update changelog

Update launch_utils.py - fixes repetead package reinstalls

.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
-      value: |
-        1. Go to .... 
-        2. Press ....
+      description: Please provide us with precise step by step instructions on how to reproduce the bug
+      placeholder: |
+        1. Go to ...
+        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
-    validations:
-      required: true
-  - 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 "
+      description: Tell us what you think the normal behavior should be
+      placeholder: |
+        WebUI should ...
     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
-      description: Are you using any launching parameters/command line arguments (modified webui-user .bat/.sh) ? If yes, please write them below. Write "No" otherwise.
-      render: Shell
-    validations:
-      required: true
-  - type: textarea
-    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.
+      label: Sysinfo
+      description: System info file, generated by WebUI. You can generate it in settings, on the Sysinfo page. Drag the file into the field to upload it. If you submit your report without including the sysinfo file, the report will be closed. If needed, review the report to make sure it includes no personal information you don't want to share. If you can't start WebUI, you can use --dump-sysinfo commandline argument to generate the file.
+      placeholder: |
+        1. Go to WebUI Settings -> Sysinfo -> Download system info.
+            If WebUI fails to launch, use --dump-sysinfo commandline argument to generate the file
+        2. Upload the Sysinfo as a attached file, Do NOT paste it in as plain text.
     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

@@ -20,7 +20,7 @@ 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==0.0.272
+        run: pip install ruff==0.1.6
       - name: Run Ruff
         run: ruff .
   lint-js:

CHANGELOG.md

@@ -1,3 +1,318 @@
+## 1.7.0
+
+### Features:
+* settings tab rework: add search field, add categories, split UI settings page into many
+* add altdiffusion-m18 support ([#13364](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13364))
+* support inference with LyCORIS GLora networks ([#13610](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13610))
+* add lora-embedding bundle system ([#13568](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13568))
+* option to move prompt from top row into generation parameters
+* add support for SSD-1B ([#13865](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13865))
+* support inference with OFT networks ([#13692](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13692))
+* script metadata and DAG sorting mechanism ([#13944](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13944))
+* support HyperTile optimization ([#13948](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13948))
+* add support for SD 2.1 Turbo ([#14170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14170))
+* remove Train->Preprocessing tab and put all its functionality into Extras tab
+* initial IPEX support for Intel Arc GPU ([#14171](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14171))
+
+### Minor:
+* allow reading model hash from images in img2img batch mode ([#12767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12767))
+* add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))
+* extra field for lora metadata viewer: `ss_output_name` ([#12838](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12838))
+* add action in settings page to calculate all SD checkpoint hashes ([#12909](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12909))
+* add button to copy prompt to style editor ([#12975](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12975))
+* add --skip-load-model-at-start option ([#13253](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13253))
+* write infotext to gif images
+* read infotext from gif images ([#13068](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13068))
+* allow configuring the initial state of InputAccordion in ui-config.json ([#13189](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13189))
+* allow editing whitespace delimiters for ctrl+up/ctrl+down prompt editing ([#13444](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13444))
+* prevent accidentally closing popup dialogs ([#13480](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13480))
+* added option to play notification sound or not ([#13631](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13631))
+* show the preview image in the full screen image viewer if available ([#13459](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13459))
+* support for webui.settings.bat ([#13638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13638))
+* add an option to not print stack traces on ctrl+c
+* start/restart generation by Ctrl (Alt) + Enter ([#13644](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13644))
+* update prompts_from_file script to allow concatenating entries with the general prompt ([#13733](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13733))
+* added a visible checkbox to input accordion
+* added an option to hide all txt2img/img2img parameters in an accordion ([#13826](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13826))
+* added 'Path' sorting option for Extra network cards ([#13968](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13968))
+* enable prompt hotkeys in style editor ([#13931](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13931))
+* option to show batch img2img results in UI ([#14009](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14009))
+* infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page
+* add FP32 fallback support on sd_vae_approx ([#14046](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046))
+* support XYZ scripts / split hires path from unet ([#14126](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14126))
+* allow use of mutiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125))
+
+### Extensions and API:
+* update gradio to 3.41.2
+* support installed extensions list api ([#12774](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12774))
+* update pnginfo API to return dict with parsed values
+* add noisy latent to `ExtraNoiseParams` for callback ([#12856](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12856))
+* show extension datetime in UTC ([#12864](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12864), [#12865](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12865), [#13281](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13281))
+* add an option to choose how to combine hires fix and refiner
+* include program version in info response. ([#13135](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13135))
+* sd_unet support for SDXL
+* patch DDPM.register_betas so that users can put given_betas in model yaml ([#13276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13276))
+* xyz_grid: add prepare ([#13266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13266))
+* allow multiple localization files with same language in extensions ([#13077](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13077))
+* add onEdit function for js and rework token-counter.js to use it
+* fix the key error exception when processing override_settings keys ([#13567](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13567))
+* ability for extensions to return custom data via api in response.images ([#13463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13463))
+* call state.jobnext() before postproces*() ([#13762](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13762))
+* add option to set notification sound volume ([#13884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13884))
+* update Ruff to 0.1.6 ([#14059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14059))
+* add Block component creation callback ([#14119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14119))
+* catch uncaught exception with ui creation scripts ([#14120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14120))
+* use extension name for determining an extension is installed in the index ([#14063](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14063))
+* update is_installed() from launch_utils.py to fix reinstalling already installed packages ([#14192](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14192))
+
+### Bug Fixes:
+* fix pix2pix producing bad results
+* fix defaults settings page breaking when any of main UI tabs are hidden
+* fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt
+* fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working
+* prevent duplicate resize handler ([#12795](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12795))
+* small typo: vae resolve bug ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12797))
+* hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12792))
+* don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12780))
+* fix style editing dialog breaking if it's opened in both img2img and txt2img tabs
+* hide --gradio-auth and --api-auth values from /internal/sysinfo report
+* add missing infotext for RNG in options ([#12819](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12819))
+* 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/12833), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))
+* get progressbar to display correctly in extensions tab
+* keep order in list of checkpoints when loading model that doesn't have a checksum
+* fix inpainting models in txt2img creating black pictures
+* fix generation params regex ([#12876](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12876))
+* fix batch img2img output dir with script ([#12926](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12926))
+* fix #13080 - Hypernetwork/TI preview generation ([#13084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13084))
+* fix bug with sigma min/max overrides. ([#12995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12995))
+* more accurate check for enabling cuDNN benchmark on 16XX cards ([#12924](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12924))
+* don't use multicond parser for negative prompt counter ([#13118](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13118))
+* fix data-sort-name containing spaces ([#13412](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13412))
+* update card on correct tab when editing metadata ([#13411](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13411))
+* fix viewing/editing metadata when filename contains an apostrophe ([#13395](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13395))
+* fix: --sd_model in "Prompts from file or textbox" script is not working ([#13302](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13302))
+* better Support for Portable Git ([#13231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13231))
+* fix issues when webui_dir is not work_dir ([#13210](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13210))
+* fix: lora-bias-backup don't reset cache ([#13178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13178))
+* account for customizable extra network separators whyen removing extra network text from the prompt ([#12877](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12877))
+* re fix batch img2img output dir with script ([#13170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13170))
+* fix `--ckpt-dir` path separator and option use `short name` for checkpoint dropdown ([#13139](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13139))
+* consolidated allowed preview formats, Fix extra network `.gif` not woking as preview ([#13121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13121))
+* fix venv_dir=- environment variable not working as expected on linux ([#13469](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13469))
+* repair unload sd checkpoint button
+* edit-attention fixes ([#13533](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13533))
+* fix bug when using --gfpgan-models-path ([#13718](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13718))
+* properly apply sort order for extra network cards when selected from dropdown
+* fixes generation restart not working for some users when 'Ctrl+Enter' is pressed ([#13962](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13962))
+* thread safe extra network list_items ([#13014](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13014))
+* fix not able to exit metadata popup when pop up is too big ([#14156](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14156))
+* fix auto focal point crop for opencv >= 4.8 ([#14121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14121))
+* make 'use-cpu all' actually apply to 'all' ([#14131](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14131))
+* extras tab batch: actually use original filename
+* make webui not crash when running with --disable-all-extensions option
+
+### Other:
+* non-local condition ([#12814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12814))
+* fix minor typos ([#12827](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12827))
+* remove xformers Python version check ([#12842](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12842))
+* style: file-metadata word-break ([#12837](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12837))
+* revert SGM noise multiplier change for img2img because it breaks hires fix
+* do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))
+* [RC 1.6.0 - zoom is partly hidden] Update style.css ([#12839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12839))
+* chore: change extension time format ([#12851](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12851))
+* WEBUI.SH - Use torch 2.1.0 release candidate for Navi 3 ([#12929](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12929))
+* add Fallback at images.read_info_from_image if exif data was invalid ([#13028](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13028))
+* update cmd arg description ([#12986](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12986))
+* fix: update shared.opts.data when add_option ([#12957](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12957), [#13213](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13213))
+* restore missing tooltips ([#12976](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12976))
+* use default dropdown padding on mobile ([#12880](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12880))
+* put enable console prompts option into settings from commandline args ([#13119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13119))
+* fix some deprecated types ([#12846](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12846))
+* bump to torchsde==0.2.6 ([#13418](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13418))
+* update dragdrop.js ([#13372](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13372))
+* use orderdict as lru cache:opt/bug ([#13313](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13313))
+* XYZ if not include sub grids do not save sub grid ([#13282](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13282))
+* initialize state.time_start befroe state.job_count ([#13229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13229))
+* fix fieldname regex ([#13458](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13458))
+* change denoising_strength default to None. ([#13466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13466))
+* fix regression ([#13475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13475))
+* fix IndexError ([#13630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13630))
+* fix: checkpoints_loaded:{checkpoint:state_dict}, model.load_state_dict issue in dict value empty ([#13535](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13535))
+* update bug_report.yml ([#12991](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12991))
+* requirements_versions httpx==0.24.1 ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))
+* fix parenthesis auto selection ([#13829](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13829))
+* fix #13796 ([#13797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13797))
+* corrected a typo in `modules/cmd_args.py` ([#13855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13855))
+* feat: fix randn found element of type float at pos 2 ([#14004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14004))
+* adds tqdm handler to logging_config.py for progress bar integration ([#13996](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13996))
+* hotfix: call shared.state.end() after postprocessing done ([#13977](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13977))
+* fix dependency address patch 1 ([#13929](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13929))
+* save sysinfo as .json ([#14035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14035))
+* move exception_records related methods to errors.py ([#14084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14084))
+* compatibility ([#13936](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13936))
+* json.dump(ensure_ascii=False) ([#14108](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14108))
+* dir buttons start with / so only the correct dir will be shown and no… ([#13957](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13957))
+* alternate implementation for unet forward replacement that does not depend on hijack being applied
+* re-add `keyedit_delimiters_whitespace` setting lost as part of commit e294e46 ([#14178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14178))
+* fix `save_samples` being checked early when saving masked composite ([#14177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14177))
+* slight optimization for mask and mask_composite ([#14181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14181))
+* add import_hook hack to work around basicsr/torchvision incompatibility ([#14186](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14186))
+
+## 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:

