FlagsModel = create_model("Flags", **flags)
 
 class SamplerItem(BaseModel):
     name: str = Field(title="Name")
-    aliases: List[str] = Field(title="Aliases")
+    aliases: list[str] = Field(title="Aliases")
-    options: Dict[str, str] = Field(title="Options")
+    options: dict[str, str] = Field(title="Options")
 
 class UpscalerItem(BaseModel):
     name: str = Field(title="Name")
@@ -274,10 +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")
@@ -287,8 +283,8 @@ 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")
+    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)")
+    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")
@@ -306,11 +302,20 @@ class ScriptArg(BaseModel):
     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")
+    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")
+    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, ensure_ascii=False)
+
+            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

@@ -1,10 +1,10 @@
+from functools import wraps
 import html
-import threading
 import time
 
-from modules import shared, progress, errors
+from modules import shared, progress, errors, devices, fifo_lock
 
-queue_lock = threading.Lock()
+queue_lock = fifo_lock.FIFOLock()
 
 
 def wrap_queued_call(func):
@@ -18,6 +18,7 @@ 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
@@ -28,7 +29,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
             id_task = None
 
         with queue_lock:
-            shared.state.begin()
+            shared.state.begin(job=id_task)
             progress.start_task(id_task)
 
             try:
@@ -45,6 +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:
@@ -72,6 +74,8 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
             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
         shared.state.job_count = 0
@@ -82,9 +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()}
@@ -92,14 +96,22 @@ 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)
 

modules/cmd_args.py

@@ -13,8 +13,12 @@ parser.add_argument("--reinstall-xformers", action='store_true', help="launch.py
 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",)
@@ -32,9 +36,10 @@ parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_
 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="disables cond/uncond batching that is enabled to save memory with --medvram or --lowvram")
+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.")
@@ -65,6 +70,7 @@ parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="pre
 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)
@@ -77,14 +83,14 @@ parser.add_argument("--gradio-auth", type=str, help='set gradio authentication l
 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")
+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="print prompts to console when generating with txt2img and img2img", 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)")
@@ -101,9 +107,14 @@ parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, req
 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("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the default 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='add /_stop route to stop server')
+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_model.py

@@ -15,14 +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
+    os.makedirs(model_path, exist_ok=True)
-    if not os.path.exists(model_path):
-        os.makedirs(model_path)
 
     path = modules.paths.paths.get("CodeFormer", None)
     if path is None:
@@ -102,7 +99,7 @@ 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()
+                        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))
@@ -125,9 +122,6 @@ def setup_model(dirname):
 
                 return restored_img
 
-        global have_codeformer
-        have_codeformer = True
-
         global codeformer
         codeformer = FaceRestorerCodeFormer(dirname)
         shared.face_restorers.append(codeformer)

modules/config_states.py

@@ -4,18 +4,15 @@ Supports saving and restoring webui and extensions from a known working set of c
 
 import os
 import json
-import time
 import tqdm
 
 from datetime import datetime
-from collections import OrderedDict
 import git
 
 from modules import shared, extensions, errors
 from modules.paths_internal import script_path, config_states_dir
 
-
+all_config_states = {}
-all_config_states = OrderedDict()
 
 
 def list_config_states():
@@ -28,15 +25,19 @@ def list_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 = time.asctime(time.gmtime(cs["created_at"]))
+        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

modules/devices.py

@@ -3,7 +3,7 @@ import contextlib
 from functools import lru_cache
 
 import torch
-from modules import errors
+from modules import errors, shared
 
 if sys.platform == "darwin":
     from modules import mac_specific
@@ -15,17 +15,8 @@ def has_mps() -> bool:
     else:
         return mac_specific.has_mps
 
-def extract_device_id(args, name):
-    for x in range(len(args)):
-        if name in args[x]:
-            return args[x + 1]
-
-    return None
-
 
 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}"
 
@@ -47,8 +38,6 @@ def get_optimal_device():
 
 
 def get_device_for(task):
-    from modules import shared
-
     if task in shared.cmd_opts.use_cpu:
         return cpu
 
@@ -56,32 +45,40 @@ 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")
+cpu: torch.device = torch.device("cpu")
-device = device_interrogate = device_gfpgan = device_esrgan = device_codeformer = None
+device: torch.device = None
-dtype = torch.float16
+device_interrogate: torch.device = None
-dtype_vae = torch.float16
+device_gfpgan: torch.device = None
-dtype_unet = torch.float16
+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
 
 
@@ -93,26 +90,10 @@ def cond_cast_float(input):
     return input.float() if unet_needs_upcast else input
 
 
-def randn(seed, shape):
+nv_rng = None
-    from modules.shared import opts
-
-    torch.manual_seed(seed)
-    if opts.randn_source == "CPU" or device.type == 'mps':
-        return torch.randn(shape, device=cpu).to(device)
-    return torch.randn(shape, device=device)
-
-
-def randn_without_seed(shape):
-    from modules.shared import opts
-
-    if opts.randn_source == "CPU" or device.type == 'mps':
-        return torch.randn(shape, device=cpu).to(device)
-    return torch.randn(shape, device=device)
 
 
 def autocast(disable=False):
-    from modules import shared
-
     if disable:
         return contextlib.nullcontext()
 
@@ -131,8 +112,6 @@ class NansException(Exception):
 
 
 def test_for_nans(x, where):
-    from modules import shared
-
     if shared.cmd_opts.disable_nan_check:
         return
 
@@ -172,3 +151,4 @@ def first_time_calculation():
     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

@@ -6,6 +6,21 @@ import traceback
 exception_records = []
 
 
+def format_traceback(tb):
+    return [[f"{x.filename}, line {x.lineno}, {x.name}", x.line] for x in traceback.extract_tb(tb)]
+
+
+def format_exception(e, tb):
+    return {"exception": str(e), "traceback": format_traceback(tb)}
+
+
+def get_exceptions():
+    try:
+        return list(reversed(exception_records))
+    except Exception as e:
+        return str(e)
+
+
 def record_exception():
     _, e, tb = sys.exc_info()
     if e is None:
@@ -14,7 +29,7 @@ def record_exception():
     if exception_records and exception_records[-1] == e:
         return
 
-    exception_records.append((e, tb))
+    exception_records.append(format_exception(e, tb))
 
     if len(exception_records) > 5:
         exception_records.pop(0)
@@ -83,3 +98,53 @@ 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

@@ -1,15 +1,13 @@
-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 modelloader, images, devices
-from modules.upscaler import Upscaler, UpscalerData
 from modules.shared import opts
-
+from modules.upscaler import Upscaler, UpscalerData
 
 
 def mod2normal(state_dict):
@@ -134,7 +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)
@@ -143,26 +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:
+        if path.startswith("http"):
-            filename = load_file_from_url(
+            # 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",
-                progress=True,
             )
         else:
             filename = path
-        if not os.path.exists(filename) or filename is None:
-            print(f"Unable to load {self.model_path} from {filename}")
-            return None
 
         state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
 

modules/extensions.py

@@ -1,29 +1,76 @@
+from __future__ import annotations
+
+import configparser
 import os
 import threading
+import re
 
-from modules import shared, errors
+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 = []
 
-if not os.path.exists(extensions_dir):
+os.makedirs(extensions_dir, exist_ok=True)
-    os.makedirs(extensions_dir)
 
 
 def active():
-    if shared.opts.disable_all_extensions == "all":
+    if shared.cmd_opts.disable_all_extensions or shared.opts.disable_all_extensions == "all":
         return []
-    elif shared.opts.disable_all_extensions == "extra":
+    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 ExtensionMetadata:
+    filename = "metadata.ini"
+    config: configparser.ConfigParser
+    canonical_name: str
+    requires: list
+
+    def __init__(self, path, canonical_name):
+        self.config = configparser.ConfigParser()
+
+        filepath = os.path.join(path, self.filename)
+        if os.path.isfile(filepath):
+            try:
+                self.config.read(filepath)
+            except Exception:
+                errors.report(f"Error reading {self.filename} for extension {canonical_name}.", exc_info=True)
+
+        self.canonical_name = self.config.get("Extension", "Name", fallback=canonical_name)
+        self.canonical_name = canonical_name.lower().strip()
+
+        self.requires = self.get_script_requirements("Requires", "Extension")
+
+    def get_script_requirements(self, field, section, extra_section=None):
+        """reads a list of requirements from the config; field is the name of the field in the ini file,
+        like Requires or Before, and section is the name of the [section] in the ini file; additionally,
+        reads more requirements from [extra_section] if specified."""
+
+        x = self.config.get(section, field, fallback='')
+
+        if extra_section:
+            x = x + ', ' + self.config.get(extra_section, field, fallback='')
+
+        return self.parse_list(x.lower())
+
+    def parse_list(self, text):
+        """converts a line from config ("ext1 ext2, ext3  ") into a python list (["ext1", "ext2", "ext3"])"""
+
+        if not text:
+            return []
+
+        # both "," and " " are accepted as separator
+        return [x for x in re.split(r"[,\s]+", text.strip()) if x]
+
+
 class Extension:
     lock = threading.Lock()
+    cached_fields = ['remote', 'commit_date', 'branch', 'commit_hash', 'version']
+    metadata: ExtensionMetadata
 
-    def __init__(self, name, path, enabled=True, is_builtin=False):
+    def __init__(self, name, path, enabled=True, is_builtin=False, metadata=None):
         self.name = name
         self.path = path
         self.enabled = enabled
@@ -36,17 +83,36 @@ class Extension:
         self.branch = None
         self.remote = None
         self.have_info_from_repo = False
+        self.metadata = metadata if metadata else ExtensionMetadata(self.path, name.lower())
+        self.canonical_name = metadata.canonical_name
+
+    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:
@@ -59,7 +125,6 @@ class Extension:
             self.remote = None
         else:
             try:
-                self.status = 'unknown'
                 self.remote = next(repo.remote().urls, None)
                 commit = repo.head.commit
                 self.commit_date = commit.committed_date
@@ -75,8 +140,6 @@ class Extension:
         self.have_info_from_repo = True
 
     def list_files(self, subdir, extension):
-        from modules import scripts
-
         dirpath = os.path.join(self.path, subdir)
         if not os.path.isdir(dirpath):
             return []
@@ -123,26 +186,52 @@ class Extension:
 def list_extensions():
     extensions.clear()
 
-    if not os.path.isdir(extensions_dir):
+    if shared.cmd_opts.disable_all_extensions:
-        return
+        print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
-
+    elif shared.opts.disable_all_extensions == "all":
-    if 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 = []
+    loaded_extensions = {}
-    for dirname in [extensions_dir, extensions_builtin_dir]:
+
+    # scan through extensions directory and load metadata
+    for dirname in [extensions_builtin_dir, extensions_dir]:
         if not os.path.isdir(dirname):
-            return
+            continue
 
         for extension_dirname in sorted(os.listdir(dirname)):
             path = os.path.join(dirname, extension_dirname)
             if not os.path.isdir(path):
                 continue
 
-            extension_paths.append((extension_dirname, path, dirname == extensions_builtin_dir))
+            canonical_name = extension_dirname
+            metadata = ExtensionMetadata(path, canonical_name)
 
-    for dirname, path, is_builtin in extension_paths:
+            # check for duplicated canonical names
-        extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)
+            already_loaded_extension = loaded_extensions.get(metadata.canonical_name)
+            if already_loaded_extension is not None:
+                errors.report(f'Duplicate canonical name "{canonical_name}" found in extensions "{extension_dirname}" and "{already_loaded_extension.name}". Former will be discarded.', exc_info=False)
+                continue
+
+            is_builtin = dirname == extensions_builtin_dir
+            extension = Extension(name=extension_dirname, path=path, enabled=extension_dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin, metadata=metadata)
             extensions.append(extension)
+            loaded_extensions[canonical_name] = extension
+
+    # check for requirements
+    for extension in extensions:
+        for req in extension.metadata.requires:
+            required_extension = loaded_extensions.get(req)
+            if required_extension is None:
+                errors.report(f'Extension "{extension.name}" requires "{req}" which is not installed.', exc_info=False)
+                continue
+
+            if not extension.enabled:
+                errors.report(f'Extension "{extension.name}" requires "{required_extension.name}" which is disabled.', exc_info=False)
+                continue
+
+
+extensions: list[Extension] = []

modules/extra_networks.py

@@ -1,19 +1,28 @@
+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())
@@ -78,24 +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():
+    activated = []
-        extra_network = extra_network_registry.get(extra_network_name, None)
+
-        if extra_network is None:
+    for extra_network, extra_network_args in lookup_extra_networks(extra_network_data).items():
-            print(f"Skipping unknown extra network: {extra_network_name}")
-            continue
 
         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 extra_network in activated:
-        if args is not None:
             continue
 
         try:
@@ -103,24 +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 in extra_network_data:
+    data = lookup_extra_networks(extra_network_data)
-        extra_network = extra_network_registry.get(extra_network_name, None)
-        if extra_network is None:
-            continue
 
+    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 extra_network in data:
-        if args is not None:
             continue
 
         try:
@@ -162,3 +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/extras.py

@@ -7,7 +7,7 @@ import json
 import torch
 import tqdm
 
-from modules import shared, images, sd_models, sd_vae, sd_models_config
+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
@@ -72,9 +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, save_metadata):
+def read_metadata(primary_model_name, secondary_model_name, tertiary_model_name):
-    shared.state.begin()
+    metadata = {}
-    shared.state.job = 'model-merge'
+
+    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
@@ -242,11 +254,25 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
     shared.state.textinfo = "Saving"
     print(f"Saving to {output_modelname}...")
 
-    metadata = None
+    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:
-        metadata = {"format": "pt"}
+        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,
@@ -262,7 +288,6 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
             "is_inpainting": result_is_inpainting_model,
             "is_instruct_pix2pix": result_is_instruct_pix2pix_model
         }
-        metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
 
         sd_merge_models = {}
 
@@ -282,11 +307,12 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
         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=metadata)
+        safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata if len(metadata)>0 else None)
     else:
         torch.save(theta_0, output_modelname)
 

modules/fifo_lock.py

@@ -0,0 +1,37 @@
+import threading
+import collections
+
+
+# reference: https://gist.github.com/vitaliyp/6d54dd76ca2c3cdfc1149d33007dc34a
+class FIFOLock(object):
+    def __init__(self):
+        self._lock = threading.Lock()
+        self._inner_lock = threading.Lock()
+        self._pending_threads = collections.deque()
+
+    def acquire(self, blocking=True):
+        with self._inner_lock:
+            lock_acquired = self._lock.acquire(False)
+            if lock_acquired:
+                return True
+            elif not blocking:
+                return False
+
+            release_event = threading.Event()
+            self._pending_threads.append(release_event)
+
+        release_event.wait()
+        return self._lock.acquire()
+
+    def release(self):
+        with self._inner_lock:
+            if self._pending_threads:
+                release_event = self._pending_threads.popleft()
+                release_event.set()
+
+            self._lock.release()
+
+    __enter__ = acquire
+
+    def __exit__(self, t, v, tb):
+        self.release()

modules/generation_parameters_copypaste.py

@@ -6,10 +6,10 @@ import re
 
 import gradio as gr
 from modules.paths import data_path
-from modules import shared, ui_tempdir, script_callbacks
+from modules import shared, ui_tempdir, script_callbacks, processing
 from PIL import Image
 
-re_param_code = r'\s*([\w ]+):\s*("(?:\\"[^,]|\\"|\\|[^\"])+"|[^,]*)(?:,|$)'
+re_param_code = r'\s*(\w[\w \-/]+):\s*("(?:\\.|[^\\"])+"|[^,]*)(?:,|$)'
 re_param = re.compile(re_param_code)
 re_imagesize = re.compile(r"^(\d+)x(\d+)$")
 re_hypernet_hash = re.compile("\(([0-9a-f]+)\)$")
@@ -32,6 +32,7 @@ class ParamBinding:
 
 def reset():
     paste_fields.clear()
+    registered_param_bindings.clear()
 
 
 def quote(text):
@@ -174,31 +175,6 @@ def send_image_and_dimensions(x):
     return img, w, h
 
 
-
-def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
-    """Determines the config parameter name to use for the hypernet based on the parameters in the infotext.
-
-    Example: an infotext provides "Hypernet: ke-ta" and "Hypernet hash: 1234abcd". For the "Hypernet" config
-    parameter this means there should be an entry that looks like "ke-ta-10000(1234abcd)" to set it to.
-
-    If the infotext has no hash, then a hypernet with the same name will be selected instead.
-    """
-    hypernet_name = hypernet_name.lower()
-    if hypernet_hash is not None:
-        # Try to match the hash in the name
-        for hypernet_key in shared.hypernetworks.keys():
-            result = re_hypernet_hash.search(hypernet_key)
-            if result is not None and result[1] == hypernet_hash:
-                return hypernet_key
-    else:
-        # Fall back to a hypernet with the same name
-        for hypernet_key in shared.hypernetworks.keys():
-            if hypernet_key.lower().startswith(hypernet_name):
-                return hypernet_key
-
-    return None
-
-
 def restore_old_hires_fix_params(res):
     """for infotexts that specify old First pass size parameter, convert it into
     width, height, and hr scale"""
@@ -223,7 +199,6 @@ def restore_old_hires_fix_params(res):
     height = int(res.get("Size-2", 512))
 
     if firstpass_width == 0 or firstpass_height == 0:
-        from modules import processing
         firstpass_width, firstpass_height = processing.old_hires_fix_first_pass_dimensions(width, height)
 
     res['Size-1'] = firstpass_width
@@ -305,6 +280,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "Hires sampler" not in res:
         res["Hires sampler"] = "Use same sampler"
 
+    if "Hires checkpoint" not in res:
+        res["Hires checkpoint"] = "Use same checkpoint"
+
     if "Hires prompt" not in res:
         res["Hires prompt"] = ""
 
@@ -329,35 +307,28 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "Schedule rho" not in res:
         res["Schedule rho"] = 0
 
+    if "VAE Encoder" not in res:
+        res["VAE Encoder"] = "Full"
+
+    if "VAE Decoder" not in res:
+        res["VAE Decoder"] = "Full"
+
     return res
 
 
-settings_map = {}
+infotext_to_setting_name_mapping = [
-
 
+]
+"""Mapping of infotext labels to setting names. Only left for backwards compatibility - use OptionInfo(..., infotext='...') instead.
+Example content:
 
 infotext_to_setting_name_mapping = [
-    ('Clip skip', 'CLIP_stop_at_last_layers', ),
     ('Conditional mask weight', 'inpainting_mask_weight'),
     ('Model hash', 'sd_model_checkpoint'),
     ('ENSD', 'eta_noise_seed_delta'),
     ('Schedule type', 'k_sched_type'),
-    ('Schedule max sigma', 'sigma_max'),
-    ('Schedule min sigma', 'sigma_min'),
-    ('Schedule rho', 'rho'),
-    ('Noise multiplier', 'initial_noise_multiplier'),
-    ('Eta', 'eta_ancestral'),
-    ('Eta DDIM', 'eta_ddim'),
-    ('Discard penultimate sigma', 'always_discard_next_to_last_sigma'),
-    ('UniPC variant', 'uni_pc_variant'),
-    ('UniPC skip type', 'uni_pc_skip_type'),
-    ('UniPC order', 'uni_pc_order'),
-    ('UniPC lower order final', 'uni_pc_lower_order_final'),
-    ('Token merging ratio', 'token_merging_ratio'),
-    ('Token merging ratio hr', 'token_merging_ratio_hr'),
-    ('RNG', 'randn_source'),
-    ('NGMS', 's_min_uncond'),
 ]
+"""
 
 
 def create_override_settings_dict(text_pairs):
@@ -378,7 +349,8 @@ def create_override_settings_dict(text_pairs):
 
         params[k] = v.strip()
 
-    for param_name, setting_name in infotext_to_setting_name_mapping:
+    mapping = [(info.infotext, k) for k, info in shared.opts.data_labels.items() if info.infotext]
+    for param_name, setting_name in mapping + infotext_to_setting_name_mapping:
         value = params.get(param_name, None)
 
         if value is None:
@@ -427,10 +399,16 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
         return res
 
     if override_settings_component is not None:
+        already_handled_fields = {key: 1 for _, key in paste_fields}
+
         def paste_settings(params):
             vals = {}
 
-            for param_name, setting_name in infotext_to_setting_name_mapping:
+            mapping = [(info.infotext, k) for k, info in shared.opts.data_labels.items() if info.infotext]
+            for param_name, setting_name in mapping + infotext_to_setting_name_mapping:
+                if param_name in already_handled_fields:
+                    continue
+
                 v = params.get(param_name, None)
                 if v is None:
                     continue

modules/gfpgan_model.py

@@ -9,6 +9,7 @@ from modules import paths, shared, devices, modelloader, errors
 model_dir = "GFPGAN"
 user_path = None
 model_path = os.path.join(paths.models_path, model_dir)
+model_file_path = None
 model_url = "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth"
 have_gfpgan = False
 loaded_gfpgan_model = None
@@ -17,6 +18,7 @@ loaded_gfpgan_model = None
 def gfpgann():
     global loaded_gfpgan_model
     global model_path
+    global model_file_path
     if loaded_gfpgan_model is not None:
         loaded_gfpgan_model.gfpgan.to(devices.device_gfpgan)
         return loaded_gfpgan_model
@@ -24,17 +26,24 @@ def gfpgann():
     if gfpgan_constructor is None:
         return None
 
-    models = modelloader.load_models(model_path, model_url, user_path, ext_filter="GFPGAN")
+    models = modelloader.load_models(model_path, model_url, user_path, ext_filter=['.pth'])
-    if len(models) == 1 and "http" in models[0]:
+
+    if len(models) == 1 and models[0].startswith("http"):
         model_file = models[0]
     elif len(models) != 0:
-        latest_file = max(models, key=os.path.getctime)
+        gfp_models = []
+        for item in models:
+            if 'GFPGAN' in os.path.basename(item):
+                gfp_models.append(item)
+        latest_file = max(gfp_models, key=os.path.getctime)
         model_file = latest_file
     else:
         print("Unable to load gfpgan model!")
         return None
+
     if hasattr(facexlib.detection.retinaface, 'device'):
         facexlib.detection.retinaface.device = devices.device_gfpgan
+    model_file_path = model_file
     model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan)
     loaded_gfpgan_model = model
 
@@ -70,29 +79,32 @@ gfpgan_constructor = None
 
 
 def setup_model(dirname):
-    global model_path
-    if not os.path.exists(model_path):
-        os.makedirs(model_path)
-
     try:
+        os.makedirs(model_path, exist_ok=True)
         from gfpgan import GFPGANer
         from facexlib import detection, parsing  # noqa: F401
         global user_path
         global have_gfpgan
         global gfpgan_constructor
+        global model_file_path
+
+        facexlib_path = model_path
+
+        if dirname is not None:
+            facexlib_path = dirname
 
         load_file_from_url_orig = gfpgan.utils.load_file_from_url
         facex_load_file_from_url_orig = facexlib.detection.load_file_from_url
         facex_load_file_from_url_orig2 = facexlib.parsing.load_file_from_url
 
         def my_load_file_from_url(**kwargs):
-            return load_file_from_url_orig(**dict(kwargs, model_dir=model_path))
+            return load_file_from_url_orig(**dict(kwargs, model_dir=model_file_path))
 
         def facex_load_file_from_url(**kwargs):
-            return facex_load_file_from_url_orig(**dict(kwargs, save_dir=model_path, model_dir=None))
+            return facex_load_file_from_url_orig(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
 
         def facex_load_file_from_url2(**kwargs):
-            return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=model_path, model_dir=None))
+            return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
 
         gfpgan.utils.load_file_from_url = my_load_file_from_url
         facexlib.detection.load_file_from_url = facex_load_file_from_url

modules/gitpython_hack.py

@@ -23,7 +23,7 @@ class Git(git.Git):
         )
         return self._parse_object_header(ret)
 
-    def stream_object_data(self, ref: str) -> tuple[str, str, int, "Git.CatFileContentStream"]:
+    def stream_object_data(self, ref: str) -> tuple[str, str, int, Git.CatFileContentStream]:
         # Not really streaming, per se; this buffers the entire object in memory.
         # Shouldn't be a problem for our use case, since we're only using this for
         # object headers (commit objects).

modules/gradio_extensons.py

@@ -0,0 +1,142 @@
+from inspect import signature
+from functools import wraps
+import gradio as gr
+
+from modules import scripts, ui_tempdir, patches
+
+
+def add_classes_to_gradio_component(comp):
+    """
+    this adds gradio-* to the component for css styling (ie gradio-button to gr.Button), as well as some others
+    """
+
+    comp.elem_classes = [f"gradio-{comp.get_block_name()}", *(comp.elem_classes or [])]
+
+    if getattr(comp, 'multiselect', False):
+        comp.elem_classes.append('multiselect')
+
+
+def IOComponent_init(self, *args, **kwargs):
+    self.webui_tooltip = kwargs.pop('tooltip', None)
+
+    if scripts.scripts_current is not None:
+        scripts.scripts_current.before_component(self, **kwargs)
+
+    scripts.script_callbacks.before_component_callback(self, **kwargs)
+
+    res = original_IOComponent_init(self, *args, **kwargs)
+
+    add_classes_to_gradio_component(self)
+
+    scripts.script_callbacks.after_component_callback(self, **kwargs)
+
+    if scripts.scripts_current is not None:
+        scripts.scripts_current.after_component(self, **kwargs)
+
+    return res
+
+
+def Block_get_config(self):
+    config = original_Block_get_config(self)
+
+    webui_tooltip = getattr(self, 'webui_tooltip', None)
+    if webui_tooltip:
+        config["webui_tooltip"] = webui_tooltip
+
+    config.pop('example_inputs', None)
+
+    return config
+
+
+def BlockContext_init(self, *args, **kwargs):
+    res = original_BlockContext_init(self, *args, **kwargs)
+
+    add_classes_to_gradio_component(self)
+
+    return res
+
+
+def Blocks_get_config_file(self, *args, **kwargs):
+    config = original_Blocks_get_config_file(self, *args, **kwargs)
+
+    for comp_config in config["components"]:
+        if "example_inputs" in comp_config:
+            comp_config["example_inputs"] = {"serialized": []}
+
+    return config
+
+
+def gradio_component_compatibility_layer(component_function):
+    @wraps(component_function)
+    def patched_function(*args, **kwargs):
+        original_signature = signature(component_function).parameters
+        valid_kwargs = {k: v for k, v in kwargs.items() if k in original_signature}
+        result = component_function(*args, **valid_kwargs)
+        return result
+
+    return patched_function
+
+
+sub_events = ['then', 'success']
+
+
+def gradio_component_events_compatibility_layer(component_function):
+    @wraps(component_function)
+    def patched_function(*args, **kwargs):
+        kwargs['js'] = kwargs.get('js', kwargs.pop('_js', None))
+        original_signature = signature(component_function).parameters
+        valid_kwargs = {k: v for k, v in kwargs.items() if k in original_signature}
+
+        result = component_function(*args, **valid_kwargs)
+
+        for sub_event in sub_events:
+            component_event_then_function = getattr(result, sub_event, None)
+            if component_event_then_function:
+                patched_component_event_then_function = gradio_component_sub_events_compatibility_layer(component_event_then_function)
+                setattr(result, sub_event, patched_component_event_then_function)
+        # original_component_event_then_function = patches.patch(f'{__name__}.', obj=result, field='then', replacement=patched_component_event_then_function)
+
+        return result
+
+    return patched_function
+
+
+def gradio_component_sub_events_compatibility_layer(component_function):
+    @wraps(component_function)
+    def patched_function(*args, **kwargs):
+        kwargs['js'] = kwargs.get('js', kwargs.pop('_js', None))
+        original_signature = signature(component_function).parameters
+        valid_kwargs = {k: v for k, v in kwargs.items() if k in original_signature}
+        result = component_function(*args, **valid_kwargs)
+        return result
+
+    return patched_function
+
+
+for component_name in set(gr.components.__all__ + gr.layouts.__all__):
+    try:
+        component = getattr(gr, component_name)
+        component_init = getattr(component, '__init__')
+        patched_component_init = gradio_component_compatibility_layer(component_init)
+        original_IOComponent_init = patches.patch(f'{__name__}.{component_name}', obj=component, field="__init__", replacement=patched_component_init)
+
+        component_events = set(getattr(component, 'EVENTS'))
+        for component_event in component_events:
+            component_event_function = getattr(component, component_event)
+            patched_component_event_function = gradio_component_events_compatibility_layer(component_event_function)
+            original_component_event_function = patches.patch(f'{__name__}.{component_name}.{component_event}', obj=component, field=component_event, replacement=patched_component_event_function)
+    except Exception as e:
+        print(e)
+        pass
+
+gr.Box = gr.Group
+
+
+original_IOComponent_init = patches.patch(__name__, obj=gr.components.base.Component, field="__init__", replacement=IOComponent_init)
+original_Block_get_config = patches.patch(__name__, obj=gr.blocks.Block, field="get_config", replacement=Block_get_config)
+original_BlockContext_init = patches.patch(__name__, obj=gr.blocks.BlockContext, field="__init__", replacement=BlockContext_init)
+original_Blocks_get_config_file = patches.patch(__name__, obj=gr.blocks.Blocks, field="get_config_file", replacement=Blocks_get_config_file)
+
+
+ui_tempdir.install_ui_tempdir_override()
+

modules/hashes.py

@@ -1,38 +1,11 @@
 import hashlib
-import json
 import os.path
 
-import filelock
-
 from modules import shared
-from modules.paths import data_path
+import modules.cache
 
-
+dump_cache = modules.cache.dump_cache
-cache_filename = os.path.join(data_path, "cache.json")
+cache = modules.cache.cache
-cache_data = None
-
-
-def dump_cache():
-    with filelock.FileLock(f"{cache_filename}.lock"):
-        with open(cache_filename, "w", encoding="utf8") as file:
-            json.dump(cache_data, file, indent=4)
-
-
-def cache(subsection):
-    global cache_data
-
-    if cache_data is None:
-        with filelock.FileLock(f"{cache_filename}.lock"):
-            if not os.path.isfile(cache_filename):
-                cache_data = {}
-            else:
-                with open(cache_filename, "r", encoding="utf8") as file:
-                    cache_data = json.load(file)
-
-    s = cache_data.get(subsection, {})
-    cache_data[subsection] = s
-
-    return s
 
 
 def calculate_sha256(filename):

modules/hypernetworks/hypernetwork.py

@@ -3,13 +3,14 @@ import glob
 import html
 import os
 import inspect
+from contextlib import closing
 
 import modules.textual_inversion.dataset
 import torch
 import tqdm
 from einops import rearrange, repeat
 from ldm.util import default
-from modules import devices, processing, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint, errors
+from modules import devices, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint, errors
 from modules.textual_inversion import textual_inversion, logging
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 from torch import einsum
@@ -353,17 +354,6 @@ def load_hypernetworks(names, multipliers=None):
         shared.loaded_hypernetworks.append(hypernetwork)
 
 
-def find_closest_hypernetwork_name(search: str):
-    if not search:
-        return None
-    search = search.lower()
-    applicable = [name for name in shared.hypernetworks if search in name.lower()]
-    if not applicable:
-        return None
-    applicable = sorted(applicable, key=lambda name: len(name))
-    return applicable[0]
-
-
 def apply_single_hypernetwork(hypernetwork, context_k, context_v, layer=None):
     hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context_k.shape[2], None)
 
@@ -388,7 +378,7 @@ def apply_hypernetworks(hypernetworks, context, layer=None):
     return context_k, context_v
 
 
-def attention_CrossAttention_forward(self, x, context=None, mask=None):
+def attention_CrossAttention_forward(self, x, context=None, mask=None, **kwargs):
     h = self.heads
 
     q = self.to_q(x)
@@ -446,18 +436,6 @@ def statistics(data):
     return total_information, recent_information
 
 
-def report_statistics(loss_info:dict):
-    keys = sorted(loss_info.keys(), key=lambda x: sum(loss_info[x]) / len(loss_info[x]))
-    for key in keys:
-        try:
-            print("Loss statistics for file " + key)
-            info, recent = statistics(list(loss_info[key]))
-            print(info)
-            print(recent)
-        except Exception as e:
-            print(e)
-
-
 def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, dropout_structure=None):
     # Remove illegal characters from name.
     name = "".join( x for x in name if (x.isalnum() or x in "._- "))
@@ -490,9 +468,8 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
     shared.reload_hypernetworks()
 