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.
@@ -143,7 +149,7 @@ For the purposes of getting Google and other search engines to crawl the wiki, h
 ## 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
@@ -169,5 +175,7 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - 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/Lora/extra_networks_lora.py

@@ -6,9 +6,14 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
     def __init__(self):
         super().__init__('lora')
 
+        self.errors = {}
+        """mapping of network names to the number of errors the network had during operation"""
+
     def activate(self, p, params_list):
         additional = shared.opts.sd_lora
 
+        self.errors.clear()
+
         if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
             p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
             params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
@@ -56,4 +61,7 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
                 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_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

@@ -19,3 +19,50 @@ 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

@@ -93,6 +93,7 @@ class Network:  # LoraModule
         self.unet_multiplier = 1.0
         self.dyn_dim = None
         self.modules = {}
+        self.bundle_embeddings = {}
         self.mtime = None
 
         self.mentioned_name = None
@@ -133,7 +134,7 @@ class NetworkModule:
 
         return 1.0
 
-    def finalize_updown(self, updown, orig_weight, output_shape):
+    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)
@@ -145,7 +146,10 @@ class NetworkModule:
         if orig_weight.size().numel() == updown.size().numel():
             updown = updown.reshape(orig_weight.shape)
 
-        return updown * self.calc_scale() * self.multiplier()
+        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()

extensions-builtin/Lora/network_full.py

@@ -14,9 +14,14 @@ class NetworkModuleFull(network.NetworkModule):
         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)
+        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_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

@@ -1,17 +1,25 @@
+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(),
@@ -19,6 +27,9 @@ module_types = [
     network_ia3.ModuleTypeIa3(),
     network_lokr.ModuleTypeLokr(),
     network_full.ModuleTypeFull(),
+    network_norm.ModuleTypeNorm(),
+    network_glora.ModuleTypeGLora(),
+    network_oft.ModuleTypeOFT(),
 ]
 
 
@@ -31,6 +42,8 @@ suffix_conversion = {
     "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",
     }
@@ -143,9 +156,19 @@ def load_network(name, network_on_disk):
     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)
@@ -168,6 +191,17 @@ def load_network(name, network_on_disk):
                 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
@@ -189,18 +223,38 @@ def load_network(name, network_on_disk):
 
         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:
-        print(f"Failed to match keys when loading network {network_on_disk.filename}: {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()
 
@@ -212,15 +266,19 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
 
     failed_to_load_networks = []
 
-    for i, name in enumerate(names):
+    for i, (network_on_disk, name) in enumerate(zip(networks_on_disk, names)):
         net = already_loaded.get(name, None)
 
-        network_on_disk = networks_on_disk[i]
-
         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
@@ -231,7 +289,7 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
 
         if net is None:
             failed_to_load_networks.append(name)
-            print(f"Couldn't find network with name {name}")
+            logging.info(f"Couldn't find network with name {name}")
             continue
 
         net.te_multiplier = te_multipliers[i] if te_multipliers else 1.0
@@ -239,24 +297,54 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
         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("Failed to find networks: " + ", ".join(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.MultiheadAttention]):
+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:
+    if weights_backup is None and bias_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])
+    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:
-        self.weight.copy_(weights_backup)
+        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.MultiheadAttention]):
+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.
@@ -271,7 +359,10 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
     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:
+    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:
@@ -279,21 +370,41 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
 
         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'):
-                with torch.no_grad():
-                    updown = module.calc_updown(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))
+                        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
-                    continue
+                        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)
@@ -301,21 +412,33 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
             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:
-                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 = module_out.calc_updown(self.out_proj.weight)
+                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
-                    continue
+                        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
 
-            print(f'failed to calculate network weights for layer {network_layer_name}')
+            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
 
@@ -342,7 +465,7 @@ def network_forward(module, input, original_forward):
         if module is None:
             continue
 
-        y = module.forward(y, input)
+        y = module.forward(input, y)
 
     return y
 
@@ -350,48 +473,79 @@ def network_forward(module, input, original_forward):
 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, torch.nn.Linear_forward_before_network)
+        return network_forward(self, input, originals.Linear_forward)
 
     network_apply_weights(self)
 
-    return torch.nn.Linear_forward_before_network(self, input)
+    return originals.Linear_forward(self, input)
 
 
 def network_Linear_load_state_dict(self, *args, **kwargs):
     network_reset_cached_weight(self)
 
-    return torch.nn.Linear_load_state_dict_before_network(self, *args, **kwargs)
+    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, torch.nn.Conv2d_forward_before_network)
+        return network_forward(self, input, originals.Conv2d_forward)
 
     network_apply_weights(self)
 
-    return torch.nn.Conv2d_forward_before_network(self, input)
+    return originals.Conv2d_forward(self, input)
 
 
 def network_Conv2d_load_state_dict(self, *args, **kwargs):
     network_reset_cached_weight(self)
 
-    return torch.nn.Conv2d_load_state_dict_before_network(self, *args, **kwargs)
+    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 torch.nn.MultiheadAttention_forward_before_network(self, *args, **kwargs)
+    return originals.MultiheadAttention_forward(self, *args, **kwargs)
 
 
 def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
     network_reset_cached_weight(self)
 
-    return torch.nn.MultiheadAttention_load_state_dict_before_network(self, *args, **kwargs)
+    return originals.MultiheadAttention_load_state_dict(self, *args, **kwargs)
 
 
 def list_available_networks():
@@ -459,9 +613,15 @@ def infotext_pasted(infotext, params):
         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 = {}
 

extensions-builtin/Lora/scripts/lora_script.py

@@ -1,57 +1,30 @@
 import re
 
-import torch
 import gradio as gr
 from fastapi import FastAPI
 
 import network
 import networks
 import lora  # noqa:F401
+import lora_patches
 import extra_networks_lora
 import ui_extra_networks_lora
 from modules import script_callbacks, ui_extra_networks, extra_networks, shared
 
+
 def unload():
-    torch.nn.Linear.forward = torch.nn.Linear_forward_before_network
-    torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_network
-    torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_network
-    torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_network
-    torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_network
-    torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_network
+    networks.originals.undo()
 
 
 def before_ui():
     ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
 
-    extra_network = extra_networks_lora.ExtraNetworkLora()
-    extra_networks.register_extra_network(extra_network)
-    extra_networks.register_extra_network_alias(extra_network, "lyco")
+    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_network'):
-    torch.nn.Linear_forward_before_network = torch.nn.Linear.forward
-
-if not hasattr(torch.nn, 'Linear_load_state_dict_before_network'):
-    torch.nn.Linear_load_state_dict_before_network = torch.nn.Linear._load_from_state_dict
-
-if not hasattr(torch.nn, 'Conv2d_forward_before_network'):
-    torch.nn.Conv2d_forward_before_network = torch.nn.Conv2d.forward
-
-if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_network'):
-    torch.nn.Conv2d_load_state_dict_before_network = torch.nn.Conv2d._load_from_state_dict
-
-if not hasattr(torch.nn, 'MultiheadAttention_forward_before_network'):
-    torch.nn.MultiheadAttention_forward_before_network = torch.nn.MultiheadAttention.forward
-
-if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_network'):
-    torch.nn.MultiheadAttention_load_state_dict_before_network = torch.nn.MultiheadAttention._load_from_state_dict
-
-torch.nn.Linear.forward = networks.network_Linear_forward
-torch.nn.Linear._load_from_state_dict = networks.network_Linear_load_state_dict
-torch.nn.Conv2d.forward = networks.network_Conv2d_forward
-torch.nn.Conv2d._load_from_state_dict = networks.network_Conv2d_load_state_dict
-torch.nn.MultiheadAttention.forward = networks.network_MultiheadAttention_forward
-torch.nn.MultiheadAttention._load_from_state_dict = networks.network_MultiheadAttention_load_state_dict
+networks.originals = lora_patches.LoraPatches()
 
 script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
 script_callbacks.on_script_unloaded(unload)
@@ -65,6 +38,7 @@ shared.options_templates.update(shared.options_section(('extra_networks', "Extra
     "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}),
 }))
 
 
@@ -121,3 +95,5 @@ def infotext_pasted(infotext, d):
 
 
 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

@@ -70,6 +70,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
         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:",
@@ -167,7 +168,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
                 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').style(full_width=True, size="lg")
+                generate_random_prompt = gr.Button('Generate', size="lg", scale=1)
 
         self.edit_notes = gr.TextArea(label='Notes', lines=4)
 

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -17,6 +17,8 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
 
     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
 
         path, ext = os.path.splitext(lora_on_disk.filename)
 
@@ -25,9 +27,10 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         item = {
             "name": name,
             "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 ""),
             "local_preview": f"{path}.{shared.opts.samples_format}",
             "metadata": lora_on_disk.metadata,
             "sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
@@ -65,9 +68,10 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         return item
 
     def list_items(self):
-        for index, name in enumerate(networks.available_networks):
+        # 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
 

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

@@ -12,8 +12,22 @@ onUiLoaded(async() => {
         "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");
 
@@ -34,7 +48,7 @@ onUiLoaded(async() => {
 
     // Wait until opts loaded
     async function waitForOpts() {
-        for (;;) {
+        for (; ;) {
             if (window.opts && Object.keys(window.opts).length) {
                 return window.opts;
             }
@@ -42,6 +56,11 @@ onUiLoaded(async() => {
         }
     }
 
+    // Detect whether the element has a horizontal scroll bar
+    function hasHorizontalScrollbar(element) {
+        return element.scrollWidth > element.clientWidth;
+    }
+
     // Function for defining the "Ctrl", "Shift" and "Alt" keys
     function isModifierKey(event, key) {
         switch (key) {
@@ -201,7 +220,8 @@ onUiLoaded(async() => {
         canvas_hotkey_overlap: "KeyO",
         canvas_disabled_functions: [],
         canvas_show_tooltip: true,
-        canvas_blur_prompt: false
+        canvas_auto_expand: true,
+        canvas_blur_prompt: false,
     };
 
     const functionMap = {
@@ -249,7 +269,7 @@ onUiLoaded(async() => {
         input?.addEventListener("input", () => restoreImgRedMask(elements));
     }
 
-    function applyZoomAndPan(elemId) {
+    function applyZoomAndPan(elemId, isExtension = true) {
         const targetElement = gradioApp().querySelector(elemId);
 
         if (!targetElement) {
@@ -361,6 +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)`;
 
@@ -371,8 +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
             ) {
@@ -381,9 +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
@@ -439,7 +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;
@@ -450,6 +492,10 @@ 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;
         }
 
@@ -472,10 +518,12 @@ onUiLoaded(async() => {
                 fullScreenMode = false;
                 elemData[elemId].zoomLevel = updateZoom(
                     elemData[elemId].zoomLevel +
-                        (operation === "+" ? delta : -delta),
+                    (operation === "+" ? delta : -delta),
                     zoomPosX - targetElement.getBoundingClientRect().left,
                     zoomPosY - targetElement.getBoundingClientRect().top
                 );
+
+                targetElement.isZoomed = true;
             }
         }
 
@@ -489,10 +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;
 
@@ -545,8 +602,12 @@ onUiLoaded(async() => {
 
             if (!canvas) return;
 