 
-def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_hypernetwork(id_task, hypernetwork_name: str, learn_rate: float, batch_size: int, gradient_step: int, data_root: str, log_directory: str, training_width: int, training_height: int, varsize: bool, steps: int, clip_grad_mode: str, clip_grad_value: float, shuffle_tags: bool, tag_drop_out: bool, latent_sampling_method: str, use_weight: bool, create_image_every: int, save_hypernetwork_every: int, template_filename: str, preview_from_txt2img: bool, preview_prompt: str, preview_negative_prompt: str, preview_steps: int, preview_sampler_name: str, preview_cfg_scale: float, preview_seed: int, preview_width: int, preview_height: int):
-    # images allows training previews to have infotext. Importing it at the top causes a circular import problem.
+    from modules import images, processing
-    from modules import images
 
     save_hypernetwork_every = save_hypernetwork_every or 0
     create_image_every = create_image_every or 0
@@ -721,7 +698,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
                         p.prompt = preview_prompt
                         p.negative_prompt = preview_negative_prompt
                         p.steps = preview_steps
-                        p.sampler_name = sd_samplers.samplers[preview_sampler_index].name
+                        p.sampler_name = sd_samplers.samplers_map[preview_sampler_name.lower()]
                         p.cfg_scale = preview_cfg_scale
                         p.seed = preview_seed
                         p.width = preview_width
@@ -734,6 +711,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
 
                     preview_text = p.prompt
 
+                    with closing(p):
                         processed = processing.process_images(p)
                         image = processed.images[0] if len(processed.images) > 0 else None
 
@@ -770,7 +748,6 @@ Last saved image: {html.escape(last_saved_image)}<br/>
         pbar.leave = False
         pbar.close()
         hypernetwork.eval()
-        #report_statistics(loss_dict)
         sd_hijack_checkpoint.remove()
 
 

modules/images.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import datetime
 
 import pytz
@@ -10,7 +12,7 @@ import re
 import numpy as np
 import piexif
 import piexif.helper
-from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
+from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin
 import string
 import json
 import hashlib
@@ -19,8 +21,6 @@ from modules import sd_samplers, shared, script_callbacks, errors
 from modules.paths_internal import roboto_ttf_file
 from modules.shared import opts
 
-import modules.sd_vae as sd_vae
-
 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
 
 
@@ -139,6 +139,11 @@ class GridAnnotation:
 
 
 def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
+
+    color_active = ImageColor.getcolor(opts.grid_text_active_color, 'RGB')
+    color_inactive = ImageColor.getcolor(opts.grid_text_inactive_color, 'RGB')
+    color_background = ImageColor.getcolor(opts.grid_background_color, 'RGB')
+
     def wrap(drawing, text, font, line_length):
         lines = ['']
         for word in text.split():
@@ -168,9 +173,6 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
 
     fnt = get_font(fontsize)
 
-    color_active = (0, 0, 0)
-    color_inactive = (153, 153, 153)
-
     pad_left = 0 if sum([sum([len(line.text) for line in lines]) for lines in ver_texts]) == 0 else width * 3 // 4
 
     cols = im.width // width
@@ -179,7 +181,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
     assert cols == len(hor_texts), f'bad number of horizontal texts: {len(hor_texts)}; must be {cols}'
     assert rows == len(ver_texts), f'bad number of vertical texts: {len(ver_texts)}; must be {rows}'
 
-    calc_img = Image.new("RGB", (1, 1), "white")
+    calc_img = Image.new("RGB", (1, 1), color_background)
     calc_d = ImageDraw.Draw(calc_img)
 
     for texts, allowed_width in zip(hor_texts + ver_texts, [width] * len(hor_texts) + [pad_left] * len(ver_texts)):
@@ -200,7 +202,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
 
     pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
 
-    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), "white")
+    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), color_background)
 
     for row in range(rows):
         for col in range(cols):
@@ -302,17 +304,19 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
 
         if ratio < src_ratio:
             fill_height = height // 2 - src_h // 2
+            if fill_height > 0:
                 res.paste(resized.resize((width, fill_height), box=(0, 0, width, 0)), box=(0, 0))
                 res.paste(resized.resize((width, fill_height), box=(0, resized.height, width, resized.height)), box=(0, fill_height + src_h))
         elif ratio > src_ratio:
             fill_width = width // 2 - src_w // 2
+            if fill_width > 0:
                 res.paste(resized.resize((fill_width, height), box=(0, 0, 0, height)), box=(0, 0))
                 res.paste(resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)), box=(fill_width + src_w, 0))
 
     return res
 
 
-invalid_filename_chars = '<>:"/\\|?*\n'
+invalid_filename_chars = '<>:"/\\|?*\n\r\t'
 invalid_filename_prefix = ' '
 invalid_filename_postfix = ' .'
 re_nonletters = re.compile(r'[\s' + string.punctuation + ']+')
@@ -336,16 +340,6 @@ def sanitize_filename_part(text, replace_spaces=True):
 
 
 class FilenameGenerator:
-    def get_vae_filename(self): #get the name of the VAE file.
-        if sd_vae.loaded_vae_file is None:
-            return "NoneType"
-        file_name = os.path.basename(sd_vae.loaded_vae_file)
-        split_file_name = file_name.split('.')
-        if len(split_file_name) > 1 and split_file_name[0] == '':
-            return split_file_name[1] # if the first character of the filename is "." then [1] is obtained.
-        else:
-            return split_file_name[0]
-
     replacements = {
         'seed': lambda self: self.seed if self.seed is not None else '',
         'seed_first': lambda self: self.seed if self.p.batch_size == 1 else self.p.all_seeds[0],
@@ -357,11 +351,13 @@ class FilenameGenerator:
         'styles': lambda self: self.p and sanitize_filename_part(", ".join([style for style in self.p.styles if not style == "None"]) or "None", replace_spaces=False),
         'sampler': lambda self: self.p and sanitize_filename_part(self.p.sampler_name, replace_spaces=False),
         'model_hash': lambda self: getattr(self.p, "sd_model_hash", shared.sd_model.sd_model_hash),
-        'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.model_name, replace_spaces=False),
+        'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.name_for_extra, replace_spaces=False),
         'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
         'datetime': lambda self, *args: self.datetime(*args),  # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
         'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
-        'prompt_hash': lambda self: hashlib.sha256(self.prompt.encode()).hexdigest()[0:8],
+        'prompt_hash': lambda self, *args: self.string_hash(self.prompt, *args),
+        'negative_prompt_hash': lambda self, *args: self.string_hash(self.p.negative_prompt, *args),
+        'full_prompt_hash': lambda self, *args: self.string_hash(f"{self.p.prompt} {self.p.negative_prompt}", *args),  # a space in between to create a unique string
         'prompt': lambda self: sanitize_filename_part(self.prompt),
         'prompt_no_styles': lambda self: self.prompt_no_style(),
         'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),
@@ -372,8 +368,10 @@ class FilenameGenerator:
         'hasprompt': lambda self, *args: self.hasprompt(*args),  # accepts formats:[hasprompt<prompt1|default><prompt2>..]
         'clip_skip': lambda self: opts.data["CLIP_stop_at_last_layers"],
         'denoising': lambda self: self.p.denoising_strength if self.p and self.p.denoising_strength else NOTHING_AND_SKIP_PREVIOUS_TEXT,
+        'user': lambda self: self.p.user,
         'vae_filename': lambda self: self.get_vae_filename(),
-
+        'none': lambda self: '',  # Overrides the default, so you can get just the sequence number
+        'image_hash': lambda self, *args: self.image_hash(*args)  # accepts formats: [image_hash<length>] default full hash
     }
     default_time_format = '%Y%m%d%H%M%S'
 
@@ -384,6 +382,22 @@ class FilenameGenerator:
         self.image = image
         self.zip = zip
 
+    def get_vae_filename(self):
+        """Get the name of the VAE file."""
+
+        import modules.sd_vae as sd_vae
+
+        if sd_vae.loaded_vae_file is None:
+            return "NoneType"
+
+        file_name = os.path.basename(sd_vae.loaded_vae_file)
+        split_file_name = file_name.split('.')
+        if len(split_file_name) > 1 and split_file_name[0] == '':
+            return split_file_name[1]  # if the first character of the filename is "." then [1] is obtained.
+        else:
+            return split_file_name[0]
+
+
     def hasprompt(self, *args):
         lower = self.prompt.lower()
         if self.p is None or self.prompt is None:
@@ -437,6 +451,14 @@ class FilenameGenerator:
 
         return sanitize_filename_part(formatted_time, replace_spaces=False)
 
+    def image_hash(self, *args):
+        length = int(args[0]) if (args and args[0] != "") else None
+        return hashlib.sha256(self.image.tobytes()).hexdigest()[0:length]
+
+    def string_hash(self, text, *args):
+        length = int(args[0]) if (args and args[0] != "") else 8
+        return hashlib.sha256(text.encode()).hexdigest()[0:length]
+
     def apply(self, x):
         res = ''
 
@@ -497,13 +519,23 @@ def get_next_sequence_number(path, basename):
     return result + 1
 
 
-def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_pnginfo=None):
+def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_pnginfo=None, pnginfo_section_name='parameters'):
+    """
+    Saves image to filename, including geninfo as text information for generation info.
+    For PNG images, geninfo is added to existing pnginfo dictionary using the pnginfo_section_name argument as key.
+    For JPG images, there's no dictionary and geninfo just replaces the EXIF description.
+    """
+
     if extension is None:
         extension = os.path.splitext(filename)[1]
 
     image_format = Image.registered_extensions()[extension]
 
     if extension.lower() == '.png':
+        existing_pnginfo = existing_pnginfo or {}
+        if opts.enable_pnginfo:
+            existing_pnginfo[pnginfo_section_name] = geninfo
+
         if opts.enable_pnginfo:
             pnginfo_data = PngImagePlugin.PngInfo()
             for k, v in (existing_pnginfo or {}).items():
@@ -529,6 +561,8 @@ def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_p
             })
 
             piexif.insert(exif_bytes, filename)
+    elif extension.lower() == ".gif":
+        image.save(filename, format=image_format, comment=geninfo)
     else:
         image.save(filename, format=image_format, quality=opts.jpeg_quality)
 
@@ -568,6 +602,11 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     """
     namegen = FilenameGenerator(p, seed, prompt, image)
 
+    # WebP and JPG formats have maximum dimension limits of 16383 and 65535 respectively. switch to PNG which has a much higher limit
+    if (image.height > 65535 or image.width > 65535) and extension.lower() in ("jpg", "jpeg") or (image.height > 16383 or image.width > 16383) and extension.lower() == "webp":
+        print('Image dimensions too large; saving as PNG')
+        extension = ".png"
+
     if save_to_dirs is None:
         save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)
 
@@ -585,13 +624,13 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         else:
             file_decoration = opts.samples_filename_pattern or "[seed]-[prompt_spaces]"
 
+        file_decoration = namegen.apply(file_decoration) + suffix
+
         add_number = opts.save_images_add_number or file_decoration == ''
 
         if file_decoration != "" and add_number:
             file_decoration = f"-{file_decoration}"
 
-        file_decoration = namegen.apply(file_decoration) + suffix
-
         if add_number:
             basecount = get_next_sequence_number(path, basename)
             fullfn = None
@@ -622,9 +661,15 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         """
         temp_file_path = f"{filename_without_extension}.tmp"
 
-        save_image_with_geninfo(image_to_save, info, temp_file_path, extension, params.pnginfo)
+        save_image_with_geninfo(image_to_save, info, temp_file_path, extension, existing_pnginfo=params.pnginfo, pnginfo_section_name=pnginfo_section_name)
 
-        os.replace(temp_file_path, filename_without_extension + extension)
+        filename = filename_without_extension + extension
+        if shared.opts.save_images_replace_action != "Replace":
+            n = 0
+            while os.path.exists(filename):
+                n += 1
+                filename = f"{filename_without_extension}-{n}{extension}"
+        os.replace(temp_file_path, filename)
 
     fullfn_without_extension, extension = os.path.splitext(params.filename)
     if hasattr(os, 'statvfs'):
@@ -639,12 +684,18 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     oversize = image.width > opts.target_side_length or image.height > opts.target_side_length
     if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > opts.img_downscale_threshold * 1024 * 1024):
         ratio = image.width / image.height
-
+        resize_to = None
         if oversize and ratio > 1:
-            image = image.resize((round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)), LANCZOS)
+            resize_to = round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)
         elif oversize:
-            image = image.resize((round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)), LANCZOS)
+            resize_to = round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)
 
+        if resize_to is not None:
+            try:
+                # Resizing image with LANCZOS could throw an exception if e.g. image mode is I;16
+                image = image.resize(resize_to, LANCZOS)
+            except Exception:
+                image = image.resize(resize_to)
         try:
             _atomically_save_image(image, fullfn_without_extension, ".jpg")
         except Exception as e:
@@ -662,13 +713,25 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     return fullfn, txt_fullfn
 
 
-def read_info_from_image(image):
+IGNORED_INFO_KEYS = {
-    items = image.info or {}
+    'jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
+    'loop', 'background', 'timestamp', 'duration', 'progressive', 'progression',
+    'icc_profile', 'chromaticity', 'photoshop',
+}
+
+
+def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
+    items = (image.info or {}).copy()
 
     geninfo = items.pop('parameters', None)
 
     if "exif" in items:
-        exif = piexif.load(items["exif"])
+        exif_data = items["exif"]
+        try:
+            exif = piexif.load(exif_data)
+        except OSError:
+            # memory / exif was not valid so piexif tried to read from a file
+            exif = None
         exif_comment = (exif or {}).get("Exif", {}).get(piexif.ExifIFD.UserComment, b'')
         try:
             exif_comment = piexif.helper.UserComment.load(exif_comment)
@@ -678,10 +741,10 @@ def read_info_from_image(image):
         if exif_comment:
             items['exif comment'] = exif_comment
             geninfo = exif_comment
+    elif "comment" in items: # for gif
+        geninfo = items["comment"].decode('utf8', errors="ignore")
 
-    for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
+    for field in IGNORED_INFO_KEYS:
-                    'loop', 'background', 'timestamp', 'duration', 'progressive', 'progression',
-                    'icc_profile', 'chromaticity']:
         items.pop(field, None)
 
     if items.get("Software", None) == "NovelAI":

modules/img2img.py

@@ -1,23 +1,27 @@
 import os
+from contextlib import closing
 from pathlib import Path
 
 import numpy as np
-from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError
+from PIL import Image, ImageOps, ImageFilter, ImageEnhance, UnidentifiedImageError
+import gradio as gr
 
-from modules import sd_samplers
+from modules import images as imgutil
-from modules.generation_parameters_copypaste import create_override_settings_dict
+from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
+from modules.sd_models import get_closet_checkpoint_match
 import modules.shared as shared
 import modules.processing as processing
 from modules.ui import plaintext_to_html
 import modules.scripts
 
 
-def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0):
+def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
+    output_dir = output_dir.strip()
     processing.fix_seed(p)
 
-    images = shared.listfiles(input_dir)
+    images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
 
     is_inpaint_batch = False
     if inpaint_mask_dir:
@@ -29,13 +33,19 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
 
     print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")
 
-    save_normally = output_dir == ''
-
-    p.do_not_save_grid = True
-    p.do_not_save_samples = not save_normally
-
     state.job_count = len(images) * p.n_iter
 
+    # extract "default" params to use in case getting png info fails
+    prompt = p.prompt
+    negative_prompt = p.negative_prompt
+    seed = p.seed
+    cfg_scale = p.cfg_scale
+    sampler_name = p.sampler_name
+    steps = p.steps
+    override_settings = p.override_settings
+    sd_model_checkpoint_override = get_closet_checkpoint_match(override_settings.get("sd_model_checkpoint", None))
+    batch_results = None
+    discard_further_results = False
     for i, image in enumerate(images):
         state.job = f"{i+1} out of {len(images)}"
         if state.skipped:
@@ -79,41 +89,77 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
             mask_image = Image.open(mask_image_path)
             p.image_mask = mask_image
 
+        if use_png_info:
+            try:
+                info_img = img
+                if png_info_dir:
+                    info_img_path = os.path.join(png_info_dir, os.path.basename(image))
+                    info_img = Image.open(info_img_path)
+                geninfo, _ = imgutil.read_info_from_image(info_img)
+                parsed_parameters = parse_generation_parameters(geninfo)
+                parsed_parameters = {k: v for k, v in parsed_parameters.items() if k in (png_info_props or {})}
+            except Exception:
+                parsed_parameters = {}
+
+            p.prompt = prompt + (" " + parsed_parameters["Prompt"] if "Prompt" in parsed_parameters else "")
+            p.negative_prompt = negative_prompt + (" " + parsed_parameters["Negative prompt"] if "Negative prompt" in parsed_parameters else "")
+            p.seed = int(parsed_parameters.get("Seed", seed))
+            p.cfg_scale = float(parsed_parameters.get("CFG scale", cfg_scale))
+            p.sampler_name = parsed_parameters.get("Sampler", sampler_name)
+            p.steps = int(parsed_parameters.get("Steps", steps))
+
+            model_info = get_closet_checkpoint_match(parsed_parameters.get("Model hash", None))
+            if model_info is not None:
+                p.override_settings['sd_model_checkpoint'] = model_info.name
+            elif sd_model_checkpoint_override:
+                p.override_settings['sd_model_checkpoint'] = sd_model_checkpoint_override
+            else:
+                p.override_settings.pop("sd_model_checkpoint", None)
+
+        if output_dir:
+            p.outpath_samples = output_dir
+            p.override_settings['save_to_dirs'] = False
+            p.override_settings['save_images_replace_action'] = "Add number suffix"
+            if p.n_iter > 1 or p.batch_size > 1:
+                p.override_settings['samples_filename_pattern'] = f'{image_path.stem}-[generation_number]'
+            else:
+                p.override_settings['samples_filename_pattern'] = f'{image_path.stem}'
+
         proc = modules.scripts.scripts_img2img.run(p, *args)
+
         if proc is None:
+            p.override_settings.pop('save_images_replace_action', None)
             proc = process_images(p)
 
-        for n, processed_image in enumerate(proc.images):
+        if not discard_further_results and proc:
-            filename = image_path.name
+            if batch_results:
+                batch_results.images.extend(proc.images)
+                batch_results.infotexts.extend(proc.infotexts)
+            else:
+                batch_results = proc
 
-            if n > 0:
+            if 0 <= shared.opts.img2img_batch_show_results_limit < len(batch_results.images):
-                left, right = os.path.splitext(filename)
+                discard_further_results = True
-                filename = f"{left}-{n}{right}"
+                batch_results.images = batch_results.images[:int(shared.opts.img2img_batch_show_results_limit)]
+                batch_results.infotexts = batch_results.infotexts[:int(shared.opts.img2img_batch_show_results_limit)]
 
-            if not save_normally:
+    return batch_results
-                os.makedirs(output_dir, exist_ok=True)
-                if processed_image.mode == 'RGBA':
-                    processed_image = processed_image.convert("RGB")
-                processed_image.save(os.path.join(output_dir, filename))
 
 
-def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args):
+def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_name: str, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
     override_settings = create_override_settings_dict(override_settings_texts)
 
     is_batch = mode == 5
 
     if mode == 0:  # img2img
-        image = init_img.convert("RGB")
+        image = init_img
         mask = None
     elif mode == 1:  # img2img sketch
-        image = sketch.convert("RGB")
+        image = sketch
         mask = None
     elif mode == 2:  # inpaint
         image, mask = init_img_with_mask["image"], init_img_with_mask["mask"]
-        alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')
+        mask = processing.create_binary_mask(mask)
-        mask = mask.convert('L').point(lambda x: 255 if x > 128 else 0, mode='1')
-        mask = ImageChops.lighter(alpha_mask, mask).convert('L')
-        image = image.convert("RGB")
     elif mode == 3:  # inpaint sketch
         image = inpaint_color_sketch
         orig = inpaint_color_sketch_orig or inpaint_color_sketch
@@ -122,7 +168,6 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         mask = ImageEnhance.Brightness(mask).enhance(1 - mask_alpha / 100)
         blur = ImageFilter.GaussianBlur(mask_blur)
         image = Image.composite(image.filter(blur), orig, mask.filter(blur))
-        image = image.convert("RGB")
     elif mode == 4:  # inpaint upload mask
         image = init_img_inpaint
         mask = init_mask_inpaint
@@ -149,21 +194,13 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         prompt=prompt,
         negative_prompt=negative_prompt,
         styles=prompt_styles,
-        seed=seed,
+        sampler_name=sampler_name,
-        subseed=subseed,
-        subseed_strength=subseed_strength,
-        seed_resize_from_h=seed_resize_from_h,
-        seed_resize_from_w=seed_resize_from_w,
-        seed_enable_extras=seed_enable_extras,
-        sampler_name=sd_samplers.samplers_for_img2img[sampler_index].name,
         batch_size=batch_size,
         n_iter=n_iter,
         steps=steps,
         cfg_scale=cfg_scale,
         width=width,
         height=height,
-        restore_faces=restore_faces,
-        tiling=tiling,
         init_images=[image],
         mask=mask,
         mask_blur=mask_blur,
@@ -180,25 +217,26 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     p.scripts = modules.scripts.scripts_img2img
     p.script_args = args
 
-    if shared.cmd_opts.enable_console_prompts:
+    p.user = request.username
+
+    if shared.opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
     if mask:
         p.extra_generation_params["Mask blur"] = mask_blur
 
+    with closing(p):
         if is_batch:
             assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
+            processed = process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
 
-        process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by)
+            if processed is None:
-
                 processed = Processed(p, [], p.seed, "")
         else:
             processed = modules.scripts.scripts_img2img.run(p, *args)
             if processed is None:
                 processed = process_images(p)
 
-    p.close()
-
     shared.total_tqdm.clear()
 
     generation_info_js = processed.js()
@@ -208,4 +246,4 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     if opts.do_not_show_images:
         processed.images = []
 
-    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)
+    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments, classname="comments")

modules/initialize.py

@@ -0,0 +1,168 @@
+import importlib
+import logging
+import sys
+import warnings
+from threading import Thread
+
+from modules.timer import startup_timer
+
+
+def imports():
+    logging.getLogger("torch.distributed.nn").setLevel(logging.ERROR)  # sshh...
+    logging.getLogger("xformers").addFilter(lambda record: 'A matching Triton is not available' not in record.getMessage())
+
+    import torch  # noqa: F401
+    startup_timer.record("import torch")
+    import pytorch_lightning  # noqa: F401
+    startup_timer.record("import torch")
+    warnings.filterwarnings(action="ignore", category=DeprecationWarning, module="pytorch_lightning")
+    warnings.filterwarnings(action="ignore", category=UserWarning, module="torchvision")
+
+    import gradio  # noqa: F401
+    startup_timer.record("import gradio")
+
+    from modules import paths, timer, import_hook, errors  # noqa: F401
+    startup_timer.record("setup paths")
+
+    import ldm.modules.encoders.modules  # noqa: F401
+    startup_timer.record("import ldm")
+
+    import sgm.modules.encoders.modules  # noqa: F401
+    startup_timer.record("import sgm")
+
+    from modules import shared_init
+    shared_init.initialize()
+    startup_timer.record("initialize shared")
+
+    from modules import processing, gradio_extensons, ui  # noqa: F401
+    startup_timer.record("other imports")
+
+
+def check_versions():
+    from modules.shared_cmd_options import cmd_opts
+
+    if not cmd_opts.skip_version_check:
+        from modules import errors
+        errors.check_versions()
+
+
+def initialize():
+    from modules import initialize_util
+    initialize_util.fix_torch_version()
+    initialize_util.fix_asyncio_event_loop_policy()
+    initialize_util.validate_tls_options()
+    initialize_util.configure_sigint_handler()
+    initialize_util.configure_opts_onchange()
+
+    from modules import modelloader
+    modelloader.cleanup_models()
+
+    from modules import sd_models
+    sd_models.setup_model()
+    startup_timer.record("setup SD model")
+
+    from modules.shared_cmd_options import cmd_opts
+
+    from modules import codeformer_model
+    warnings.filterwarnings(action="ignore", category=UserWarning, module="torchvision.transforms.functional_tensor")
+    codeformer_model.setup_model(cmd_opts.codeformer_models_path)
+    startup_timer.record("setup codeformer")
+
+    from modules import gfpgan_model
+    gfpgan_model.setup_model(cmd_opts.gfpgan_models_path)
+    startup_timer.record("setup gfpgan")
+
+    initialize_rest(reload_script_modules=False)
+
+
+def initialize_rest(*, reload_script_modules=False):
+    """
+    Called both from initialize() and when reloading the webui.
+    """
+    from modules.shared_cmd_options import cmd_opts
+
+    from modules import sd_samplers
+    sd_samplers.set_samplers()
+    startup_timer.record("set samplers")
+
+    from modules import extensions
+    extensions.list_extensions()
+    startup_timer.record("list extensions")
+
+    from modules import initialize_util
+    initialize_util.restore_config_state_file()
+    startup_timer.record("restore config state file")
+
+    from modules import shared, upscaler, scripts
+    if cmd_opts.ui_debug_mode:
+        shared.sd_upscalers = upscaler.UpscalerLanczos().scalers
+        scripts.load_scripts()
+        return
+
+    from modules import sd_models
+    sd_models.list_models()
+    startup_timer.record("list SD models")
+
+    from modules import localization
+    localization.list_localizations(cmd_opts.localizations_dir)
+    startup_timer.record("list localizations")
+
+    with startup_timer.subcategory("load scripts"):
+        scripts.load_scripts()
+
+    if reload_script_modules:
+        for module in [module for name, module in sys.modules.items() if name.startswith("modules.ui")]:
+            importlib.reload(module)
+        startup_timer.record("reload script modules")
+
+    from modules import modelloader
+    modelloader.load_upscalers()
+    startup_timer.record("load upscalers")
+
+    from modules import sd_vae
+    sd_vae.refresh_vae_list()
+    startup_timer.record("refresh VAE")
+
+    from modules import textual_inversion
+    textual_inversion.textual_inversion.list_textual_inversion_templates()
+    startup_timer.record("refresh textual inversion templates")
+
+    from modules import script_callbacks, sd_hijack_optimizations, sd_hijack
+    script_callbacks.on_list_optimizers(sd_hijack_optimizations.list_optimizers)
+    sd_hijack.list_optimizers()
+    startup_timer.record("scripts list_optimizers")
+
+    from modules import sd_unet
+    sd_unet.list_unets()
+    startup_timer.record("scripts list_unets")
+
+    def load_model():
+        """
+        Accesses shared.sd_model property to load model.
+        After it's available, if it has been loaded before this access by some extension,
+        its optimization may be None because the list of optimizaers has neet been filled
+        by that time, so we apply optimization again.
+        """
+
+        shared.sd_model  # noqa: B018
+
+        if sd_hijack.current_optimizer is None:
+            sd_hijack.apply_optimizations()
+
+        from modules import devices
+        devices.first_time_calculation()
+    if not shared.cmd_opts.skip_load_model_at_start:
+        Thread(target=load_model).start()
+
+    from modules import shared_items
+    shared_items.reload_hypernetworks()
+    startup_timer.record("reload hypernetworks")
+
+    from modules import ui_extra_networks
+    ui_extra_networks.initialize()
+    ui_extra_networks.register_default_pages()
+
+    from modules import extra_networks
+    extra_networks.initialize()
+    extra_networks.register_default_extra_networks()
+    startup_timer.record("initialize extra networks")

modules/initialize_util.py

@@ -0,0 +1,206 @@
+import json
+import os
+import signal
+import sys
+import re
+
+from modules.timer import startup_timer
+
+
+def gradio_server_name():
+    from modules.shared_cmd_options import cmd_opts
+
+    if cmd_opts.server_name:
+        return cmd_opts.server_name
+    else:
+        return "0.0.0.0" if cmd_opts.listen else None
+
+
+def fix_torch_version():
+    import torch
+
+    # Truncate version number of nightly/local build of PyTorch to not cause exceptions with CodeFormer or Safetensors
+    if ".dev" in torch.__version__ or "+git" in torch.__version__:
+        torch.__long_version__ = torch.__version__
+        torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0)
+
+
+def fix_asyncio_event_loop_policy():
+    """
+        The default `asyncio` event loop policy only automatically creates
+        event loops in the main threads. Other threads must create event
+        loops explicitly or `asyncio.get_event_loop` (and therefore
+        `.IOLoop.current`) will fail. Installing this policy allows event
+        loops to be created automatically on any thread, matching the
+        behavior of Tornado versions prior to 5.0 (or 5.0 on Python 2).
+    """
+
+    import asyncio
+
+    if sys.platform == "win32" and hasattr(asyncio, "WindowsSelectorEventLoopPolicy"):
+        # "Any thread" and "selector" should be orthogonal, but there's not a clean
+        # interface for composing policies so pick the right base.
+        _BasePolicy = asyncio.WindowsSelectorEventLoopPolicy  # type: ignore
+    else:
+        _BasePolicy = asyncio.DefaultEventLoopPolicy
+
+    class AnyThreadEventLoopPolicy(_BasePolicy):  # type: ignore
+        """Event loop policy that allows loop creation on any thread.
+        Usage::
+
+            asyncio.set_event_loop_policy(AnyThreadEventLoopPolicy())
+        """
+
+        def get_event_loop(self) -> asyncio.AbstractEventLoop:
+            try:
+                return super().get_event_loop()
+            except (RuntimeError, AssertionError):
+                # This was an AssertionError in python 3.4.2 (which ships with debian jessie)
+                # and changed to a RuntimeError in 3.4.3.
+                # "There is no current event loop in thread %r"
+                loop = self.new_event_loop()
+                self.set_event_loop(loop)
+                return loop
+
+    asyncio.set_event_loop_policy(AnyThreadEventLoopPolicy())
+
+
+def restore_config_state_file():
+    from modules import shared, config_states
+
+    config_state_file = shared.opts.restore_config_state_file
+    if config_state_file == "":
+        return
+
+    shared.opts.restore_config_state_file = ""
+    shared.opts.save(shared.config_filename)
+
+    if os.path.isfile(config_state_file):
+        print(f"*** About to restore extension state from file: {config_state_file}")
+        with open(config_state_file, "r", encoding="utf-8") as f:
+            config_state = json.load(f)
+            config_states.restore_extension_config(config_state)
+        startup_timer.record("restore extension config")
+    elif config_state_file:
+        print(f"!!! Config state backup not found: {config_state_file}")
+
+
+def validate_tls_options():
+    from modules.shared_cmd_options import cmd_opts
+
+    if not (cmd_opts.tls_keyfile and cmd_opts.tls_certfile):
+        return
+
+    try:
+        if not os.path.exists(cmd_opts.tls_keyfile):
+            print("Invalid path to TLS keyfile given")
+        if not os.path.exists(cmd_opts.tls_certfile):
+            print(f"Invalid path to TLS certfile: '{cmd_opts.tls_certfile}'")
+    except TypeError:
+        cmd_opts.tls_keyfile = cmd_opts.tls_certfile = None
+        print("TLS setup invalid, running webui without TLS")
+    else:
+        print("Running with TLS")
+    startup_timer.record("TLS")
+
+
+def get_gradio_auth_creds():
+    """
+    Convert the gradio_auth and gradio_auth_path commandline arguments into
+    an iterable of (username, password) tuples.
+    """
+    from modules.shared_cmd_options import cmd_opts
+
+    def process_credential_line(s):
+        s = s.strip()
+        if not s:
+            return None
+        return tuple(s.split(':', 1))
+
+    if cmd_opts.gradio_auth:
+        for cred in cmd_opts.gradio_auth.split(','):
+            cred = process_credential_line(cred)
+            if cred:
+                yield cred
+
+    if cmd_opts.gradio_auth_path:
+        with open(cmd_opts.gradio_auth_path, 'r', encoding="utf8") as file:
+            for line in file.readlines():
+                for cred in line.strip().split(','):
+                    cred = process_credential_line(cred)
+                    if cred:
+                        yield cred
+
+
+def dumpstacks():
+    import threading
+    import traceback
+
+    id2name = {th.ident: th.name for th in threading.enumerate()}
+    code = []
+    for threadId, stack in sys._current_frames().items():
+        code.append(f"\n# Thread: {id2name.get(threadId, '')}({threadId})")
+        for filename, lineno, name, line in traceback.extract_stack(stack):
+            code.append(f"""File: "{filename}", line {lineno}, in {name}""")
+            if line:
+                code.append("  " + line.strip())
+
+    print("\n".join(code))
+
+
+def configure_sigint_handler():
+    # make the program just exit at ctrl+c without waiting for anything
+
+    from modules import shared
+
+    def sigint_handler(sig, frame):
+        print(f'Interrupted with signal {sig} in {frame}')
+
+        if shared.opts.dump_stacks_on_signal:
+            dumpstacks()
+
+        os._exit(0)
+
+    if not os.environ.get("COVERAGE_RUN"):
+        # Don't install the immediate-quit handler when running under coverage,
+        # as then the coverage report won't be generated.
+        signal.signal(signal.SIGINT, sigint_handler)
+
+
+def configure_opts_onchange():
+    from modules import shared, sd_models, sd_vae, ui_tempdir, sd_hijack
+    from modules.call_queue import wrap_queued_call
+
+    shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
+    shared.opts.onchange("sd_vae", wrap_queued_call(lambda: sd_vae.reload_vae_weights()), call=False)
+    shared.opts.onchange("sd_vae_overrides_per_model_preferences", wrap_queued_call(lambda: sd_vae.reload_vae_weights()), call=False)
+    shared.opts.onchange("temp_dir", ui_tempdir.on_tmpdir_changed)
+    shared.opts.onchange("gradio_theme", shared.reload_gradio_theme)
+    shared.opts.onchange("cross_attention_optimization", wrap_queued_call(lambda: sd_hijack.model_hijack.redo_hijack(shared.sd_model)), call=False)
+    startup_timer.record("opts onchange")
+
+
+def setup_middleware(app):
+    from starlette.middleware.gzip import GZipMiddleware
+
+    app.middleware_stack = None  # reset current middleware to allow modifying user provided list
+    app.add_middleware(GZipMiddleware, minimum_size=1000)
+    configure_cors_middleware(app)
+    app.build_middleware_stack()  # rebuild middleware stack on-the-fly
+
+
+def configure_cors_middleware(app):
+    from starlette.middleware.cors import CORSMiddleware
+    from modules.shared_cmd_options import cmd_opts
+
+    cors_options = {
+        "allow_methods": ["*"],
+        "allow_headers": ["*"],
+        "allow_credentials": True,
+    }
+    if cmd_opts.cors_allow_origins:
+        cors_options["allow_origins"] = cmd_opts.cors_allow_origins.split(',')
+    if cmd_opts.cors_allow_origins_regex:
+        cors_options["allow_origin_regex"] = cmd_opts.cors_allow_origins_regex
+    app.add_middleware(CORSMiddleware, **cors_options)
+