-            if (canvas.offsetWidth > 862) {
-                targetElement.style.width = canvas.offsetWidth + "px";
+            if (canvas.offsetWidth > 862 || isExtension) {
+                targetElement.style.width = (canvas.offsetWidth + 2) + "px";
+            }
+
+            if (isExtension) {
+                targetElement.style.overflow = "visible";
             }
 
             if (fullScreenMode) {
@@ -648,8 +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;
 
@@ -754,6 +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";
             }
@@ -764,13 +870,93 @@ onUiLoaded(async() => {
             isMoving = false;
         };
 
+        // Checks for extension
+        function checkForOutBox() {
+            const parentElement = targetElement.closest('[id^="component-"]');
+            if (parentElement.offsetWidth < targetElement.offsetWidth && !targetElement.isExpanded) {
+                resetZoom();
+                targetElement.isExpanded = true;
+            }
+
+            if (parentElement.offsetWidth < targetElement.offsetWidth && elemData[elemId].zoomLevel == 1) {
+                resetZoom();
+            }
+
+            if (parentElement.offsetWidth < targetElement.offsetWidth && targetElement.offsetWidth * elemData[elemId].zoomLevel > parentElement.offsetWidth && elemData[elemId].zoomLevel < 1 && !targetElement.isZoomed) {
+                resetZoom();
+            }
+        }
+
+        if (isExtension) {
+            targetElement.addEventListener("mousemove", checkForOutBox);
+        }
+
+
+        window.addEventListener('resize', (e) => {
+            resetZoom();
+
+            if (isExtension) {
+                targetElement.isExpanded = false;
+                targetElement.isZoomed = false;
+            }
+        });
+
         gradioApp().addEventListener("mousemove", handleMoveByKey);
+
+
     }
 
-    applyZoomAndPan(elementIDs.sketch);
-    applyZoomAndPan(elementIDs.inpaint);
-    applyZoomAndPan(elementIDs.inpaintSketch);
+    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

@@ -9,6 +9,7 @@ shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas
     "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas positon"),
     "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, neededs for testing"),
     "canvas_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
+    "canvas_auto_expand": shared.OptionInfo(True, "Automatically expands an image that does not fit completely in the canvas area, similar to manually pressing the S and R buttons"),
     "canvas_blur_prompt": shared.OptionInfo(False, "Take the focus off the prompt when working with a canvas"),
     "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size", "Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
 }))

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

@@ -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():
-                for setting_name in shared.opts.extra_options:
-                    with FormColumn():
-                        comp = ui_settings.create_setting_component(setting_name)
+            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
 
-                    self.comps.append(comp)
-                    self.setting_names.append(setting_name)
+                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)
 
@@ -42,7 +64,14 @@ class ExtraOptionsSection(scripts.Script):
                 p.override_settings[name] = value
 
 
-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_accordion": shared.OptionInfo(False, "Place options in main UI into an accordion")
+shared.options_templates.update(shared.options_section(('settings_in_ui', "Settings in UI", "ui"), {
+    "settings_in_ui": shared.OptionHTML("""
+This page allows you to add some settings to the main interface of txt2img and img2img tabs.
+"""),
+    "extra_options_txt2img": shared.OptionInfo([], "Settings for txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
+    "extra_options_img2img": shared.OptionInfo([], "Settings for 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, "Number of columns for added settings", gr.Number, {"precision": 0}).needs_reload_ui(),
+    "extra_options_accordion": shared.OptionInfo(False, "Place added settings into an accordion").needs_reload_ui()
 }))
+
+

extensions-builtin/hypertile/hypertile.py

@@ -0,0 +1,351 @@
+"""
+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
+
+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()
+
+@cache
+def get_divisors(value: int, min_value: int, /, max_options: int = 1) -> list[int]:
+    """
+    Returns divisors of value that
+        x * min_value <= value
+    in big -> small order, amount of divisors is limited by max_options
+    """
+    max_options = max(1, max_options) # at least 1 option should be returned
+    min_value = min(min_value, value)
+    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
+    return ns
+
+
+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
+    """
+    ns = get_divisors(value, min_value, max_options=max_options) # get cached divisors
+    idx = RNG_INSTANCE.randint(0, len(ns) - 1)
+
+    return ns[idx]
+
+
+def set_hypertile_seed(seed: int) -> None:
+    RNG_INSTANCE.seed(seed)
+
+
+@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 +1,78 @@
+import hypertile
+from modules import scripts, script_callbacks, shared
+from scripts.hypertile_xyz import add_axis_options
+
+
+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):
+        # exclusive hypertile seed for the second pass
+        if not shared.opts.hypertile_enable_unet:
+            hypertile.set_hypertile_seed(p.all_seeds[0])
+        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=shared.opts.hypertile_enable_unet_secondpass)
+
+
+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": 64, "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": 64, "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)
+script_callbacks.on_before_ui(add_axis_options)

extensions-builtin/hypertile/scripts/hypertile_xyz.py

@@ -0,0 +1,51 @@
+from modules import scripts
+from modules.shared import opts
+
+xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
+
+def int_applier(value_name:str, min_range:int = -1, max_range:int = -1):
+    """
+    Returns a function that applies the given value to the given value_name in opts.data.
+    """
+    def validate(value_name:str, value:str):
+        value = int(value)
+        # validate value
+        if not min_range == -1:
+            assert value >= min_range, f"Value {value} for {value_name} must be greater than or equal to {min_range}"
+        if not max_range == -1:
+            assert value <= max_range, f"Value {value} for {value_name} must be less than or equal to {max_range}"
+    def apply_int(p, x, xs):
+        validate(value_name, x)
+        opts.data[value_name] = int(x)
+    return apply_int
+
+def bool_applier(value_name:str):
+    """
+    Returns a function that applies the given value to the given value_name in opts.data.
+    """
+    def validate(value_name:str, value:str):
+        assert value.lower() in ["true", "false"], f"Value {value} for {value_name} must be either true or false"
+    def apply_bool(p, x, xs):
+        validate(value_name, x)
+        value_boolean = x.lower() == "true"
+        opts.data[value_name] = value_boolean
+    return apply_bool
+
+def add_axis_options():
+    extra_axis_options = [
+        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, bool_applier("hypertile_enable_unet"), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, bool_applier("hypertile_enable_unet_secondpass"), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, int_applier("hypertile_max_depth_unet", 0, 3), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, int_applier("hypertile_max_tile_unet", 0, 512)),
+        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, int_applier("hypertile_swap_size_unet", 0, 64)),
+        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, bool_applier("hypertile_enable_vae"), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, int_applier("hypertile_max_depth_vae", 0, 3), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, int_applier("hypertile_max_tile_vae", 0, 512)),
+        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, int_applier("hypertile_swap_size_vae", 0, 64)),
+    ]
+    set_a = {opt.label for opt in xyz_grid.axis_options}
+    set_b = {opt.label for opt in extra_axis_options}
+    if set_a.intersection(set_b):
+        return
+
+    xyz_grid.axis_options.extend(extra_axis_options)

extensions-builtin/mobile/javascript/mobile.js

@@ -12,6 +12,8 @@ function isMobile() {
 }
 
 function reportWindowSize() {
+    if (gradioApp().querySelector('.toprow-compact-tools')) return; // not applicable for compact prompt layout
+
     var currentlyMobile = isMobile();
     if (currentlyMobile == isSetupForMobile) return;
     isSetupForMobile = currentlyMobile;
@@ -20,7 +22,13 @@ function reportWindowSize() {
         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();
+});

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) {
-            beforeParen = before.lastIndexOf(OPEN, beforeParen - 1);
-            beforeParenClose = before.lastIndexOf(CLOSE, beforeParenClose - 1);
-        }
+
+        let beforeClosingParen = before.lastIndexOf(CLOSE);
+        if (beforeClosingParen != -1 && beforeClosingParen > beforeParen) return false;
 
         // Find closing parenthesis around current cursor
         const after = text.substring(selectionStart);
         let afterParen = after.indexOf(CLOSE);
         if (afterParen == -1) return false;
-        let afterParenOpen = after.indexOf(OPEN);
-        while (afterParenOpen !== -1 && afterParen > afterParenOpen) {
-            afterParen = after.indexOf(CLOSE, afterParen + 1);
-            afterParenOpen = after.indexOf(OPEN, afterParenOpen + 1);
-        }
-        if (beforeParen === -1 || afterParen === -1) return false;
+
+        let afterOpeningParen = after.indexOf(OPEN);
+        if (afterOpeningParen != -1 && afterOpeningParen < afterParen) return false;
 
         // Set the selection to the text between the parenthesis
         const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
-        const lastColon = parenContent.lastIndexOf(":");
-        selectionStart = beforeParen + 1;
-        selectionEnd = selectionStart + lastColon;
+        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();
     }
 
@@ -71,33 +77,54 @@ 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;
-        selectionEnd += 1;
+        selectionStart++;
+        selectionEnd++;
     }
 
-    var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
-    var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end));
+    if (text[selectionEnd] != ':') return;
+    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) {
         var endParenPos = text.substring(selectionEnd).indexOf(')');
@@ -105,7 +132,7 @@ function keyupEditAttention(event) {
         selectionStart--;
         selectionEnd--;
     } else {
-        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + end);
+        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + weightLength);
     }
 
     target.focus();

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() {
 
     });
 

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');
-    sort.classList.add('sort');
-    sortOrder.classList.add('sortorder');
-    sort.dataset.sortkey = 'sortDefault';
-    tabs.appendChild(search);
+    tabs.appendChild(searchDiv);
     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(/_+$/, "").trim();
-        sortKey = sortKey ? "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1) : "";
-        var sortKeyStore = sortKey ? sortKey + (reverse ? "Reverse" : "") : "";
-        if (!sortKey || sortKeyStore == sort.dataset.sortkey) {
+        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim() || "name";
+        sortKey = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
+        var sortKeyStore = sortKey + "-" + (reverse ? "Descending" : "Ascending") + "-" + cards.length;
+
+        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() {
@@ -113,14 +182,15 @@ function setupExtraNetworks() {
 
 onUiLoaded(setupExtraNetworks);
 
-var re_extranet = /<([^:]+:[^:]+):[\d.]+>(.*)/;
-var re_extranet_g = /\s+<([^:]+:[^:]+):[\d.]+>/g;
+var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
+var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
 
 function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
     var m = text.match(re_extranet);
     var replaced = false;
     var newTextareaText;
     if (m) {
+        var extraTextBeforeNet = opts.extra_networks_add_text_separator;
         var extraTextAfterNet = m[2];
         var partToSearch = m[1];
         var foundAtPosition = -1;
@@ -134,8 +204,13 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
             return found;
         });
 
-        if (foundAtPosition >= 0 && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
-            newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
+        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) {
@@ -179,7 +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();
 
@@ -189,27 +264,24 @@ 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 = closePopup;
         globalPopup.classList.add('global-popup');
 
         var close = document.createElement('div');
         close.classList.add('global-popup-close');
-        close.onclick = closePopup;
+        close.addEventListener("click", closePopup);
         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);
 