modules/interrogate.py

@@ -184,10 +184,8 @@ class InterrogateModels:
 
     def interrogate(self, pil_image):
         res = ""
-        shared.state.begin()
+        shared.state.begin(job="interrogate")
-        shared.state.job = 'interrogate'
         try:
-            if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
             lowvram.send_everything_to_cpu()
             devices.torch_gc()
 

modules/launch_utils.py

@@ -1,6 +1,9 @@
 # this scripts installs necessary requirements and launches main program in webui.py
+import logging
+import re
 import subprocess
 import os
+import shutil
 import sys
 import importlib.util
 import platform
@@ -9,8 +12,11 @@ from functools import lru_cache
 
 from modules import cmd_args, errors
 from modules.paths_internal import script_path, extensions_dir
+from modules.timer import startup_timer
+from modules import logging_config
 
 args, _ = cmd_args.parser.parse_known_args()
+logging_config.setup_logging(args.loglevel)
 
 python = sys.executable
 git = os.environ.get('GIT', "git")
@@ -58,7 +64,7 @@ Use --skip-python-version-check to suppress this warning.
 @lru_cache()
 def commit_hash():
     try:
-        return subprocess.check_output([git, "rev-parse", "HEAD"], shell=False, encoding='utf8').strip()
+        return subprocess.check_output([git, "-C", script_path, "rev-parse", "HEAD"], shell=False, encoding='utf8').strip()
     except Exception:
         return "<none>"
 
@@ -66,13 +72,15 @@ def commit_hash():
 @lru_cache()
 def git_tag():
     try:
-        return subprocess.check_output([git, "describe", "--tags"], shell=False, encoding='utf8').strip()
+        return subprocess.check_output([git, "-C", script_path, "describe", "--tags"], shell=False, encoding='utf8').strip()
     except Exception:
         try:
-            from pathlib import Path
+
-            changelog_md = Path(__file__).parent.parent / "CHANGELOG.md"
+            changelog_md = os.path.join(os.path.dirname(os.path.dirname(__file__)), "CHANGELOG.md")
-            with changelog_md.open(encoding="utf-8") as file:
+            with open(changelog_md, "r", encoding="utf-8") as file:
-                return next((line.strip() for line in file if line.strip()), "<none>")
+                line = next((line.strip() for line in file if line.strip()), "<none>")
+                line = line.replace("## ", "")
+                return line
         except Exception:
             return "<none>"
 
@@ -135,6 +143,25 @@ def check_run_python(code: str) -> bool:
     return result.returncode == 0
 
 
+def git_fix_workspace(dir, name):
+    run(f'"{git}" -C "{dir}" fetch --refetch --no-auto-gc', f"Fetching all contents for {name}", f"Couldn't fetch {name}", live=True)
+    run(f'"{git}" -C "{dir}" gc --aggressive --prune=now', f"Pruning {name}", f"Couldn't prune {name}", live=True)
+    return
+
+
+def run_git(dir, name, command, desc=None, errdesc=None, custom_env=None, live: bool = default_command_live, autofix=True):
+    try:
+        return run(f'"{git}" -C "{dir}" {command}', desc=desc, errdesc=errdesc, custom_env=custom_env, live=live)
+    except RuntimeError:
+        if not autofix:
+            raise
+
+    print(f"{errdesc}, attempting autofix...")
+    git_fix_workspace(dir, name)
+
+    return run(f'"{git}" -C "{dir}" {command}', desc=desc, errdesc=errdesc, custom_env=custom_env, live=live)
+
+
 def git_clone(url, dir, name, commithash=None):
     # TODO clone into temporary dir and move if successful
 
@@ -142,15 +169,24 @@ def git_clone(url, dir, name, commithash=None):
         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()
+        current_hash = run_git(dir, name, 'rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}", live=False).strip()
         if current_hash == commithash:
             return
 
-        run(f'"{git}" -C "{dir}" fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}")
+        if run_git(dir, name, 'config --get remote.origin.url', None, f"Couldn't determine {name}'s origin URL", live=False).strip() != url:
-        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}")
+            run_git(dir, name, f'remote set-url origin "{url}"', None, f"Failed to set {name}'s origin URL", live=False)
+
+        run_git(dir, name, 'fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}", autofix=False)
+
+        run_git(dir, name, f'checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
+
         return
 
-    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}")
+    try:
+        run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
+    except RuntimeError:
+        shutil.rmtree(dir, ignore_errors=True)
+        raise
 
     if commithash is not None:
         run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
@@ -190,9 +226,11 @@ def run_extension_installer(extension_dir):
 
     try:
         env = os.environ.copy()
-        env['PYTHONPATH'] = os.path.abspath(".")
+        env['PYTHONPATH'] = f"{os.path.abspath('.')}{os.pathsep}{env.get('PYTHONPATH', '')}"
 
-        print(run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env))
+        stdout = run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env).strip()
+        if stdout:
+            print(stdout)
     except Exception as e:
         errors.report(str(e))
 
@@ -210,7 +248,7 @@ def list_extensions(settings_file):
     disabled_extensions = set(settings.get('disabled_extensions', []))
     disable_all_extensions = settings.get('disable_all_extensions', 'none')
 
-    if disable_all_extensions != 'none':
+    if disable_all_extensions != 'none' or args.disable_extra_extensions or args.disable_all_extensions or not os.path.isdir(extensions_dir):
         return []
 
     return [x for x in os.listdir(extensions_dir) if x not in disabled_extensions]
@@ -220,8 +258,53 @@ def run_extensions_installers(settings_file):
     if not os.path.isdir(extensions_dir):
         return
 
+    with startup_timer.subcategory("run extensions installers"):
         for dirname_extension in list_extensions(settings_file):
-        run_extension_installer(os.path.join(extensions_dir, dirname_extension))
+            logging.debug(f"Installing {dirname_extension}")
+
+            path = os.path.join(extensions_dir, dirname_extension)
+
+            if os.path.isdir(path):
+                run_extension_installer(path)
+                startup_timer.record(dirname_extension)
+
+
+re_requirement = re.compile(r"\s*([-_a-zA-Z0-9]+)\s*(?:==\s*([-+_.a-zA-Z0-9]+))?\s*")
+
+
+def requirements_met(requirements_file):
+    """
+    Does a simple parse of a requirements.txt file to determine if all rerqirements in it
+    are already installed. Returns True if so, False if not installed or parsing fails.
+    """
+
+    import importlib.metadata
+    import packaging.version
+
+    with open(requirements_file, "r", encoding="utf8") as file:
+        for line in file:
+            if line.strip() == "":
+                continue
+
+            m = re.match(re_requirement, line)
+            if m is None:
+                return False
+
+            package = m.group(1).strip()
+            version_required = (m.group(2) or "").strip()
+
+            if version_required == "":
+                continue
+
+            try:
+                version_installed = importlib.metadata.version(package)
+            except Exception:
+                return False
+
+            if packaging.version.parse(version_required) != packaging.version.parse(version_installed):
+                return False
+
+    return True
 
 
 def prepare_environment():
@@ -230,22 +313,23 @@ def prepare_environment():
     requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
 
     xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.20')
-    gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "https://github.com/TencentARC/GFPGAN/archive/8d2447a2d918f8eba5a4a01463fd48e45126a379.zip")
     clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip")
     openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip")
 
     stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
+    stable_diffusion_xl_repo = os.environ.get('STABLE_DIFFUSION_XL_REPO', "https://github.com/Stability-AI/generative-models.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', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
-    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "c9fe758757e022f05ca5a53fa8fac28889e4f1cf")
+    stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "45c443b316737a4ab6e40413d7794a7f5657c19f")
+    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "ab527a9a6d347f364e3d185ba6d714e22d80cb3c")
     codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
     blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
 
     try:
-        # the existance of this file is a signal to webui.sh/bat that webui needs to be restarted when it stops execution
+        # the existence of this file is a signal to webui.sh/bat that webui needs to be restarted when it stops execution
         os.remove(os.path.join(script_path, "tmp", "restart"))
         os.environ.setdefault('SD_WEBUI_RESTARTING', '1')
     except OSError:
@@ -254,8 +338,11 @@ def prepare_environment():
     if not args.skip_python_version_check:
         check_python_version()
 
+    startup_timer.record("checks")
+
     commit = commit_hash()
     tag = git_tag()
+    startup_timer.record("git version info")
 
     print(f"Python {sys.version}")
     print(f"Version: {tag}")
@@ -263,64 +350,69 @@ def prepare_environment():
 
     if args.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)
+        startup_timer.record("install torch")
 
     if not args.skip_torch_cuda_test and not check_run_python("import torch; assert torch.cuda.is_available()"):
         raise RuntimeError(
             'Torch is not able to use GPU; '
             'add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'
         )
-
+    startup_timer.record("torch GPU test")
-    if not is_installed("gfpgan"):
-        run_pip(f"install {gfpgan_package}", "gfpgan")
 
     if not is_installed("clip"):
         run_pip(f"install {clip_package}", "clip")
+        startup_timer.record("install clip")
 
     if not is_installed("open_clip"):
         run_pip(f"install {openclip_package}", "open_clip")
+        startup_timer.record("install open_clip")
 
     if (not is_installed("xformers") or args.reinstall_xformers) and args.xformers:
-        if platform.system() == "Windows":
-            if platform.python_version().startswith("3.10"):
-                run_pip(f"install -U -I --no-deps {xformers_package}", "xformers", live=True)
-            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(f"install -U -I --no-deps {xformers_package}", "xformers")
+        startup_timer.record("install xformers")
 
     if not is_installed("ngrok") and args.ngrok:
         run_pip("install ngrok", "ngrok")
+        startup_timer.record("install ngrok")
 
     os.makedirs(os.path.join(script_path, dir_repos), exist_ok=True)
 
     git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
+    git_clone(stable_diffusion_xl_repo, repo_dir('generative-models'), "Stable Diffusion XL", stable_diffusion_xl_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)
 
+    startup_timer.record("clone repositores")
+
     if not is_installed("lpips"):
         run_pip(f"install -r \"{os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}\"", "requirements for CodeFormer")
+        startup_timer.record("install CodeFormer requirements")
 
     if not os.path.isfile(requirements_file):
         requirements_file = os.path.join(script_path, requirements_file)
-    run_pip(f"install -r \"{requirements_file}\"", "requirements")
 
+    if not requirements_met(requirements_file):
+        run_pip(f"install -r \"{requirements_file}\"", "requirements")
+        startup_timer.record("install requirements")
+
+    if not args.skip_install:
         run_extensions_installers(settings_file=args.ui_settings_file)
 
     if args.update_check:
         version_check(commit)
+        startup_timer.record("check version")
 
     if args.update_all_extensions:
         git_pull_recursive(extensions_dir)
+        startup_timer.record("update extensions")
 
     if "--exit" in sys.argv:
         print("Exiting because of --exit argument")
         exit(0)
 
 
+
 def configure_for_tests():
     if "--api" not in sys.argv:
         sys.argv.append("--api")
@@ -342,3 +434,16 @@ def start():
         webui.api_only()
     else:
         webui.webui()
+
+
+def dump_sysinfo():
+    from modules import sysinfo
+    import datetime
+
+    text = sysinfo.get()
+    filename = f"sysinfo-{datetime.datetime.utcnow().strftime('%Y-%m-%d-%H-%M')}.json"
+
+    with open(filename, "w", encoding="utf8") as file:
+        file.write(text)
+
+    return filename

modules/localization.py

@@ -1,7 +1,7 @@
 import json
 import os
 
-from modules import errors
+from modules import errors, scripts
 
 localizations = {}
 
@@ -14,21 +14,23 @@ def list_localizations(dirname):
         if ext.lower() != ".json":
             continue
 
-        localizations[fn] = os.path.join(dirname, file)
+        localizations[fn] = [os.path.join(dirname, file)]
 
-    from modules import scripts
     for file in scripts.list_scripts("localizations", ".json"):
         fn, ext = os.path.splitext(file.filename)
-        localizations[fn] = file.path
+        if fn not in localizations:
+            localizations[fn] = []
+        localizations[fn].append(file.path)
 
 
 def localization_js(current_localization_name: str) -> str:
-    fn = localizations.get(current_localization_name, None)
+    fns = localizations.get(current_localization_name, None)
     data = {}
-    if fn is not None:
+    if fns is not None:
+        for fn in fns:
             try:
                 with open(fn, "r", encoding="utf8") as file:
-                data = json.load(file)
+                    data.update(json.load(file))
             except Exception:
                 errors.report(f"Error loading localization from {fn}", exc_info=True)
 

modules/logging_config.py

@@ -0,0 +1,41 @@
+import os
+import logging
+
+try:
+    from tqdm.auto import tqdm
+
+    class TqdmLoggingHandler(logging.Handler):
+        def __init__(self, level=logging.INFO):
+            super().__init__(level)
+
+        def emit(self, record):
+            try:
+                msg = self.format(record)
+                tqdm.write(msg)
+                self.flush()
+            except Exception:
+                self.handleError(record)
+
+    TQDM_IMPORTED = True
+except ImportError:
+    # tqdm does not exist before first launch
+    # I will import once the UI finishes seting up the enviroment and reloads.
+    TQDM_IMPORTED = False
+
+def setup_logging(loglevel):
+    if loglevel is None:
+        loglevel = os.environ.get("SD_WEBUI_LOG_LEVEL")
+
+    loghandlers = []
+
+    if TQDM_IMPORTED:
+        loghandlers.append(TqdmLoggingHandler())
+
+    if loglevel:
+        log_level = getattr(logging, loglevel.upper(), None) or logging.INFO
+        logging.basicConfig(
+            level=log_level,
+            format='%(asctime)s %(levelname)s [%(name)s] %(message)s',
+            datefmt='%Y-%m-%d %H:%M:%S',
+            handlers=loghandlers
+        )

modules/lowvram.py

@@ -1,5 +1,5 @@
 import torch
-from modules import devices
+from modules import devices, shared
 
 module_in_gpu = None
 cpu = torch.device("cpu")
@@ -14,7 +14,24 @@ def send_everything_to_cpu():
     module_in_gpu = None
 
 
+def is_needed(sd_model):
+    return shared.cmd_opts.lowvram or shared.cmd_opts.medvram or shared.cmd_opts.medvram_sdxl and hasattr(sd_model, 'conditioner')
+
+
+def apply(sd_model):
+    enable = is_needed(sd_model)
+    shared.parallel_processing_allowed = not enable
+
+    if enable:
+        setup_for_low_vram(sd_model, not shared.cmd_opts.lowvram)
+    else:
+        sd_model.lowvram = False
+
+
 def setup_for_low_vram(sd_model, use_medvram):
+    if getattr(sd_model, 'lowvram', False):
+        return
+
     sd_model.lowvram = True
 
     parents = {}
@@ -53,19 +70,50 @@ def setup_for_low_vram(sd_model, use_medvram):
         send_me_to_gpu(first_stage_model, None)
         return first_stage_model_decode(z)
 
-    # for SD1, cond_stage_model is CLIP and its NN is in the tranformer frield, but for SD2, it's open clip, and it's in model field
+    to_remain_in_cpu = [
-    if hasattr(sd_model.cond_stage_model, 'model'):
+        (sd_model, 'first_stage_model'),
-        sd_model.cond_stage_model.transformer = sd_model.cond_stage_model.model
+        (sd_model, 'depth_model'),
+        (sd_model, 'embedder'),
+        (sd_model, 'model'),
+        (sd_model, 'embedder'),
+    ]
 
-    # remove several big modules: cond, first_stage, depth/embedder (if applicable), and unet from the model and then
+    is_sdxl = hasattr(sd_model, 'conditioner')
-    # send the model to GPU. Then put modules back. the modules will be in CPU.
+    is_sd2 = not is_sdxl and hasattr(sd_model.cond_stage_model, 'model')
-    stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, getattr(sd_model, 'depth_model', None), getattr(sd_model, 'embedder', None), sd_model.model
+
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = None, None, None, None, None
+    if is_sdxl:
+        to_remain_in_cpu.append((sd_model, 'conditioner'))
+    elif is_sd2:
+        to_remain_in_cpu.append((sd_model.cond_stage_model, 'model'))
+    else:
+        to_remain_in_cpu.append((sd_model.cond_stage_model, 'transformer'))
+
+    # remove several big modules: cond, first_stage, depth/embedder (if applicable), and unet from the model
+    stored = []
+    for obj, field in to_remain_in_cpu:
+        module = getattr(obj, field, None)
+        stored.append(module)
+        setattr(obj, field, None)
+
+    # send the model to GPU.
     sd_model.to(devices.device)
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = stored
+
+    # put modules back. the modules will be in CPU.
+    for (obj, field), module in zip(to_remain_in_cpu, stored):
+        setattr(obj, field, module)
 
     # register hooks for those the first three models
+    if is_sdxl:
+        sd_model.conditioner.register_forward_pre_hook(send_me_to_gpu)
+    elif is_sd2:
+        sd_model.cond_stage_model.model.register_forward_pre_hook(send_me_to_gpu)
+        sd_model.cond_stage_model.model.token_embedding.register_forward_pre_hook(send_me_to_gpu)
+        parents[sd_model.cond_stage_model.model] = sd_model.cond_stage_model
+        parents[sd_model.cond_stage_model.model.token_embedding] = sd_model.cond_stage_model
+    else:
         sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
+        parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
+
     sd_model.first_stage_model.register_forward_pre_hook(send_me_to_gpu)
     sd_model.first_stage_model.encode = first_stage_model_encode_wrap
     sd_model.first_stage_model.decode = first_stage_model_decode_wrap
@@ -73,11 +121,6 @@ def setup_for_low_vram(sd_model, use_medvram):
         sd_model.depth_model.register_forward_pre_hook(send_me_to_gpu)
     if sd_model.embedder:
         sd_model.embedder.register_forward_pre_hook(send_me_to_gpu)
-    parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
-
-    if hasattr(sd_model.cond_stage_model, 'model'):
-        sd_model.cond_stage_model.model = sd_model.cond_stage_model.transformer
-        del sd_model.cond_stage_model.transformer
 
     if use_medvram:
         sd_model.model.register_forward_pre_hook(send_me_to_gpu)
@@ -101,4 +144,4 @@ def setup_for_low_vram(sd_model, use_medvram):
 
 
 def is_enabled(sd_model):
-    return getattr(sd_model, 'lowvram', False)
+    return sd_model.lowvram

modules/mac_specific.py

@@ -1,12 +1,20 @@
+import logging
+
 import torch
 import platform
 from modules.sd_hijack_utils import CondFunc
 from packaging import version
+from modules import shared
+
+log = logging.getLogger(__name__)
 
 
-# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
+# before torch version 1.13, has_mps is only available in nightly pytorch and macOS 12.3+,
-# check `getattr` and try it for compatibility
+# use check `getattr` and try it for compatibility.
+# in torch version 1.13, backends.mps.is_available() and backends.mps.is_built() are introduced in to check mps availabilty,
+# since torch 2.0.1+ nightly build, getattr(torch, 'has_mps', False) was deprecated, see https://github.com/pytorch/pytorch/pull/103279
 def check_for_mps() -> bool:
+    if version.parse(torch.__version__) <= version.parse("2.0.1"):
         if not getattr(torch, 'has_mps', False):
             return False
         try:
@@ -14,9 +22,24 @@ def check_for_mps() -> bool:
             return True
         except Exception:
             return False
+    else:
+        return torch.backends.mps.is_available() and torch.backends.mps.is_built()
+
+
 has_mps = check_for_mps()
 
 
+def torch_mps_gc() -> None:
+    try:
+        if shared.state.current_latent is not None:
+            log.debug("`current_latent` is set, skipping MPS garbage collection")
+            return
+        from torch.mps import empty_cache
+        empty_cache()
+    except Exception:
+        log.warning("MPS garbage collection failed", exc_info=True)
+
+
 # MPS workaround for https://github.com/pytorch/pytorch/issues/89784
 def cumsum_fix(input, cumsum_func, *args, **kwargs):
     if input.device.type == 'mps':
@@ -29,9 +52,6 @@ def cumsum_fix(input, cumsum_func, *args, **kwargs):
 
 
 if has_mps:
-    # MPS fix for randn in torchsde
-    CondFunc('torchsde._brownian.brownian_interval._randn', lambda _, size, dtype, device, seed: torch.randn(size, dtype=dtype, device=torch.device("cpu"), generator=torch.Generator(torch.device("cpu")).manual_seed(int(seed))).to(device), lambda _, size, dtype, device, seed: device.type == 'mps')
-
     if platform.mac_ver()[0].startswith("13.2."):
         # MPS workaround for https://github.com/pytorch/pytorch/issues/95188, thanks to danieldk (https://github.com/explosion/curated-transformers/pull/124)
         CondFunc('torch.nn.functional.linear', lambda _, input, weight, bias: (torch.matmul(input, weight.t()) + bias) if bias is not None else torch.matmul(input, weight.t()), lambda _, input, weight, bias: input.numel() > 10485760)

modules/modelloader.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import os
 import shutil
 import importlib
@@ -8,6 +10,29 @@ from modules.upscaler import Upscaler, UpscalerLanczos, UpscalerNearest, Upscale
 from modules.paths import script_path, models_path
 
 
+def load_file_from_url(
+    url: str,
+    *,
+    model_dir: str,
+    progress: bool = True,
+    file_name: str | None = None,
+) -> str:
+    """Download a file from `url` into `model_dir`, using the file present if possible.
+
+    Returns the path to the downloaded file.
+    """
+    os.makedirs(model_dir, exist_ok=True)
+    if not file_name:
+        parts = urlparse(url)
+        file_name = os.path.basename(parts.path)
+    cached_file = os.path.abspath(os.path.join(model_dir, file_name))
+    if not os.path.exists(cached_file):
+        print(f'Downloading: "{url}" to {cached_file}\n')
+        from torch.hub import download_url_to_file
+        download_url_to_file(url, cached_file, progress=progress)
+    return cached_file
+
+
 def load_models(model_path: str, model_url: str = None, command_path: str = None, ext_filter=None, download_name=None, ext_blacklist=None) -> list:
     """
     A one-and done loader to try finding the desired models in specified directories.
@@ -46,9 +71,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
 
         if model_url is not None and len(output) == 0:
             if download_name is not None:
-                from basicsr.utils.download_util import load_file_from_url
+                output.append(load_file_from_url(model_url, model_dir=places[0], file_name=download_name))
-                dl = load_file_from_url(model_url, places[0], True, download_name)
-                output.append(dl)
             else:
                 output.append(model_url)
 
@@ -59,7 +82,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
 
 
 def friendly_name(file: str):
-    if "http" in file:
+    if file.startswith("http"):
         file = urlparse(file).path
 
     file = os.path.basename(file)
@@ -95,8 +118,7 @@ def cleanup_models():
 
 def move_files(src_path: str, dest_path: str, ext_filter: str = None):
     try:
-        if not os.path.exists(dest_path):
+        os.makedirs(dest_path, exist_ok=True)
-            os.makedirs(dest_path)
         if os.path.exists(src_path):
             for file in os.listdir(src_path):
                 fullpath = os.path.join(src_path, file)

modules/options.py

@@ -0,0 +1,308 @@
+import json
+import sys
+from dataclasses import dataclass
+
+import gradio as gr
+
+from modules import errors
+from modules.shared_cmd_options import cmd_opts
+
+
+class OptionInfo:
+    def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None, restrict_api=False, category_id=None):
+        self.default = default
+        self.label = label
+        self.component = component
+        self.component_args = component_args
+        self.onchange = onchange
+        self.section = section
+        self.category_id = category_id
+        self.refresh = refresh
+        self.do_not_save = False
+
+        self.comment_before = comment_before
+        """HTML text that will be added after label in UI"""
+
+        self.comment_after = comment_after
+        """HTML text that will be added before label in UI"""
+
+        self.infotext = infotext
+
+        self.restrict_api = restrict_api
+        """If True, the setting will not be accessible via API"""
+
+    def link(self, label, url):
+        self.comment_before += f"[<a href='{url}' target='_blank'>{label}</a>]"
+        return self
+
+    def js(self, label, js_func):
+        self.comment_before += f"[<a onclick='{js_func}(); return false'>{label}</a>]"
+        return self
+
+    def info(self, info):
+        self.comment_after += f"<span class='info'>({info})</span>"
+        return self
+
+    def html(self, html):
+        self.comment_after += html
+        return self
+
+    def needs_restart(self):
+        self.comment_after += " <span class='info'>(requires restart)</span>"
+        return self
+
+    def needs_reload_ui(self):
+        self.comment_after += " <span class='info'>(requires Reload UI)</span>"
+        return self
+
+
+class OptionHTML(OptionInfo):
+    def __init__(self, text):
+        super().__init__(str(text).strip(), label='', component=lambda **kwargs: gr.HTML(elem_classes="settings-info", **kwargs))
+
+        self.do_not_save = True
+
+
+def options_section(section_identifier, options_dict):
+    for v in options_dict.values():
+        if len(section_identifier) == 2:
+            v.section = section_identifier
+        elif len(section_identifier) == 3:
+            v.section = section_identifier[0:2]
+            v.category_id = section_identifier[2]
+
+    return options_dict
+
+
+options_builtin_fields = {"data_labels", "data", "restricted_opts", "typemap"}
+
+
+class Options:
+    typemap = {int: float}
+
+    def __init__(self, data_labels: dict[str, OptionInfo], restricted_opts):
+        self.data_labels = data_labels
+        self.data = {k: v.default for k, v in self.data_labels.items() if not v.do_not_save}
+        self.restricted_opts = restricted_opts
+
+    def __setattr__(self, key, value):
+        if key in options_builtin_fields:
+            return super(Options, self).__setattr__(key, value)
+
+        if self.data is not None:
+            if key in self.data or key in self.data_labels:
+                assert not cmd_opts.freeze_settings, "changing settings is disabled"
+
+                info = self.data_labels.get(key, None)
+                if info.do_not_save:
+                    return
+
+                comp_args = info.component_args if info else None
+                if isinstance(comp_args, dict) and comp_args.get('visible', True) is False:
+                    raise RuntimeError(f"not possible to set {key} because it is restricted")
+
+                if cmd_opts.hide_ui_dir_config and key in self.restricted_opts:
+                    raise RuntimeError(f"not possible to set {key} because it is restricted")
+
+                self.data[key] = value
+                return
+
+        return super(Options, self).__setattr__(key, value)
+
+    def __getattr__(self, item):
+        if item in options_builtin_fields:
+            return super(Options, self).__getattribute__(item)
+
+        if self.data is not None:
+            if item in self.data:
+                return self.data[item]
+
+        if item in self.data_labels:
+            return self.data_labels[item].default
+
+        return super(Options, self).__getattribute__(item)
+
+    def set(self, key, value, is_api=False, run_callbacks=True):
+        """sets an option and calls its onchange callback, returning True if the option changed and False otherwise"""
+
+        oldval = self.data.get(key, None)
+        if oldval == value:
+            return False
+
+        option = self.data_labels[key]
+        if option.do_not_save:
+            return False
+
+        if is_api and option.restrict_api:
+            return False
+
+        try:
+            setattr(self, key, value)
+        except RuntimeError:
+            return False
+
+        if run_callbacks and option.onchange is not None:
+            try:
+                option.onchange()
+            except Exception as e:
+                errors.display(e, f"changing setting {key} to {value}")
+                setattr(self, key, oldval)
+                return False
+
+        return True
+
+    def get_default(self, key):
+        """returns the default value for the key"""
+
+        data_label = self.data_labels.get(key)
+        if data_label is None:
+            return None
+
+        return data_label.default
+
+    def save(self, filename):
+        assert not cmd_opts.freeze_settings, "saving settings is disabled"
+
+        with open(filename, "w", encoding="utf8") as file:
+            json.dump(self.data, file, indent=4, ensure_ascii=False)
+
+    def same_type(self, x, y):
+        if x is None or y is None:
+            return True
+
+        type_x = self.typemap.get(type(x), type(x))
+        type_y = self.typemap.get(type(y), type(y))
+
+        return type_x == type_y
+
+    def load(self, filename):
+        with open(filename, "r", encoding="utf8") as file:
+            self.data = json.load(file)
+
+        # 1.6.0 VAE defaults
+        if self.data.get('sd_vae_as_default') is not None and self.data.get('sd_vae_overrides_per_model_preferences') is None:
+            self.data['sd_vae_overrides_per_model_preferences'] = not self.data.get('sd_vae_as_default')
+
+        # 1.1.1 quicksettings list migration
+        if self.data.get('quicksettings') is not None and self.data.get('quicksettings_list') is None:
+            self.data['quicksettings_list'] = [i.strip() for i in self.data.get('quicksettings').split(',')]
+
+        # 1.4.0 ui_reorder
+        if isinstance(self.data.get('ui_reorder'), str) and self.data.get('ui_reorder') and "ui_reorder_list" not in self.data:
+            self.data['ui_reorder_list'] = [i.strip() for i in self.data.get('ui_reorder').split(',')]
+
+        bad_settings = 0
+        for k, v in self.data.items():
+            info = self.data_labels.get(k, None)
+            if info is not None and not self.same_type(info.default, v):
+                print(f"Warning: bad setting value: {k}: {v} ({type(v).__name__}; expected {type(info.default).__name__})", file=sys.stderr)
+                bad_settings += 1
+
+        if bad_settings > 0:
+            print(f"The program is likely to not work with bad settings.\nSettings file: {filename}\nEither fix the file, or delete it and restart.", file=sys.stderr)
+
+    def onchange(self, key, func, call=True):
+        item = self.data_labels.get(key)
+        item.onchange = func
+
+        if call:
+            func()
+
+    def dumpjson(self):
+        d = {k: self.data.get(k, v.default) for k, v in self.data_labels.items()}
+        d["_comments_before"] = {k: v.comment_before for k, v in self.data_labels.items() if v.comment_before is not None}
+        d["_comments_after"] = {k: v.comment_after for k, v in self.data_labels.items() if v.comment_after is not None}
+
+        item_categories = {}
+        for item in self.data_labels.values():
+            category = categories.mapping.get(item.category_id)
+            category = "Uncategorized" if category is None else category.label
+            if category not in item_categories:
+                item_categories[category] = item.section[1]
+
+        # _categories is a list of pairs: [section, category]. Each section (a setting page) will get a special heading above it with the category as text.
+        d["_categories"] = [[v, k] for k, v in item_categories.items()] + [["Defaults", "Other"]]
+
+        return json.dumps(d)
+
+    def add_option(self, key, info):
+        self.data_labels[key] = info
+        if key not in self.data and not info.do_not_save:
+            self.data[key] = info.default
+
+    def reorder(self):
+        """Reorder settings so that:
+            - all items related to section always go together
+            - all sections belonging to a category go together
+            - sections inside a category are ordered alphabetically
+            - categories are ordered by creation order
+
+        Category is a superset of sections: for category "postprocessing" there could be multiple sections: "face restoration", "upscaling".
+
+        This function also changes items' category_id so that all items belonging to a section have the same category_id.
+        """
+
+        category_ids = {}
+        section_categories = {}
+
+        settings_items = self.data_labels.items()
+        for _, item in settings_items:
+            if item.section not in section_categories:
+                section_categories[item.section] = item.category_id
+
+        for _, item in settings_items:
+            item.category_id = section_categories.get(item.section)
+
+        for category_id in categories.mapping:
+            if category_id not in category_ids:
+                category_ids[category_id] = len(category_ids)
+
+        def sort_key(x):
+            item: OptionInfo = x[1]
+            category_order = category_ids.get(item.category_id, len(category_ids))
+            section_order = item.section[1]
+
+            return category_order, section_order
+
+        self.data_labels = dict(sorted(settings_items, key=sort_key))
+
+    def cast_value(self, key, value):
+        """casts an arbitrary to the same type as this setting's value with key
+        Example: cast_value("eta_noise_seed_delta", "12") -> returns 12 (an int rather than str)
+        """
+
+        if value is None:
+            return None
+
+        default_value = self.data_labels[key].default
+        if default_value is None:
+            default_value = getattr(self, key, None)
+        if default_value is None:
+            return None
+
+        expected_type = type(default_value)
+        if expected_type == bool and value == "False":
+            value = False
+        else:
+            value = expected_type(value)
+
+        return value
+
+
+@dataclass
+class OptionsCategory:
+    id: str
+    label: str
+
+class OptionsCategories:
+    def __init__(self):
+        self.mapping = {}
+
+    def register_category(self, category_id, label):
+        if category_id in self.mapping:
+            return category_id
+
+        self.mapping[category_id] = OptionsCategory(category_id, label)
+
+
+categories = OptionsCategories()