@@ -222,6 +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');
@@ -299,15 +380,21 @@ function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
 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('.card[data-name=' + JSON.stringify(name) + ']'); // likely using the wrong stringify function
+            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 = '';
+            newCard.style.display = '';
             card.parentElement.insertBefore(newCard, card);
             card.parentElement.removeChild(card);
         }
     });
 }
+
+window.addEventListener("keydown", function(event) {
+    if (event.key == "Escape") {
+        closePopup();
+    }
+});

javascript/hints.js

@@ -190,3 +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();
-
-        if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
+        let preview = gradioApp().querySelectorAll('.livePreview > img');
+        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_face_restoration_model: 'SPAN',
-    setting_realesrgan_enabled_models: 'SPAN',
-    extras_upscaler_1: 'SPAN',
-    extras_upscaler_2: 'SPAN',
+    setting_random_artist_categories: 'OPTION',
+    setting_face_restoration_model: 'OPTION',
+    setting_realesrgan_enabled_models: 'OPTION',
+    extras_upscaler_1: 'OPTION',
+    extras_upscaler_2: 'OPTION',
 };
 
 var re_num = /^[.\d]+$/;
@@ -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 = document.createElement('div');
-        livePreview.className = 'livePreview';
-        parentGallery.insertBefore(livePreview, gallery);
-    }
+    var livePreview = null;
 
     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) {
-        request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) {
+    var funProgress = function(id_task) {
+        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) {
+                onProgress(res);
+            }
+
+            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) {
-                rect = gallery.getBoundingClientRect();
-                if (rect.width) {
-                    livePreview.style.width = rect.width + "px";
-                    livePreview.style.height = rect.height + "px";
-                }
-
                 var img = new Image();
                 img.onload = function() {
+                    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 promptTokenCountTimeouts = {};
-var promptTokenCountUpdateFunctions = {};
+let promptTokenCountUpdateFunctions = {};
 
 function update_txt2img_tokens(...args) {
     // Called from Gradio
     update_token_counter("txt2img_token_button");
+    update_token_counter("txt2img_negative_token_button");
     if (args.length == 2) {
         return args[0];
     }
@@ -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) {
-        return;
-    }
-    if (promptTokenCountTimeouts[button_id]) {
-        clearTimeout(promptTokenCountTimeouts[button_id]);
-    }
-    promptTokenCountTimeouts[button_id] = setTimeout(
-        () => gradioApp().getElementById(button_id)?.click(),
-        promptTokenCountDebounceTime,
-    );
+    promptTokenCountUpdateFunctions[button_id]?.();
 }
 
 
@@ -69,10 +60,11 @@ function setupTokenCounting(id, id_counter, id_button) {
     prompt.parentElement.insertBefore(counter, prompt);
     prompt.parentElement.style.position = "relative";
 
-    promptTokenCountUpdateFunctions[id] = function() {
-        update_token_counter(id_button);
-    };
-    textarea.addEventListener("input", promptTokenCountUpdateFunctions[id]);
+    var func = onEdit(id, textarea, 800, function() {
+        gradioApp().getElementById(id_button)?.click();
+    });
+    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');
-    var visibleCurrentButton = null;
-    allCurrentButtons.forEach(function(elem) {
-        if (elem.parentElement.offsetParent) {
-            visibleCurrentButton = elem;
-        }
-    });
-    return visibleCurrentButton;
+    return all_gallery_buttons().find(elem => elem.classList.contains('selected')) ?? null;
 }
 
 function selected_gallery_index() {
-    var buttons = all_gallery_buttons();
-    var button = selected_gallery_button();
-
-    var result = -1;
-    buttons.forEach(function(v, i) {
-        if (v == button) {
-            result = i;
-        }
-    });
-
-    return result;
+    return all_gallery_buttons().findIndex(elem => elem.classList.contains('selected'));
 }
 
 function extract_image_from_gallery(gallery) {
@@ -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);
     });
 
@@ -187,11 +170,26 @@ function submit_img2img() {
     return res;
 }
 
+function submit_extras() {
+    showSubmitButtons('extras', false);
+
+    var id = randomId();
+
+    requestProgress(id, gradioApp().getElementById('extras_gallery_container'), gradioApp().getElementById('extras_gallery'), function() {
+        showSubmitButtons('extras', true);
+    });
+
+    var res = create_submit_args(arguments);
+
+    res[0] = id;
+
+    console.log(res);
+    return res;
+}
+
 function restoreProgressTxt2img() {
     showRestoreProgressButton("txt2img", false);
-    var id = localStorage.getItem("txt2img_task_id");
-
-    id = localStorage.getItem("txt2img_task_id");
+    var id = localGet("txt2img_task_id");
 
     if (id) {
         requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
@@ -205,7 +203,7 @@ 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 +216,8 @@ function restoreProgressImg2img() {
 
 
 onUiLoaded(function() {
-    showRestoreProgressButton('txt2img', localStorage.getItem("txt2img_task_id"));
-    showRestoreProgressButton('img2img', localStorage.getItem("img2img_task_id"));
+    showRestoreProgressButton('txt2img', localGet("txt2img_task_id"));
+    showRestoreProgressButton('img2img', localGet("img2img_task_id"));
 });
 
 
@@ -282,21 +280,6 @@ 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 +368,20 @@ 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
@@ -26,8 +25,18 @@ start = launch_utils.start
 
 
 def main():
-    if not args.skip_prepare_environment:
-        prepare_environment()
+    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()
 
     if args.test_server:
         configure_for_tests()

modules/api/api.py

@@ -4,6 +4,8 @@ import os
 import time
 import datetime
 import uvicorn
+import ipaddress
+import requests
 import gradio as gr
 from threading import Lock
 from io import BytesIO
@@ -15,20 +17,17 @@ 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, restart
+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
 from modules.textual_inversion.textual_inversion import create_embedding, train_embedding
-from modules.textual_inversion.preprocess import preprocess
 from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
-from PIL import PngImagePlugin,Image
-from modules.sd_models import checkpoints_list, unload_model_weights, reload_model_weights, checkpoint_aliases
-from modules.sd_vae import vae_dict
+from PIL import PngImagePlugin, Image
 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
@@ -56,7 +55,41 @@ 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:
@@ -68,7 +101,8 @@ 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()
@@ -186,27 +220,28 @@ 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/upscalers", self.get_upscalers, methods=["GET"], response_model=List[models.UpscalerItem])
-        self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=List[models.LatentUpscalerModeItem])
-        self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[models.SDModelItem])
-        self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=List[models.SDVaeItem])
-        self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem])
-        self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[models.FaceRestorerItem])
-        self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[models.RealesrganItem])
-        self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem])
+        self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=list[models.SamplerItem])
+        self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=list[models.UpscalerItem])
+        self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=list[models.LatentUpscalerModeItem])
+        self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=list[models.SDModelItem])
+        self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=list[models.SDVaeItem])
+        self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=list[models.HypernetworkItem])
+        self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=list[models.FaceRestorerItem])
+        self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=list[models.RealesrganItem])
+        self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=list[models.PromptStyleItem])
         self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse)
         self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
+        self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"])
         self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse)
         self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse)
-        self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse)
         self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse)
         self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse)
         self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse)
         self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList)
-        self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=List[models.ScriptInfo])
+        self.add_api_route("/sdapi/v1/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"])
@@ -329,6 +364,7 @@ class Api:
 
         with self.queue_lock:
             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
@@ -343,6 +379,7 @@ class Api:
                         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 []
 
@@ -388,6 +425,7 @@ class Api:
         with self.queue_lock:
             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
@@ -402,6 +440,7 @@ class Api:
                         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 []
 
@@ -433,9 +472,6 @@ 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="")
@@ -444,9 +480,10 @@ 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
@@ -501,12 +538,12 @@ 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 {}
 
@@ -524,13 +561,13 @@ class Api:
 
         return options
 
-    def set_config(self, req: Dict[str, Any]):
+    def set_config(self, req: dict[str, Any]):
         checkpoint_name = req.get("sd_model_checkpoint", None)
-        if checkpoint_name is not None and checkpoint_name not in checkpoint_aliases:
+        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
@@ -562,10 +599,12 @@ 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]
@@ -608,6 +647,10 @@ class Api:
         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(job="create_embedding")
@@ -630,19 +673,6 @@ class Api:
         finally:
             shared.state.end()
 
-    def preprocess(self, args: dict):
-        try:
-            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:
-            return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}")
-        except Exception as e:
-            return models.PreprocessResponse(info=f"preprocess error: {e}")
-        finally:
-            shared.state.end()
-
     def train_embedding(self, args: dict):
         try:
             shared.state.begin(job="train_embedding")
@@ -724,6 +754,25 @@ class Api:
             cuda = {'error': f'{err}'}
         return models.MemoryResponse(ram=ram, cuda=cuda)
 
+    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=shared.cmd_opts.timeout_keep_alive, root_path=root_path)

modules/api/models.py

@@ -1,12 +1,10 @@
 import inspect
 
 from pydantic import BaseModel, Field, create_model
-from typing import Any, Optional
-from typing_extensions import Literal
+from typing import Any, Optional, Literal
 from inflection import underscore
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
 from modules.shared import sd_upscalers, opts, parser
-from typing import Dict, List
 
 API_NOT_ALLOWED = [
     "self",
@@ -50,10 +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_):
@@ -63,7 +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)
 
@@ -72,7 +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
         ]
@@ -129,12 +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
 
@@ -167,17 +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")
@@ -202,9 +202,6 @@ class TrainResponse(BaseModel):
 class CreateResponse(BaseModel):
     info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.")
 
-class PreprocessResponse(BaseModel):
-    info: str = Field(title="Preprocess info", description="Response string from preprocessing task.")
-
 fields = {}
 for key, metadata in opts.data_labels.items():
     value = opts.data.get(key)
@@ -231,8 +228,8 @@ FlagsModel = create_model("Flags", **flags)
 
 class SamplerItem(BaseModel):
     name: str = Field(title="Name")
-    aliases: List[str] = Field(title="Aliases")
-    options: Dict[str, str] = Field(title="Options")
+    aliases: list[str] = Field(title="Aliases")
+    options: dict[str, str] = Field(title="Options")
 
 class UpscalerItem(BaseModel):
     name: str = Field(title="Name")
@@ -283,8 +280,8 @@ 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")
-    skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
+    loaded: dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model")
+    skipped: dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
 
 class MemoryResponse(BaseModel):
     ram: dict = Field(title="RAM", description="System memory stats")
@@ -302,11 +299,20 @@ 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

@@ -1,11 +1,12 @@
 import json
+import os
 import os.path
 import threading
 import time
 
 from modules.paths import data_path, script_path
 
-cache_filename = os.path.join(data_path, "cache.json")
+cache_filename = os.environ.get('SD_WEBUI_CACHE_FILE', os.path.join(data_path, "cache.json"))
 cache_data = None
 cache_lock = threading.Lock()
 
@@ -29,8 +30,11 @@ def dump_cache():
             time.sleep(1)
 
         with cache_lock:
-            with open(cache_filename, "w", encoding="utf8") as file:
-                json.dump(cache_data, file, indent=4)
+            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

modules/call_queue.py

@@ -1,11 +1,10 @@
 from functools import wraps
 import html
-import threading
 import time
 
-from modules import shared, progress, errors, devices
+from modules import shared, progress, errors, devices, fifo_lock
 
-queue_lock = threading.Lock()
+queue_lock = fifo_lock.FIFOLock()
 
 
 def wrap_queued_call(func):

modules/cmd_args.py

@@ -13,8 +13,11 @@ 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",)
@@ -33,9 +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.")
@@ -66,6 +70,8 @@ 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("--use-ipex", action="store_true", help="use Intel XPU as torch device")
+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)
@@ -78,14 +84,14 @@ 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)")
@@ -102,11 +108,14 @@ 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/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 = OrderedDict()
+all_config_states = {}
 
 
 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)
-            with open(path, "r", encoding="utf-8") as f:
-                j = json.load(f)
-                j["filepath"] = path
-                config_states.append(j)
+            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

@@ -3,11 +3,18 @@ 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
 
+if shared.cmd_opts.use_ipex:
+    from modules import xpu_specific
+
+
+def has_xpu() -> bool:
+    return shared.cmd_opts.use_ipex and xpu_specific.has_xpu
+
 
 def has_mps() -> bool:
     if sys.platform != "darwin":
@@ -17,8 +24,6 @@ def has_mps() -> bool:
 
 
 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}"
 
@@ -32,6 +37,9 @@ def get_optimal_device_name():
     if has_mps():
         return "mps"
 
+    if has_xpu():
+        return xpu_specific.get_xpu_device_string()
+
     return "cpu"
 
 
@@ -40,9 +48,7 @@ def get_optimal_device():
 
 
 def get_device_for(task):
-    from modules import shared
-
-    if task in shared.cmd_opts.use_cpu:
+    if task in shared.cmd_opts.use_cpu or "all" in shared.cmd_opts.use_cpu:
         return cpu
 
     return get_optimal_device()
@@ -58,27 +64,34 @@ def torch_gc():
     if has_mps():
         mac_specific.torch_mps_gc()
 
+    if has_xpu():
+        xpu_specific.torch_xpu_gc()
+
 
 def enable_tf32():
     if torch.cuda.is_available():
 
         # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
         # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
-        if any(torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())):
+        device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()
+        if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"):
             torch.backends.cudnn.benchmark = True
 
         torch.backends.cuda.matmul.allow_tf32 = True
         torch.backends.cudnn.allow_tf32 = True
 
 
-
 errors.run(enable_tf32, "Enabling TF32")
 
-cpu = torch.device("cpu")
-device = device_interrogate = device_gfpgan = device_esrgan = device_codeformer = None
-dtype = torch.float16
-dtype_vae = torch.float16
-dtype_unet = torch.float16
+cpu: torch.device = torch.device("cpu")
+device: torch.device = None
+device_interrogate: torch.device = None
+device_gfpgan: torch.device = None
+device_esrgan: torch.device = None
+device_codeformer: torch.device = None
+dtype: torch.dtype = torch.float16
+dtype_vae: torch.dtype = torch.float16
+dtype_unet: torch.dtype = torch.float16
 unet_needs_upcast = False
 
 
@@ -90,26 +103,10 @@ def cond_cast_float(input):
     return input.float() if unet_needs_upcast else input
 
 
-def randn(seed, shape):
-    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)
+nv_rng = None
 
 
 def autocast(disable=False):
-    from modules import shared
-
     if disable:
         return contextlib.nullcontext()
 
@@ -128,8 +125,6 @@ class NansException(Exception):
 
 
 def test_for_nans(x, where):
-    from modules import shared
-
     if shared.cmd_opts.disable_nan_check:
         return
 
@@ -169,3 +164,4 @@ 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:
@@ -14,8 +29,7 @@ def record_exception():
     if exception_records and exception_records[-1] == e:
         return
 
-    from modules import sysinfo
-    exception_records.append(sysinfo.format_exception(e, tb))
+    exception_records.append(format_exception(e, tb))
 
     if len(exception_records) > 5:
         exception_records.pop(0)
@@ -84,3 +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/extensions.py

@@ -1,29 +1,76 @@
+from __future__ import annotations
+
+import configparser
 import os
 import threading
+import re
 
-from modules import shared, errors, cache
+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 = []
 
 os.makedirs(extensions_dir, exist_ok=True)
 
 
 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
@@ -36,6 +83,8 @@ 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}
@@ -56,6 +105,7 @@ class Extension:
                 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)
@@ -90,8 +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 []
@@ -138,26 +186,52 @@ class Extension:
 def list_extensions():
     extensions.clear()
 
-    if not os.path.isdir(extensions_dir):
-        return
-
-    if shared.opts.disable_all_extensions == "all":
+    if shared.cmd_opts.disable_all_extensions:
+        print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
+    elif shared.opts.disable_all_extensions == "all":
         print("*** \"Disable all extensions\" option was set, will not load any extensions ***")
+    elif shared.cmd_opts.disable_extra_extensions:
+        print("*** \"--disable-extra-extensions\" arg was used, will only load built-in extensions ***")
     elif shared.opts.disable_all_extensions == "extra":
         print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
 
-    extension_paths = []
-    for dirname in [extensions_dir, extensions_builtin_dir]:
+    loaded_extensions = {}
+
+    # 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:
-        extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)
-        extensions.append(extension)
+            # check for duplicated canonical names
+            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

@@ -1,4 +1,7 @@
+import json
+import os
 import re
+import logging
 from collections import defaultdict
 
 from modules import errors
@@ -84,27 +87,55 @@ 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"""
 
     activated = []
 
-    for extra_network_name, extra_network_args in extra_network_data.items():
-        extra_network = extra_network_registry.get(extra_network_name, None)
-
-        if extra_network is None:
-            extra_network = extra_network_aliases.get(extra_network_name, None)
-
-        if extra_network is None:
-            print(f"Skipping unknown extra network: {extra_network_name}")
-            continue
+    for extra_network, extra_network_args in lookup_extra_networks(extra_network_data).items():
 
         try:
             extra_network.activate(p, extra_network_args)
             activated.append(extra_network)
         except Exception as e:
-            errors.display(e, f"activating extra network {extra_network_name} with arguments {extra_network_args}")
+            errors.display(e, f"activating extra network {extra_network.name} with arguments {extra_network_args}")
 
     for extra_network_name, extra_network in extra_network_registry.items():
         if extra_network in activated:
@@ -123,19 +154,16 @@ 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:
-        extra_network = extra_network_registry.get(extra_network_name, None)
-        if extra_network is None:
-            continue
+    data = lookup_extra_networks(extra_network_data)
 
+    for extra_network in data:
         try:
             extra_network.deactivate(p)
         except Exception as e:
-            errors.display(e, f"deactivating extra network {extra_network_name}")
+            errors.display(e, f"deactivating extra network {extra_network.name}")
 
     for extra_network_name, extra_network in extra_network_registry.items():
-        args = extra_network_data.get(extra_network_name, None)
-        if args is not None:
+        if extra_network in data:
             continue
 
         try:
@@ -177,3 +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
@@ -72,7 +72,20 @@ 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):
+    metadata = {}
+
+    for checkpoint_name in [primary_model_name, secondary_model_name, tertiary_model_name]:
+        checkpoint_info = sd_models.checkpoints_list.get(checkpoint_name, None)
+        if checkpoint_info is None:
+            continue
+
+        metadata.update(checkpoint_info.metadata)
+
+    return json.dumps(metadata, indent=4, ensure_ascii=False)
+
+
+def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata, add_merge_recipe, copy_metadata_fields, metadata_json):
     shared.state.begin(job="model-merge")
 
     def fail(message):
@@ -241,11 +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,
@@ -261,7 +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 = {}
 
@@ -281,11 +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

@@ -1,3 +1,4 @@
+from __future__ import annotations
 import base64
 import io
 import json
@@ -6,18 +7,15 @@ 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("\(([0-9a-f]+)\)$")
 type_of_gr_update = type(gr.update())
 
-paste_fields = {}
-registered_param_bindings = []
-
 
 class ParamBinding:
     def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=None):
@@ -30,8 +28,13 @@ class ParamBinding:
         self.paste_field_names = paste_field_names or []
 
 
+paste_fields: dict[str, dict] = {}
+registered_param_bindings: list[ParamBinding] = []
+
+
 def reset():
     paste_fields.clear()
+    registered_param_bindings.clear()
 
 
 def quote(text):
@@ -112,7 +115,6 @@ def register_paste_params_button(binding: ParamBinding):
 
 
 def connect_paste_params_buttons():
-    binding: ParamBinding
     for binding in registered_param_bindings:
         destination_image_component = paste_fields[binding.tabname]["init_img"]
         fields = paste_fields[binding.tabname]["fields"]
@@ -198,7 +200,6 @@ 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
@@ -280,6 +281,9 @@ 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"] = ""
 
@@ -304,32 +308,31 @@ 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"
+
+    skip = set(shared.opts.infotext_skip_pasting)
+    res = {k: v for k, v in res.items() if k not in skip}
+
     return res
 
 
 infotext_to_setting_name_mapping = [
-    ('Clip skip', 'CLIP_stop_at_last_layers', ),
+
+]
+"""Mapping of infotext labels to setting names. Only left for backwards compatibility - use OptionInfo(..., infotext='...') instead.
+Example content:
+
+infotext_to_setting_name_mapping = [
     ('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'),
-    ('Pad conds', 'pad_cond_uncond'),
 ]
+"""
 
 
 def create_override_settings_dict(text_pairs):
@@ -350,7 +353,8 @@ 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:
@@ -399,10 +403,16 @@ 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
@@ -437,3 +447,4 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
         outputs=[],
         show_progress=False,
     )
+

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 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
 
@@ -77,19 +86,25 @@ def setup_model(dirname):
         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 +1,83 @@
+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):
+    if scripts.scripts_current is not None:
+        scripts.scripts_current.before_component(self, **kwargs)
+
+    scripts.script_callbacks.before_component_callback(self, **kwargs)
+
+    res = original_BlockContext_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 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
+
+
+original_IOComponent_init = patches.patch(__name__, obj=gr.components.IOComponent, 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/hypernetworks/hypernetwork.py

@@ -10,7 +10,7 @@ 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
@@ -468,9 +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):
-    # images allows training previews to have infotext. Importing it at the top causes a circular import problem.
-    from modules import images
+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):
+    from modules import images, processing
 
     save_hypernetwork_every = save_hypernetwork_every or 0
     create_image_every = create_image_every or 0
@@ -699,7 +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

modules/images.py

@@ -21,8 +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)
 
 
@@ -318,7 +316,7 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
     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 + ']+')
@@ -342,16 +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],
@@ -367,7 +355,9 @@ class FilenameGenerator:
         '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),
@@ -380,7 +370,8 @@ class FilenameGenerator:
         '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
+        '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'
 
@@ -391,6 +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:
@@ -444,6 +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 = ''
 
@@ -546,6 +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)
 
@@ -585,6 +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)
 
@@ -641,7 +663,13 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
 
         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'):
@@ -698,7 +726,12 @@ def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
     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)
@@ -708,6 +741,8 @@ def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
         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 IGNORED_INFO_KEYS:
         items.pop(field, None)

modules/img2img.py

@@ -3,14 +3,14 @@ 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, images as imgutil
+from modules import images as imgutil
 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.images import save_image
+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
@@ -18,9 +18,10 @@ import modules.scripts
 