modules/patches.py

@@ -0,0 +1,64 @@
+from collections import defaultdict
+
+
+def patch(key, obj, field, replacement):
+    """Replaces a function in a module or a class.
+
+    Also stores the original function in this module, possible to be retrieved via original(key, obj, field).
+    If the function is already replaced by this caller (key), an exception is raised -- use undo() before that.
+
+    Arguments:
+        key: identifying information for who is doing the replacement. You can use __name__.
+        obj: the module or the class
+        field: name of the function as a string
+        replacement: the new function
+
+    Returns:
+        the original function
+    """
+
+    patch_key = (obj, field)
+    if patch_key in originals[key]:
+        raise RuntimeError(f"patch for {field} is already applied")
+
+    original_func = getattr(obj, field)
+    originals[key][patch_key] = original_func
+
+    setattr(obj, field, replacement)
+
+    return original_func
+
+
+def undo(key, obj, field):
+    """Undoes the peplacement by the patch().
+
+    If the function is not replaced, raises an exception.
+
+    Arguments:
+        key: identifying information for who is doing the replacement. You can use __name__.
+        obj: the module or the class
+        field: name of the function as a string
+
+    Returns:
+        Always None
+    """
+
+    patch_key = (obj, field)
+
+    if patch_key not in originals[key]:
+        raise RuntimeError(f"there is no patch for {field} to undo")
+
+    original_func = originals[key].pop(patch_key)
+    setattr(obj, field, original_func)
+
+    return None
+
+
+def original(key, obj, field):
+    """Returns the original function for the patch created by the patch() function"""
+    patch_key = (obj, field)
+
+    return originals[key].get(patch_key, None)
+
+
+originals = defaultdict(dict)

modules/paths.py

@@ -1,10 +1,25 @@
 import os
 import sys
-from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir  # noqa: F401
+from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, cwd  # noqa: F401
 
 import modules.safe  # noqa: F401
 
 
+def mute_sdxl_imports():
+    """create fake modules that SDXL wants to import but doesn't actually use for our purposes"""
+
+    class Dummy:
+        pass
+
+    module = Dummy()
+    module.LPIPS = None
+    sys.modules['taming.modules.losses.lpips'] = module
+
+    module = Dummy()
+    module.StableDataModuleFromConfig = None
+    sys.modules['sgm.data'] = module
+
+
 # data_path = cmd_opts_pre.data
 sys.path.insert(0, script_path)
 
@@ -18,8 +33,11 @@ for possible_sd_path in possible_sd_paths:
 
 assert sd_path is not None, f"Couldn't find Stable Diffusion in any of: {possible_sd_paths}"
 
+mute_sdxl_imports()
+
 path_dirs = [
     (sd_path, 'ldm', 'Stable Diffusion', []),
+    (os.path.join(sd_path, '../generative-models'), 'sgm', 'Stable Diffusion XL', ["sgm"]),
     (os.path.join(sd_path, '../CodeFormer'), 'inference_codeformer.py', 'CodeFormer', []),
     (os.path.join(sd_path, '../BLIP'), 'models/blip.py', 'BLIP', []),
     (os.path.join(sd_path, '../k-diffusion'), 'k_diffusion/sampling.py', 'k_diffusion', ["atstart"]),
@@ -35,20 +53,13 @@ for d, must_exist, what, options in path_dirs:
         d = os.path.abspath(d)
         if "atstart" in options:
             sys.path.insert(0, d)
+        elif "sgm" in options:
+            # Stable Diffusion XL repo has scripts dir with __init__.py in it which ruins every extension's scripts dir, so we
+            # import sgm and remove it from sys.path so that when a script imports scripts.something, it doesbn't use sgm's scripts dir.
+
+            sys.path.insert(0, d)
+            import sgm  # noqa: F401
+            sys.path.pop(0)
         else:
             sys.path.append(d)
         paths[what] = d
-
-
-class Prioritize:
-    def __init__(self, name):
-        self.name = name
-        self.path = None
-
-    def __enter__(self):
-        self.path = sys.path.copy()
-        sys.path = [paths[self.name]] + sys.path
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        sys.path = self.path
-        self.path = None

modules/paths_internal.py

@@ -8,6 +8,7 @@ import shlex
 commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
 sys.argv += shlex.split(commandline_args)
 
+cwd = os.getcwd()
 modules_path = os.path.dirname(os.path.realpath(__file__))
 script_path = os.path.dirname(modules_path)
 

modules/postprocessing.py

@@ -9,13 +9,11 @@ from modules.shared import opts
 def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True):
     devices.torch_gc()
 
-    shared.state.begin()
+    shared.state.begin(job="extras")
-    shared.state.job = 'extras'
 
-    image_data = []
-    image_names = []
     outputs = []
 
+    def get_images(extras_mode, image, image_folder, input_dir):
         if extras_mode == 1:
             for img in image_folder:
                 if isinstance(img, Image.Image):
@@ -24,8 +22,7 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
                 else:
                     image = Image.open(os.path.abspath(img.name))
                     fn = os.path.splitext(img.orig_name)[0]
-            image_data.append(image)
+                yield image, fn
-            image_names.append(fn)
         elif extras_mode == 2:
             assert not shared.cmd_opts.hide_ui_dir_config, '--hide-ui-dir-config option must be disabled'
             assert input_dir, 'input directory not selected'
@@ -36,13 +33,10 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
                     image = Image.open(filename)
                 except Exception:
                     continue
-            image_data.append(image)
+                yield image, filename
-            image_names.append(filename)
         else:
             assert image, 'image not selected'
-
+            yield image, None
-        image_data.append(image)
-        image_names.append(None)
 
     if extras_mode == 2 and output_dir != '':
         outpath = output_dir
@@ -51,12 +45,16 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
 
     infotext = ''
 
-    for image, name in zip(image_data, image_names):
+    for image_data, name in get_images(extras_mode, image, image_folder, input_dir):
+        image_data: Image.Image
+
         shared.state.textinfo = name
 
-        existing_pnginfo = image.info or {}
+        parameters, existing_pnginfo = images.read_info_from_image(image_data)
+        if parameters:
+            existing_pnginfo["parameters"] = parameters
 
-        pp = scripts_postprocessing.PostprocessedImage(image.convert("RGB"))
+        pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB"))
 
         scripts.scripts_postproc.run(pp, args)
 
@@ -77,8 +75,10 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
         if extras_mode != 2 or show_extras_results:
             outputs.append(pp.image)
 
-    devices.torch_gc()
+        image_data.close()
 
+    devices.torch_gc()
+    shared.state.end()
     return outputs, ui_common.plaintext_to_html(infotext), ''
 
 

modules/processing_scripts/refiner.py

@@ -0,0 +1,49 @@
+import gradio as gr
+
+from modules import scripts, sd_models
+from modules.ui_common import create_refresh_button
+from modules.ui_components import InputAccordion
+
+
+class ScriptRefiner(scripts.ScriptBuiltinUI):
+    section = "accordions"
+    create_group = False
+
+    def __init__(self):
+        pass
+
+    def title(self):
+        return "Refiner"
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def ui(self, is_img2img):
+        with InputAccordion(False, label="Refiner", elem_id=self.elem_id("enable")) as enable_refiner:
+            with gr.Row():
+                refiner_checkpoint = gr.Dropdown(label='Checkpoint', elem_id=self.elem_id("checkpoint"), choices=sd_models.checkpoint_tiles(), value='', tooltip="switch to another model in the middle of generation")
+                create_refresh_button(refiner_checkpoint, sd_models.list_models, lambda: {"choices": sd_models.checkpoint_tiles()}, self.elem_id("checkpoint_refresh"))
+
+                refiner_switch_at = gr.Slider(value=0.8, label="Switch at", minimum=0.01, maximum=1.0, step=0.01, elem_id=self.elem_id("switch_at"), tooltip="fraction of sampling steps when the switch to refiner model should happen; 1=never, 0.5=switch in the middle of generation")
+
+        def lookup_checkpoint(title):
+            info = sd_models.get_closet_checkpoint_match(title)
+            return None if info is None else info.title
+
+        self.infotext_fields = [
+            (enable_refiner, lambda d: 'Refiner' in d),
+            (refiner_checkpoint, lambda d: lookup_checkpoint(d.get('Refiner'))),
+            (refiner_switch_at, 'Refiner switch at'),
+        ]
+
+        return enable_refiner, refiner_checkpoint, refiner_switch_at
+
+    def setup(self, p, enable_refiner, refiner_checkpoint, refiner_switch_at):
+        # the actual implementation is in sd_samplers_common.py, apply_refiner
+
+        if not enable_refiner or refiner_checkpoint in (None, "", "None"):
+            p.refiner_checkpoint = None
+            p.refiner_switch_at = None
+        else:
+            p.refiner_checkpoint = refiner_checkpoint
+            p.refiner_switch_at = refiner_switch_at

modules/processing_scripts/seed.py

@@ -0,0 +1,111 @@
+import json
+
+import gradio as gr
+
+from modules import scripts, ui, errors
+from modules.shared import cmd_opts
+from modules.ui_components import ToolButton
+
+
+class ScriptSeed(scripts.ScriptBuiltinUI):
+    section = "seed"
+    create_group = False
+
+    def __init__(self):
+        self.seed = None
+        self.reuse_seed = None
+        self.reuse_subseed = None
+
+    def title(self):
+        return "Seed"
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def ui(self, is_img2img):
+        with gr.Row(elem_id=self.elem_id("seed_row")):
+            if cmd_opts.use_textbox_seed:
+                self.seed = gr.Textbox(label='Seed', value="", elem_id=self.elem_id("seed"), min_width=100)
+            else:
+                self.seed = gr.Number(label='Seed', value=-1, elem_id=self.elem_id("seed"), min_width=100, precision=0)
+
+            random_seed = ToolButton(ui.random_symbol, elem_id=self.elem_id("random_seed"), tooltip="Set seed to -1, which will cause a new random number to be used every time")
+            reuse_seed = ToolButton(ui.reuse_symbol, elem_id=self.elem_id("reuse_seed"), tooltip="Reuse seed from last generation, mostly useful if it was randomized")
+
+            seed_checkbox = gr.Checkbox(label='Extra', elem_id=self.elem_id("subseed_show"), value=False)
+
+        with gr.Group(visible=False, elem_id=self.elem_id("seed_extras")) as seed_extras:
+            with gr.Row(elem_id=self.elem_id("subseed_row")):
+                subseed = gr.Number(label='Variation seed', value=-1, elem_id=self.elem_id("subseed"), precision=0)
+                random_subseed = ToolButton(ui.random_symbol, elem_id=self.elem_id("random_subseed"))
+                reuse_subseed = ToolButton(ui.reuse_symbol, elem_id=self.elem_id("reuse_subseed"))
+                subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=self.elem_id("subseed_strength"))
+
+            with gr.Row(elem_id=self.elem_id("seed_resize_from_row")):
+                seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0, elem_id=self.elem_id("seed_resize_from_w"))
+                seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0, elem_id=self.elem_id("seed_resize_from_h"))
+
+        random_seed.click(fn=None, _js="function(){setRandomSeed('" + self.elem_id("seed") + "')}", show_progress=False, inputs=[], outputs=[])
+        random_subseed.click(fn=None, _js="function(){setRandomSeed('" + self.elem_id("subseed") + "')}", show_progress=False, inputs=[], outputs=[])
+
+        seed_checkbox.change(lambda x: gr.update(visible=x), show_progress=False, inputs=[seed_checkbox], outputs=[seed_extras])
+
+        self.infotext_fields = [
+            (self.seed, "Seed"),
+            (seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d),
+            (subseed, "Variation seed"),
+            (subseed_strength, "Variation seed strength"),
+            (seed_resize_from_w, "Seed resize from-1"),
+            (seed_resize_from_h, "Seed resize from-2"),
+        ]
+
+        self.on_after_component(lambda x: connect_reuse_seed(self.seed, reuse_seed, x.component, False), elem_id=f'generation_info_{self.tabname}')
+        self.on_after_component(lambda x: connect_reuse_seed(subseed, reuse_subseed, x.component, True), elem_id=f'generation_info_{self.tabname}')
+
+        return self.seed, seed_checkbox, subseed, subseed_strength, seed_resize_from_w, seed_resize_from_h
+
+    def setup(self, p, seed, seed_checkbox, subseed, subseed_strength, seed_resize_from_w, seed_resize_from_h):
+        p.seed = seed
+
+        if seed_checkbox and subseed_strength > 0:
+            p.subseed = subseed
+            p.subseed_strength = subseed_strength
+
+        if seed_checkbox and seed_resize_from_w > 0 and seed_resize_from_h > 0:
+            p.seed_resize_from_w = seed_resize_from_w
+            p.seed_resize_from_h = seed_resize_from_h
+
+
+
+def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info: gr.Textbox, is_subseed):
+    """ Connects a 'reuse (sub)seed' button's click event so that it copies last used
+        (sub)seed value from generation info the to the seed field. If copying subseed and subseed strength
+        was 0, i.e. no variation seed was used, it copies the normal seed value instead."""
+
+    def copy_seed(gen_info_string: str, index):
+        res = -1
+
+        try:
+            gen_info = json.loads(gen_info_string)
+            index -= gen_info.get('index_of_first_image', 0)
+
+            if is_subseed and gen_info.get('subseed_strength', 0) > 0:
+                all_subseeds = gen_info.get('all_subseeds', [-1])
+                res = all_subseeds[index if 0 <= index < len(all_subseeds) else 0]
+            else:
+                all_seeds = gen_info.get('all_seeds', [-1])
+                res = all_seeds[index if 0 <= index < len(all_seeds) else 0]
+
+        except json.decoder.JSONDecodeError:
+            if gen_info_string:
+                errors.report(f"Error parsing JSON generation info: {gen_info_string}")
+
+        return [res, gr.update()]
+
+    reuse_seed.click(
+        fn=copy_seed,
+        _js="(x, y) => [x, selected_gallery_index()]",
+        show_progress=False,
+        inputs=[generation_info, seed],
+        outputs=[seed, seed]
+    )

modules/progress.py

@@ -48,6 +48,7 @@ def add_task_to_queue(id_job):
 class ProgressRequest(BaseModel):
     id_task: str = Field(default=None, title="Task ID", description="id of the task to get progress for")
     id_live_preview: int = Field(default=-1, title="Live preview image ID", description="id of last received last preview image")
+    live_preview: bool = Field(default=True, title="Include live preview", description="boolean flag indicating whether to include the live preview image")
 
 
 class ProgressResponse(BaseModel):
@@ -71,7 +72,12 @@ def progressapi(req: ProgressRequest):
     completed = req.id_task in finished_tasks
 
     if not active:
-        return ProgressResponse(active=active, queued=queued, completed=completed, id_live_preview=-1, textinfo="In queue..." if queued else "Waiting...")
+        textinfo = "Waiting..."
+        if queued:
+            sorted_queued = sorted(pending_tasks.keys(), key=lambda x: pending_tasks[x])
+            queue_index = sorted_queued.index(req.id_task)
+            textinfo = "In queue: {}/{}".format(queue_index + 1, len(sorted_queued))
+        return ProgressResponse(active=active, queued=queued, completed=completed, id_live_preview=-1, textinfo=textinfo)
 
     progress = 0
 
@@ -89,9 +95,12 @@ def progressapi(req: ProgressRequest):
     predicted_duration = elapsed_since_start / progress if progress > 0 else None
     eta = predicted_duration - elapsed_since_start if predicted_duration is not None else None
 