 
 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 = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp")))
+    images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
 
     is_inpaint_batch = False
     if inpaint_mask_dir:
@@ -32,11 +33,6 @@ 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
@@ -46,7 +42,10 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     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:
@@ -109,42 +108,58 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
             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):
-            filename = image_path.stem
-            infotext = proc.infotext(p, n)
-            relpath = os.path.dirname(os.path.relpath(image, input_dir))
+        if not discard_further_results and proc:
+            if batch_results:
+                batch_results.images.extend(proc.images)
+                batch_results.infotexts.extend(proc.infotexts)
+            else:
+                batch_results = proc
 
-            if n > 0:
-                filename += f"-{n}"
+            if 0 <= shared.opts.img2img_batch_show_results_limit < len(batch_results.images):
+                discard_further_results = True
+                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:
-                os.makedirs(os.path.join(output_dir, relpath), exist_ok=True)
-                if processed_image.mode == 'RGBA':
-                    processed_image = processed_image.convert("RGB")
-                save_image(processed_image, os.path.join(output_dir, relpath), None, extension=opts.samples_format, info=infotext, forced_filename=filename, save_to_dirs=False)
+    return batch_results
 
 
-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, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *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 = 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")
+        mask = processing.create_binary_mask(mask)
     elif mode == 3:  # inpaint sketch
         image = inpaint_color_sketch
         orig = inpaint_color_sketch_orig or inpaint_color_sketch
@@ -153,7 +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
@@ -180,21 +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,
-        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,
+        sampler_name=sampler_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,
@@ -213,7 +219,7 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
 
     p.user = request.username
 
-    if shared.cmd_opts.enable_console_prompts:
+    if shared.opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
     if mask:
@@ -222,10 +228,10 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     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, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
-
-            processed = Processed(p, [], p.seed, "")
+            if processed is None:
+                processed = Processed(p, [], p.seed, "")
         else:
             processed = modules.scripts.scripts_img2img.run(p, *args)
             if processed is None:

modules/import_hook.py

@@ -3,3 +3,14 @@ import sys
 # this will break any attempt to import xformers which will prevent stability diffusion repo from trying to use it
 if "--xformers" not in "".join(sys.argv):
     sys.modules["xformers"] = None
+
+# Hack to fix a changed import in torchvision 0.17+, which otherwise breaks
+# basicsr; see https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13985
+try:
+    import torchvision.transforms.functional_tensor  # noqa: F401
+except ImportError:
+    try:
+        import torchvision.transforms.functional as functional
+        sys.modules["torchvision.transforms.functional_tensor"] = functional
+    except ImportError:
+        pass  # shrug...

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

@@ -186,9 +186,8 @@ class InterrogateModels:
         res = ""
         shared.state.begin(job="interrogate")
         try:
-            if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
-                lowvram.send_everything_to_cpu()
-                devices.torch_gc()
+            lowvram.send_everything_to_cpu()
+            devices.torch_gc()
 
             self.load()
 

modules/launch_utils.py

@@ -1,20 +1,23 @@
 # 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 importlib.metadata
 import platform
 import json
 from functools import lru_cache
 
 from modules import cmd_args, errors
 from modules.paths_internal import script_path, extensions_dir
-from modules import timer
-
-timer.startup_timer.record("start")
+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")
@@ -62,7 +65,7 @@ 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>"
 
@@ -70,7 +73,7 @@ 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:
 
@@ -117,11 +120,16 @@ def run(command, desc=None, errdesc=None, custom_env=None, live: bool = default_
 
 def is_installed(package):
     try:
-        spec = importlib.util.find_spec(package)
-    except ModuleNotFoundError:
-        return False
+        dist = importlib.metadata.distribution(package)
+    except importlib.metadata.PackageNotFoundError:
+        try:
+            spec = importlib.util.find_spec(package)
+        except ModuleNotFoundError:
+            return False
 
-    return spec is not None
+        return spec is not None
+
+    return dist is not None
 
 
 def repo_dir(name):
@@ -141,6 +149,25 @@ 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
 
@@ -148,15 +175,24 @@ 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}", live=False).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}")
-        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
+        if run_git(dir, name, 'config --get remote.origin.url', None, f"Couldn't determine {name}'s origin URL", live=False).strip() != url:
+            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}", live=True)
+    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}")
@@ -198,7 +234,9 @@ def run_extension_installer(extension_dir):
         env = os.environ.copy()
         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))
 
@@ -216,7 +254,7 @@ 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]
@@ -226,8 +264,15 @@ def run_extensions_installers(settings_file):
     if not os.path.isdir(extensions_dir):
         return
 
-    for dirname_extension in list_extensions(settings_file):
-        run_extension_installer(os.path.join(extensions_dir, dirname_extension))
+    with startup_timer.subcategory("run extensions installers"):
+        for dirname_extension in list_extensions(settings_file):
+            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*")
@@ -271,10 +316,29 @@ def requirements_met(requirements_file):
 def prepare_environment():
     torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu118")
     torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url {torch_index_url}")
+    if args.use_ipex:
+        if platform.system() == "Windows":
+            # The "Nuullll/intel-extension-for-pytorch" wheels were built from IPEX source for Intel Arc GPU: https://github.com/intel/intel-extension-for-pytorch/tree/xpu-main
+            # This is NOT an Intel official release so please use it at your own risk!!
+            # See https://github.com/Nuullll/intel-extension-for-pytorch/releases/tag/v2.0.110%2Bxpu-master%2Bdll-bundle for details.
+            #
+            # Strengths (over official IPEX 2.0.110 windows release):
+            #   - AOT build (for Arc GPU only) to eliminate JIT compilation overhead: https://github.com/intel/intel-extension-for-pytorch/issues/399
+            #   - Bundles minimal oneAPI 2023.2 dependencies into the python wheels, so users don't need to install oneAPI for the whole system.
+            #   - Provides a compatible torchvision wheel: https://github.com/intel/intel-extension-for-pytorch/issues/465
+            # Limitation:
+            #   - Only works for python 3.10
+            url_prefix = "https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.0.110%2Bxpu-master%2Bdll-bundle"
+            torch_command = os.environ.get('TORCH_COMMAND', f"pip install {url_prefix}/torch-2.0.0a0+gite9ebda2-cp310-cp310-win_amd64.whl {url_prefix}/torchvision-0.15.2a0+fa99a53-cp310-cp310-win_amd64.whl {url_prefix}/intel_extension_for_pytorch-2.0.110+gitc6ea20b-cp310-cp310-win_amd64.whl")
+        else:
+            # Using official IPEX release for linux since it's already an AOT build.
+            # However, users still have to install oneAPI toolkit and activate oneAPI environment manually.
+            # See https://intel.github.io/intel-extension-for-pytorch/index.html#installation for details.
+            torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://pytorch-extension.intel.com/release-whl/stable/xpu/us/")
+            torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.0a0 intel-extension-for-pytorch==2.0.110+gitba7f6c1 --extra-index-url {torch_index_url}")
     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")
 
@@ -285,13 +349,13 @@ def prepare_environment():
     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")
-    stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "5c10deee76adad0032b412294130090932317a87")
-    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:
@@ -300,8 +364,11 @@ 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}")
@@ -309,36 +376,32 @@ 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 args.use_ipex:
+        args.skip_torch_cuda_test = True
     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'
         )
-
-    if not is_installed("gfpgan"):
-        run_pip(f"install {gfpgan_package}", "gfpgan")
+    startup_timer.record("torch GPU test")
 
     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")
+        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)
 
@@ -348,22 +411,29 @@ def prepare_environment():
     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)
 
     if not requirements_met(requirements_file):
         run_pip(f"install -r \"{requirements_file}\"", "requirements")
+        startup_timer.record("install requirements")
 
-    run_extensions_installers(settings_file=args.ui_settings_file)
+    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")
@@ -392,3 +462,16 @@ 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 = {}
 
@@ -14,22 +14,24 @@ 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:
-        try:
-            with open(fn, "r", encoding="utf8") as file:
-                data = json.load(file)
-        except Exception:
-            errors.report(f"Error loading localization from {fn}", exc_info=True)
+    if fns is not None:
+        for fn in fns:
+            try:
+                with open(fn, "r", encoding="utf8") as file:
+                    data.update(json.load(file))
+            except Exception:
+                errors.report(f"Error loading localization from {fn}", exc_info=True)
 
     return f"window.localization = {json.dumps(data)}"

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 = {}
@@ -127,4 +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

@@ -1,9 +1,11 @@
 import logging
 
 import torch
+from torch import Tensor
 import platform
 from modules.sd_hijack_utils import CondFunc
 from packaging import version
+from modules import shared
 
 log = logging.getLogger(__name__)
 
@@ -30,8 +32,7 @@ has_mps = check_for_mps()
 
 def torch_mps_gc() -> None:
     try:
-        from modules.shared import state
-        if state.current_latent is not None:
+        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
@@ -51,10 +52,18 @@ def cumsum_fix(input, cumsum_func, *args, **kwargs):
     return cumsum_func(input, *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')
+# MPS workaround for https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046
+def interpolate_with_fp32_fallback(orig_func, *args, **kwargs) -> Tensor:
+    try:
+        return orig_func(*args, **kwargs)
+    except RuntimeError as e:
+        if "not implemented for" in str(e) and "Half" in str(e):
+            input_tensor = args[0]
+            return orig_func(input_tensor.to(torch.float32), *args[1:], **kwargs).to(input_tensor.dtype)
+        else:
+            print(f"An unexpected RuntimeError occurred: {str(e)}")
 
+if has_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)
@@ -80,6 +89,9 @@ if has_mps:
         # MPS workaround for https://github.com/pytorch/pytorch/issues/96113
         CondFunc('torch.nn.functional.layer_norm', lambda orig_func, x, normalized_shape, weight, bias, eps, **kwargs: orig_func(x.float(), normalized_shape, weight.float() if weight is not None else None, bias.float() if bias is not None else bias, eps).to(x.dtype), lambda _, input, *args, **kwargs: len(args) == 4 and input.device.type == 'mps')
 
+        # MPS workaround for https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046
+        CondFunc('torch.nn.functional.interpolate', interpolate_with_fp32_fallback, None)
+
         # MPS workaround for https://github.com/pytorch/pytorch/issues/92311
         if platform.processor() == 'i386':
             for funcName in ['torch.argmax', 'torch.Tensor.argmax']:

modules/models/diffusion/ddpm_edit.py

@@ -24,10 +24,15 @@ from pytorch_lightning.utilities.distributed import rank_zero_only
 from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
 from ldm.modules.ema import LitEma
 from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
-from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.models.autoencoder import IdentityFirstStage, AutoencoderKL
 from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
 from ldm.models.diffusion.ddim import DDIMSampler
 
+try:
+    from ldm.models.autoencoder import VQModelInterface
+except Exception:
+    class VQModelInterface:
+        pass
 