+    live_preview = None
     id_live_preview = req.id_live_preview
+
+    if opts.live_previews_enable and req.live_preview:
         shared.state.set_current_image()
-    if opts.live_previews_enable and shared.state.id_live_preview != req.id_live_preview:
+        if shared.state.id_live_preview != req.id_live_preview:
             image = shared.state.current_image
             if image is not None:
                 buffered = io.BytesIO()
@@ -110,10 +119,6 @@ def progressapi(req: ProgressRequest):
                 base64_image = base64.b64encode(buffered.getvalue()).decode('ascii')
                 live_preview = f"data:image/{opts.live_previews_image_format};base64,{base64_image}"
                 id_live_preview = shared.state.id_live_preview
-        else:
-            live_preview = None
-    else:
-        live_preview = None
 
     return ProgressResponse(active=active, queued=queued, completed=completed, progress=progress, eta=eta, live_preview=live_preview, id_live_preview=id_live_preview, textinfo=shared.state.textinfo)
 

modules/prompt_parser.py

@@ -1,9 +1,10 @@
+from __future__ import annotations
+
 import re
 from collections import namedtuple
-from typing import List
 import lark
 
-# a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][ in background:0.25] [shoddy:masterful:0.5]"
+# a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][: in background:0.25] [shoddy:masterful:0.5]"
 # will be represented with prompt_schedule like this (assuming steps=100):
 # [25, 'fantasy landscape with a mountain and an oak in foreground shoddy']
 # [50, 'fantasy landscape with a lake and an oak in foreground in background shoddy']
@@ -17,14 +18,14 @@ prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)*
 !emphasized: "(" prompt ")"
         | "(" prompt ":" prompt ")"
         | "[" prompt "]"
-scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"
+scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER [WHITESPACE] "]"
-alternate: "[" prompt ("|" prompt)+ "]"
+alternate: "[" prompt ("|" [prompt])+ "]"
 WHITESPACE: /\s+/
 plain: /([^\\\[\]():|]|\\.)+/
 %import common.SIGNED_NUMBER -> NUMBER
 """)
 
-def get_learned_conditioning_prompt_schedules(prompts, steps):
+def get_learned_conditioning_prompt_schedules(prompts, base_steps, hires_steps=None, use_old_scheduling=False):
     """
     >>> g = lambda p: get_learned_conditioning_prompt_schedules([p], 10)[0]
     >>> g("test")
@@ -51,18 +52,43 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
     [[3, '((a][:b:c '], [10, '((a][:b:c d']]
     >>> g("[a|(b:1.1)]")
     [[1, 'a'], [2, '(b:1.1)'], [3, 'a'], [4, '(b:1.1)'], [5, 'a'], [6, '(b:1.1)'], [7, 'a'], [8, '(b:1.1)'], [9, 'a'], [10, '(b:1.1)']]
+    >>> g("[fe|]male")
+    [[1, 'female'], [2, 'male'], [3, 'female'], [4, 'male'], [5, 'female'], [6, 'male'], [7, 'female'], [8, 'male'], [9, 'female'], [10, 'male']]
+    >>> g("[fe|||]male")
+    [[1, 'female'], [2, 'male'], [3, 'male'], [4, 'male'], [5, 'female'], [6, 'male'], [7, 'male'], [8, 'male'], [9, 'female'], [10, 'male']]
+    >>> g = lambda p: get_learned_conditioning_prompt_schedules([p], 10, 10)[0]
+    >>> g("a [b:.5] c")
+    [[10, 'a b c']]
+    >>> g("a [b:1.5] c")
+    [[5, 'a  c'], [10, 'a b c']]
     """
 
+    if hires_steps is None or use_old_scheduling:
+        int_offset = 0
+        flt_offset = 0
+        steps = base_steps
+    else:
+        int_offset = base_steps
+        flt_offset = 1.0
+        steps = hires_steps
+
     def collect_steps(steps, tree):
         res = [steps]
 
         class CollectSteps(lark.Visitor):
             def scheduled(self, tree):
-                tree.children[-1] = float(tree.children[-1])
+                s = tree.children[-2]
-                if tree.children[-1] < 1:
+                v = float(s)
-                    tree.children[-1] *= steps
+                if use_old_scheduling:
-                tree.children[-1] = min(steps, int(tree.children[-1]))
+                    v = v*steps if v<1 else v
-                res.append(tree.children[-1])
+                else:
+                    if "." in s:
+                        v = (v - flt_offset) * steps
+                    else:
+                        v = (v - int_offset)
+                tree.children[-2] = min(steps, int(v))
+                if tree.children[-2] >= 1:
+                    res.append(tree.children[-2])
 
             def alternate(self, tree):
                 res.extend(range(1, steps+1))
@@ -73,13 +99,14 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
     def at_step(step, tree):
         class AtStep(lark.Transformer):
             def scheduled(self, args):
-                before, after, _, when = args
+                before, after, _, when, _ = args
                 yield before or () if step <= when else after
             def alternate(self, args):
-                yield next(args[(step - 1)%len(args)])
+                args = ["" if not arg else arg for arg in args]
+                yield args[(step - 1) % len(args)]
             def start(self, args):
                 def flatten(x):
-                    if type(x) == str:
+                    if isinstance(x, str):
                         yield x
                     else:
                         for gen in x:
@@ -109,7 +136,25 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
 ScheduledPromptConditioning = namedtuple("ScheduledPromptConditioning", ["end_at_step", "cond"])
 
 
-def get_learned_conditioning(model, prompts, steps):
+class SdConditioning(list):
+    """
+    A list with prompts for stable diffusion's conditioner model.
+    Can also specify width and height of created image - SDXL needs it.
+    """
+    def __init__(self, prompts, is_negative_prompt=False, width=None, height=None, copy_from=None):
+        super().__init__()
+        self.extend(prompts)
+
+        if copy_from is None:
+            copy_from = prompts
+
+        self.is_negative_prompt = is_negative_prompt or getattr(copy_from, 'is_negative_prompt', False)
+        self.width = width or getattr(copy_from, 'width', None)
+        self.height = height or getattr(copy_from, 'height', None)
+
+
+
+def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps, hires_steps=None, use_old_scheduling=False):
     """converts a list of prompts into a list of prompt schedules - each schedule is a list of ScheduledPromptConditioning, specifying the comdition (cond),
     and the sampling step at which this condition is to be replaced by the next one.
 
@@ -129,7 +174,7 @@ def get_learned_conditioning(model, prompts, steps):
     """
     res = []
 
-    prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps)
+    prompt_schedules = get_learned_conditioning_prompt_schedules(prompts, steps, hires_steps, use_old_scheduling)
     cache = {}
 
     for prompt, prompt_schedule in zip(prompts, prompt_schedules):
@@ -139,12 +184,17 @@ def get_learned_conditioning(model, prompts, steps):
             res.append(cached)
             continue
 
-        texts = [x[1] for x in prompt_schedule]
+        texts = SdConditioning([x[1] for x in prompt_schedule], copy_from=prompts)
         conds = model.get_learned_conditioning(texts)
 
         cond_schedule = []
         for i, (end_at_step, _) in enumerate(prompt_schedule):
-            cond_schedule.append(ScheduledPromptConditioning(end_at_step, conds[i]))
+            if isinstance(conds, dict):
+                cond = {k: v[i] for k, v in conds.items()}
+            else:
+                cond = conds[i]
+
+            cond_schedule.append(ScheduledPromptConditioning(end_at_step, cond))
 
         cache[prompt] = cond_schedule
         res.append(cond_schedule)
@@ -153,13 +203,15 @@ def get_learned_conditioning(model, prompts, steps):
 
 
 re_AND = re.compile(r"\bAND\b")
-re_weight = re.compile(r"^(.*?)(?:\s*:\s*([-+]?(?:\d+\.?|\d*\.\d+)))?\s*$")
+re_weight = re.compile(r"^((?:\s|.)*?)(?:\s*:\s*([-+]?(?:\d+\.?|\d*\.\d+)))?\s*$")
 
-def get_multicond_prompt_list(prompts):
+
+def get_multicond_prompt_list(prompts: SdConditioning | list[str]):
     res_indexes = []
 
-    prompt_flat_list = []
     prompt_indexes = {}
+    prompt_flat_list = SdConditioning(prompts)
+    prompt_flat_list.clear()
 
     for prompt in prompts:
         subprompts = re_AND.split(prompt)
@@ -187,16 +239,17 @@ def get_multicond_prompt_list(prompts):
 
 class ComposableScheduledPromptConditioning:
     def __init__(self, schedules, weight=1.0):
-        self.schedules: List[ScheduledPromptConditioning] = schedules
+        self.schedules: list[ScheduledPromptConditioning] = schedules
         self.weight: float = weight
 
 
 class MulticondLearnedConditioning:
     def __init__(self, shape, batch):
         self.shape: tuple = shape  # the shape field is needed to send this object to DDIM/PLMS
-        self.batch: List[List[ComposableScheduledPromptConditioning]] = batch
+        self.batch: list[list[ComposableScheduledPromptConditioning]] = batch
 
-def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearnedConditioning:
+
+def get_multicond_learned_conditioning(model, prompts, steps, hires_steps=None, use_old_scheduling=False) -> MulticondLearnedConditioning:
     """same as get_learned_conditioning, but returns a list of ScheduledPromptConditioning along with the weight objects for each prompt.
     For each prompt, the list is obtained by splitting the prompt using the AND separator.
 
@@ -205,7 +258,7 @@ def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearne
 
     res_indexes, prompt_flat_list, prompt_indexes = get_multicond_prompt_list(prompts)
 
-    learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps)
+    learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps, hires_steps, use_old_scheduling)
 
     res = []
     for indexes in res_indexes:
@@ -214,20 +267,57 @@ def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearne
     return MulticondLearnedConditioning(shape=(len(prompts),), batch=res)
 
 
-def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_step):
+class DictWithShape(dict):
+    def __init__(self, x, shape):
+        super().__init__()
+        self.update(x)
+
+    @property
+    def shape(self):
+        return self["crossattn"].shape
+
+
+def reconstruct_cond_batch(c: list[list[ScheduledPromptConditioning]], current_step):
     param = c[0][0].cond
+    is_dict = isinstance(param, dict)
+
+    if is_dict:
+        dict_cond = param
+        res = {k: torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype) for k, param in dict_cond.items()}
+        res = DictWithShape(res, (len(c),) + dict_cond['crossattn'].shape)
+    else:
         res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype)
+
     for i, cond_schedule in enumerate(c):
         target_index = 0
         for current, entry in enumerate(cond_schedule):
             if current_step <= entry.end_at_step:
                 target_index = current
                 break
+
+        if is_dict:
+            for k, param in cond_schedule[target_index].cond.items():
+                res[k][i] = param
+        else:
             res[i] = cond_schedule[target_index].cond
 
     return res
 
 
+def stack_conds(tensors):
+    # if prompts have wildly different lengths above the limit we'll get tensors of different shapes
+    # and won't be able to torch.stack them. So this fixes that.
+    token_count = max([x.shape[0] for x in tensors])
+    for i in range(len(tensors)):
+        if tensors[i].shape[0] != token_count:
+            last_vector = tensors[i][-1:]
+            last_vector_repeated = last_vector.repeat([token_count - tensors[i].shape[0], 1])
+            tensors[i] = torch.vstack([tensors[i], last_vector_repeated])
+
+    return torch.stack(tensors)
+
+
+
 def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step):
     param = c.batch[0][0].schedules[0].cond
 
@@ -249,16 +339,14 @@ def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step):
 
         conds_list.append(conds_for_batch)
 
-    # if prompts have wildly different lengths above the limit we'll get tensors fo different shapes
+    if isinstance(tensors[0], dict):
-    # and won't be able to torch.stack them. So this fixes that.
+        keys = list(tensors[0].keys())
-    token_count = max([x.shape[0] for x in tensors])
+        stacked = {k: stack_conds([x[k] for x in tensors]) for k in keys}
-    for i in range(len(tensors)):
+        stacked = DictWithShape(stacked, stacked['crossattn'].shape)
-        if tensors[i].shape[0] != token_count:
+    else:
-            last_vector = tensors[i][-1:]
+        stacked = stack_conds(tensors).to(device=param.device, dtype=param.dtype)
-            last_vector_repeated = last_vector.repeat([token_count - tensors[i].shape[0], 1])
-            tensors[i] = torch.vstack([tensors[i], last_vector_repeated])
 
-    return conds_list, torch.stack(tensors).to(device=param.device, dtype=param.dtype)
+    return conds_list, stacked
 
 
 re_attention = re.compile(r"""
@@ -270,7 +358,7 @@ re_attention = re.compile(r"""
 \\|
 \(|
 \[|
-:([+-]?[.\d]+)\)|
+:\s*([+-]?[.\d]+)\s*\)|
 \)|
 ]|
 [^\\()\[\]:]+|

modules/realesrgan_model.py

@@ -2,7 +2,6 @@ import os
 
 import numpy as np
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 from realesrgan import RealESRGANer
 
 from modules.upscaler import Upscaler, UpscalerData
@@ -43,9 +42,10 @@ class UpscalerRealESRGAN(Upscaler):
         if not self.enable:
             return img
 
+        try:
             info = self.load_model(path)
-        if not os.path.exists(info.local_data_path):
+        except Exception:
-            print(f"Unable to load RealESRGAN model: {info.name}")
+            errors.report(f"Unable to load RealESRGAN model {path}", exc_info=True)
             return img
 
         upsampler = RealESRGANer(
@@ -55,6 +55,7 @@ class UpscalerRealESRGAN(Upscaler):
             half=not cmd_opts.no_half and not cmd_opts.upcast_sampling,
             tile=opts.ESRGAN_tile,
             tile_pad=opts.ESRGAN_tile_overlap,
+            device=self.device,
         )
 
         upsampled = upsampler.enhance(np.array(img), outscale=info.scale)[0]
@@ -63,20 +64,17 @@ class UpscalerRealESRGAN(Upscaler):
         return image
 
     def load_model(self, path):
-        try:
+        for scaler in self.scalers:
-            info = next(iter([scaler for scaler in self.scalers if scaler.data_path == path]), None)
+            if scaler.data_path == path:
-
+                if scaler.local_data_path.startswith("http"):
-            if info is None:
+                    scaler.local_data_path = modelloader.load_file_from_url(
-                print(f"Unable to find model info: {path}")
+                        scaler.data_path,
-                return None
+                        model_dir=self.model_download_path,
-
+                    )
-            if info.local_data_path.startswith("http"):
+                if not os.path.exists(scaler.local_data_path):
-                info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_download_path, progress=True)
+                    raise FileNotFoundError(f"RealESRGAN data missing: {scaler.local_data_path}")
-
+                return scaler
-            return info
+        raise ValueError(f"Unable to find model info: {path}")
-        except Exception:
-            errors.report("Error making Real-ESRGAN models list", exc_info=True)
-        return None
 
     def load_models(self, _):
         return get_realesrgan_models(self)