 __conditioning_keys__ = {'concat': 'c_concat',
                          'crossattn': 'c_crossattn',

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

@@ -1,6 +1,6 @@
 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
 

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

@@ -6,42 +6,33 @@ from modules import shared, images, devices, scripts, scripts_postprocessing, ui
 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):
+def run_postprocessing(id_task, extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True):
     devices.torch_gc()
 
     shared.state.begin(job="extras")
 
-    image_data = []
-    image_names = []
     outputs = []
 
-    if extras_mode == 1:
-        for img in image_folder:
-            if isinstance(img, Image.Image):
-                image = img
-                fn = ''
-            else:
-                image = Image.open(os.path.abspath(img.name))
-                fn = os.path.splitext(img.orig_name)[0]
-            image_data.append(image)
-            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'
+    def get_images(extras_mode, image, image_folder, input_dir):
+        if extras_mode == 1:
+            for img in image_folder:
+                if isinstance(img, Image.Image):
+                    image = img
+                    fn = ''
+                else:
+                    image = Image.open(os.path.abspath(img.name))
+                    fn = os.path.splitext(img.orig_name)[0]
+                yield image, 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'
 
-        image_list = shared.listfiles(input_dir)
-        for filename in image_list:
-            try:
-                image = Image.open(filename)
-            except Exception:
-                continue
-            image_data.append(image)
-            image_names.append(filename)
-    else:
-        assert image, 'image not selected'
-
-        image_data.append(image)
-        image_names.append(None)
+            image_list = shared.listfiles(input_dir)
+            for filename in image_list:
+                yield filename, filename
+        else:
+            assert image, 'image not selected'
+            yield image, None
 
     if extras_mode == 2 and output_dir != '':
         outpath = output_dir
@@ -50,36 +41,90 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
 
     infotext = ''
 
-    for image, name in zip(image_data, image_names):
-        shared.state.textinfo = name
+    data_to_process = list(get_images(extras_mode, image, image_folder, input_dir))
+    shared.state.job_count = len(data_to_process)
 
-        parameters, existing_pnginfo = images.read_info_from_image(image)
+    for image_placeholder, name in data_to_process:
+        image_data: Image.Image
+
+        shared.state.nextjob()
+        shared.state.textinfo = name
+        shared.state.skipped = False
+
+        if shared.state.interrupted:
+            break
+
+        if isinstance(image_placeholder, str):
+            try:
+                image_data = Image.open(image_placeholder)
+            except Exception:
+                continue
+        else:
+            image_data = image_placeholder
+
+        shared.state.assign_current_image(image_data)
+
+        parameters, existing_pnginfo = images.read_info_from_image(image_data)
         if parameters:
             existing_pnginfo["parameters"] = parameters
 
-        pp = scripts_postprocessing.PostprocessedImage(image.convert("RGB"))
+        initial_pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB"))
 
-        scripts.scripts_postproc.run(pp, args)
+        scripts.scripts_postproc.run(initial_pp, args)
 
-        if opts.use_original_name_batch and name is not None:
-            basename = os.path.splitext(os.path.basename(name))[0]
-        else:
-            basename = ''
+        if shared.state.skipped:
+            continue
 
-        infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None])
+        used_suffixes = {}
+        for pp in [initial_pp, *initial_pp.extra_images]:
+            suffix = pp.get_suffix(used_suffixes)
 
-        if opts.enable_pnginfo:
-            pp.image.info = existing_pnginfo
-            pp.image.info["postprocessing"] = infotext
+            if opts.use_original_name_batch and name is not None:
+                basename = os.path.splitext(os.path.basename(name))[0]
+                forced_filename = basename + suffix
+            else:
+                basename = ''
+                forced_filename = None
 
-        if save_output:
-            images.save_image(pp.image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None)
+            infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None])
 
-        if extras_mode != 2 or show_extras_results:
-            outputs.append(pp.image)
+            if opts.enable_pnginfo:
+                pp.image.info = existing_pnginfo
+                pp.image.info["postprocessing"] = infotext
+
+            if save_output:
+                fullfn, _ = images.save_image(pp.image, path=outpath, basename=basename, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=forced_filename, suffix=suffix)
+
+                if pp.caption:
+                    caption_filename = os.path.splitext(fullfn)[0] + ".txt"
+                    if os.path.isfile(caption_filename):
+                        with open(caption_filename, encoding="utf8") as file:
+                            existing_caption = file.read().strip()
+                    else:
+                        existing_caption = ""
+
+                    action = shared.opts.postprocessing_existing_caption_action
+                    if action == 'Prepend' and existing_caption:
+                        caption = f"{existing_caption} {pp.caption}"
+                    elif action == 'Append' and existing_caption:
+                        caption = f"{pp.caption} {existing_caption}"
+                    elif action == 'Keep' and existing_caption:
+                        caption = existing_caption
+                    else:
+                        caption = pp.caption
+
+                    caption = caption.strip()
+                    if caption:
+                        with open(caption_filename, "w", encoding="utf8") as file:
+                            file.write(caption)
+
+            if extras_mode != 2 or show_extras_results:
+                outputs.append(pp.image)
+
+        image_data.close()
 
     devices.torch_gc()
-
+    shared.state.end()
     return outputs, ui_common.plaintext_to_html(infotext), ''
 
 
@@ -98,9 +143,11 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
             "upscaler_2_visibility": extras_upscaler_2_visibility,
         },
         "GFPGAN": {
+            "enable": True,
             "gfpgan_visibility": gfpgan_visibility,
         },
         "CodeFormer": {
+            "enable": True,
             "codeformer_visibility": codeformer_visibility,
             "codeformer_weight": codeformer_weight,
         },

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
 
@@ -89,31 +95,30 @@ 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
-    shared.state.set_current_image()
-    if opts.live_previews_enable and shared.state.id_live_preview != req.id_live_preview:
-        image = shared.state.current_image
-        if image is not None:
-            buffered = io.BytesIO()
 
-            if opts.live_previews_image_format == "png":
-                # using optimize for large images takes an enormous amount of time
-                if max(*image.size) <= 256:
-                    save_kwargs = {"optimize": True}
+    if opts.live_previews_enable and req.live_preview:
+        shared.state.set_current_image()
+        if shared.state.id_live_preview != req.id_live_preview:
+            image = shared.state.current_image
+            if image is not None:
+                buffered = io.BytesIO()
+
+                if opts.live_previews_image_format == "png":
+                    # using optimize for large images takes an enormous amount of time
+                    if max(*image.size) <= 256:
+                        save_kwargs = {"optimize": True}
+                    else:
+                        save_kwargs = {"optimize": False, "compress_level": 1}
+
                 else:
-                    save_kwargs = {"optimize": False, "compress_level": 1}
+                    save_kwargs = {}
 
-            else:
-                save_kwargs = {}
-
-            image.save(buffered, format=opts.live_previews_image_format, **save_kwargs)
-            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
+                image.save(buffered, format=opts.live_previews_image_format, **save_kwargs)
+                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
 
     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

@@ -2,10 +2,9 @@ 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']
@@ -19,14 +18,14 @@ prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)*
 !emphasized: "(" prompt ")"
         | "(" prompt ":" prompt ")"
         | "[" prompt "]"
-scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"
-alternate: "[" prompt ("|" prompt)+ "]"
+scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER [WHITESPACE] "]"
+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")
@@ -53,18 +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])
-                if tree.children[-1] < 1:
-                    tree.children[-1] *= steps
-                tree.children[-1] = min(steps, int(tree.children[-1]))
-                res.append(tree.children[-1])
+                s = tree.children[-2]
+                v = float(s)
+                if use_old_scheduling:
+                    v = v*steps if v<1 else v
+                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))
@@ -75,13 +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:
@@ -129,7 +154,7 @@ class SdConditioning(list):
 
 
 
-def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps):
+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.
 
@@ -149,7 +174,7 @@ def get_learned_conditioning(model, prompts: SdConditioning | list[str], 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):
@@ -214,17 +239,17 @@ def get_multicond_prompt_list(prompts: SdConditioning | list[str]):
 
 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.
 
@@ -233,7 +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:
@@ -252,7 +277,7 @@ class DictWithShape(dict):
         return self["crossattn"].shape
 
 
-def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_step):
+def reconstruct_cond_batch(c: list[list[ScheduledPromptConditioning]], current_step):
     param = c[0][0].cond
     is_dict = isinstance(param, dict)
 
@@ -333,7 +358,7 @@ re_attention = re.compile(r"""
 \\|
 \(|
 \[|
-:([+-]?[.\d]+)\)|
+:\s*([+-]?[.\d]+)\s*\)|
 \)|
 ]|
 [^\\()\[\]:]+|

modules/realesrgan_model.py

@@ -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]

modules/restart.py

@@ -14,7 +14,9 @@ def is_restartable() -> bool:
 def restart_program() -> None:
     """creates file tmp/restart and immediately stops the process, which webui.bat/webui.sh interpret as a command to start webui again"""
 
-    (Path(script_path) / "tmp" / "restart").touch()
+    tmpdir = Path(script_path) / "tmp"
+    tmpdir.mkdir(parents=True, exist_ok=True)
+    (tmpdir / "restart").touch()
 
     stop_program()
 

modules/rng.py

@@ -0,0 +1,170 @@
+import torch
+
+from modules import devices, rng_philox, shared
+
+
+def randn(seed, shape, generator=None):
+    """Generate a tensor with random numbers from a normal distribution using seed.
+
+    Uses the seed parameter to set the global torch seed; to generate more with that seed, use randn_like/randn_without_seed."""
+
+    manual_seed(seed)
+
+    if shared.opts.randn_source == "NV":
+        return torch.asarray((generator or nv_rng).randn(shape), device=devices.device)
+
+    if shared.opts.randn_source == "CPU" or devices.device.type == 'mps':
+        return torch.randn(shape, device=devices.cpu, generator=generator).to(devices.device)
+
+    return torch.randn(shape, device=devices.device, generator=generator)
+
+
+def randn_local(seed, shape):
+    """Generate a tensor with random numbers from a normal distribution using seed.
+
+    Does not change the global random number generator. You can only generate the seed's first tensor using this function."""
+
+    if shared.opts.randn_source == "NV":
+        rng = rng_philox.Generator(seed)
+        return torch.asarray(rng.randn(shape), device=devices.device)
+
+    local_device = devices.cpu if shared.opts.randn_source == "CPU" or devices.device.type == 'mps' else devices.device
+    local_generator = torch.Generator(local_device).manual_seed(int(seed))
+    return torch.randn(shape, device=local_device, generator=local_generator).to(devices.device)
+
+
+def randn_like(x):
+    """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator.
+
+    Use either randn() or manual_seed() to initialize the generator."""
+
+    if shared.opts.randn_source == "NV":
+        return torch.asarray(nv_rng.randn(x.shape), device=x.device, dtype=x.dtype)
+
+    if shared.opts.randn_source == "CPU" or x.device.type == 'mps':
+        return torch.randn_like(x, device=devices.cpu).to(x.device)
+
+    return torch.randn_like(x)
+
+
+def randn_without_seed(shape, generator=None):
+    """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator.
+
+    Use either randn() or manual_seed() to initialize the generator."""
+
+    if shared.opts.randn_source == "NV":
+        return torch.asarray((generator or nv_rng).randn(shape), device=devices.device)
+
+    if shared.opts.randn_source == "CPU" or devices.device.type == 'mps':
+        return torch.randn(shape, device=devices.cpu, generator=generator).to(devices.device)
+
+    return torch.randn(shape, device=devices.device, generator=generator)
+
+
+def manual_seed(seed):
+    """Set up a global random number generator using the specified seed."""
+
+    if shared.opts.randn_source == "NV":
+        global nv_rng
+        nv_rng = rng_philox.Generator(seed)
+        return
+
+    torch.manual_seed(seed)
+
+
+def create_generator(seed):
+    if shared.opts.randn_source == "NV":
+        return rng_philox.Generator(seed)
+
+    device = devices.cpu if shared.opts.randn_source == "CPU" or devices.device.type == 'mps' else devices.device
+    generator = torch.Generator(device).manual_seed(int(seed))
+    return generator
+
+
+# from https://discuss.pytorch.org/t/help-regarding-slerp-function-for-generative-model-sampling/32475/3
+def slerp(val, low, high):
+    low_norm = low/torch.norm(low, dim=1, keepdim=True)
+    high_norm = high/torch.norm(high, dim=1, keepdim=True)
+    dot = (low_norm*high_norm).sum(1)
+
+    if dot.mean() > 0.9995:
+        return low * val + high * (1 - val)
+
+    omega = torch.acos(dot)
+    so = torch.sin(omega)
+    res = (torch.sin((1.0-val)*omega)/so).unsqueeze(1)*low + (torch.sin(val*omega)/so).unsqueeze(1) * high
+    return res
+
+
+class ImageRNG:
+    def __init__(self, shape, seeds, subseeds=None, subseed_strength=0.0, seed_resize_from_h=0, seed_resize_from_w=0):
+        self.shape = tuple(map(int, shape))
+        self.seeds = seeds
+        self.subseeds = subseeds
+        self.subseed_strength = subseed_strength
+        self.seed_resize_from_h = seed_resize_from_h
+        self.seed_resize_from_w = seed_resize_from_w
+
+        self.generators = [create_generator(seed) for seed in seeds]
+
+        self.is_first = True
+
+    def first(self):
+        noise_shape = self.shape if self.seed_resize_from_h <= 0 or self.seed_resize_from_w <= 0 else (self.shape[0], int(self.seed_resize_from_h) // 8, int(self.seed_resize_from_w // 8))
+
+        xs = []
+
+        for i, (seed, generator) in enumerate(zip(self.seeds, self.generators)):
+            subnoise = None
+            if self.subseeds is not None and self.subseed_strength != 0:
+                subseed = 0 if i >= len(self.subseeds) else self.subseeds[i]
+                subnoise = randn(subseed, noise_shape)
+
+            if noise_shape != self.shape:
+                noise = randn(seed, noise_shape)
+            else:
+                noise = randn(seed, self.shape, generator=generator)
+
+            if subnoise is not None:
+                noise = slerp(self.subseed_strength, noise, subnoise)
+
+            if noise_shape != self.shape:
+                x = randn(seed, self.shape, generator=generator)
+                dx = (self.shape[2] - noise_shape[2]) // 2
+                dy = (self.shape[1] - noise_shape[1]) // 2
+                w = noise_shape[2] if dx >= 0 else noise_shape[2] + 2 * dx
+                h = noise_shape[1] if dy >= 0 else noise_shape[1] + 2 * dy
+                tx = 0 if dx < 0 else dx
+                ty = 0 if dy < 0 else dy
+                dx = max(-dx, 0)
+                dy = max(-dy, 0)
+
+                x[:, ty:ty + h, tx:tx + w] = noise[:, dy:dy + h, dx:dx + w]
+                noise = x
+
+            xs.append(noise)
+
+        eta_noise_seed_delta = shared.opts.eta_noise_seed_delta or 0
+        if eta_noise_seed_delta:
+            self.generators = [create_generator(seed + eta_noise_seed_delta) for seed in self.seeds]
+
+        return torch.stack(xs).to(shared.device)
+
+    def next(self):
+        if self.is_first:
+            self.is_first = False
+            return self.first()
+
+        xs = []
+        for generator in self.generators:
+            x = randn_without_seed(self.shape, generator=generator)
+            xs.append(x)
+
+        return torch.stack(xs).to(shared.device)
+
+
+devices.randn = randn
+devices.randn_local = randn_local
+devices.randn_like = randn_like
+devices.randn_without_seed = randn_without_seed
+devices.manual_seed = manual_seed

modules/rng_philox.py

@@ -0,0 +1,102 @@
+"""RNG imitiating torch cuda randn on CPU. You are welcome.
+
+Usage:
+
+```
+g = Generator(seed=0)
+print(g.randn(shape=(3, 4)))
+```
+
+Expected output:
+```
+[[-0.92466259 -0.42534415 -2.6438457   0.14518388]
+ [-0.12086647 -0.57972564 -0.62285122 -0.32838709]
+ [-1.07454231 -0.36314407 -1.67105067  2.26550497]]
+```
+"""
+
+import numpy as np
+
+philox_m = [0xD2511F53, 0xCD9E8D57]
+philox_w = [0x9E3779B9, 0xBB67AE85]
+
+two_pow32_inv = np.array([2.3283064e-10], dtype=np.float32)
+two_pow32_inv_2pi = np.array([2.3283064e-10 * 6.2831855], dtype=np.float32)
+
+
+def uint32(x):
+    """Converts (N,) np.uint64 array into (2, N) np.unit32 array."""
+    return x.view(np.uint32).reshape(-1, 2).transpose(1, 0)
+
+
+def philox4_round(counter, key):
+    """A single round of the Philox 4x32 random number generator."""
+
+    v1 = uint32(counter[0].astype(np.uint64) * philox_m[0])
+    v2 = uint32(counter[2].astype(np.uint64) * philox_m[1])
+
+    counter[0] = v2[1] ^ counter[1] ^ key[0]
+    counter[1] = v2[0]
+    counter[2] = v1[1] ^ counter[3] ^ key[1]
+    counter[3] = v1[0]
+
+
+def philox4_32(counter, key, rounds=10):
+    """Generates 32-bit random numbers using the Philox 4x32 random number generator.
+
+    Parameters:
+        counter (numpy.ndarray): A 4xN array of 32-bit integers representing the counter values (offset into generation).
+        key (numpy.ndarray): A 2xN array of 32-bit integers representing the key values (seed).
+        rounds (int): The number of rounds to perform.
+
+    Returns:
+        numpy.ndarray: A 4xN array of 32-bit integers containing the generated random numbers.
+    """
+
+    for _ in range(rounds - 1):
+        philox4_round(counter, key)
+
+        key[0] = key[0] + philox_w[0]
+        key[1] = key[1] + philox_w[1]
+
+    philox4_round(counter, key)
+    return counter
+
+
+def box_muller(x, y):
+    """Returns just the first out of two numbers generated by Box–Muller transform algorithm."""
+    u = x * two_pow32_inv + two_pow32_inv / 2
+    v = y * two_pow32_inv_2pi + two_pow32_inv_2pi / 2
+
+    s = np.sqrt(-2.0 * np.log(u))
+
+    r1 = s * np.sin(v)
+    return r1.astype(np.float32)
+
+
+class Generator:
+    """RNG that produces same outputs as torch.randn(..., device='cuda') on CPU"""
+
+    def __init__(self, seed):
+        self.seed = seed
+        self.offset = 0
+
+    def randn(self, shape):
+        """Generate a sequence of n standard normal random variables using the Philox 4x32 random number generator and the Box-Muller transform."""
+
+        n = 1
+        for x in shape:
+            n *= x
+
+        counter = np.zeros((4, n), dtype=np.uint32)
+        counter[0] = self.offset
+        counter[2] = np.arange(n, dtype=np.uint32)  # up to 2^32 numbers can be generated - if you want more you'd need to spill into counter[3]
+        self.offset += 1
+
+        key = np.empty(n, dtype=np.uint64)
+        key.fill(self.seed)
+        key = uint32(key)
+
+        g = philox4_32(counter, key)
+
+        return box_muller(g[0], g[1]).reshape(shape)  # discard g[2] and g[3]

modules/script_callbacks.py

@@ -1,7 +1,7 @@
 import inspect
 import os
 from collections import namedtuple
-from typing import Optional, Dict, Any
+from typing import Optional, Any
 
 from fastapi import FastAPI
 from gradio import Blocks
@@ -28,6 +28,18 @@ class ImageSaveParams:
         """dictionary with parameters for image's PNG info data; infotext will have the key 'parameters'"""
 
 
+class ExtraNoiseParams:
+    def __init__(self, noise, x, xi):
+        self.noise = noise
+        """Random noise generated by the seed"""
+
+        self.x = x
+        """Latent representation of the image"""
+
+        self.xi = xi
+        """Noisy latent representation of the image"""
+
+
 class CFGDenoiserParams:
     def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond):
         self.x = x
@@ -100,6 +112,7 @@ callback_map = dict(
     callbacks_ui_settings=[],
     callbacks_before_image_saved=[],
     callbacks_image_saved=[],
+    callbacks_extra_noise=[],
     callbacks_cfg_denoiser=[],
     callbacks_cfg_denoised=[],
     callbacks_cfg_after_cfg=[],
@@ -189,6 +202,14 @@ def image_saved_callback(params: ImageSaveParams):
             report_exception(c, 'image_saved_callback')
 
 
+def extra_noise_callback(params: ExtraNoiseParams):
+    for c in callback_map['callbacks_extra_noise']:
+        try:
+            c.callback(params)
+        except Exception:
+            report_exception(c, 'callbacks_extra_noise')
+
+
 def cfg_denoiser_callback(params: CFGDenoiserParams):
     for c in callback_map['callbacks_cfg_denoiser']:
         try:
@@ -237,7 +258,7 @@ def image_grid_callback(params: ImageGridLoopParams):
             report_exception(c, 'image_grid')
 
 
-def infotext_pasted_callback(infotext: str, params: Dict[str, Any]):
+def infotext_pasted_callback(infotext: str, params: dict[str, Any]):
     for c in callback_map['callbacks_infotext_pasted']:
         try:
             c.callback(infotext, params)
@@ -367,6 +388,14 @@ def on_image_saved(callback):
     add_callback(callback_map['callbacks_image_saved'], callback)
 
 
+def on_extra_noise(callback):
+    """register a function to be called before adding extra noise in img2img or hires fix;
+    The callback is called with one argument:
+        - params: ExtraNoiseParams - contains noise determined by seed and latent representation of image
+    """
+    add_callback(callback_map['callbacks_extra_noise'], callback)
+
+
 def on_cfg_denoiser(callback):
     """register a function to be called in the kdiffussion cfg_denoiser method after building the inner model inputs.
     The callback is called with one argument:
@@ -420,7 +449,7 @@ def on_infotext_pasted(callback):
     """register a function to be called before applying an infotext.
     The callback is called with two arguments:
        - infotext: str - raw infotext.
-       - result: Dict[str, any] - parsed infotext parameters.
+       - result: dict[str, any] - parsed infotext parameters.
     """
     add_callback(callback_map['callbacks_infotext_pasted'], callback)
 

modules/scripts.py

@@ -3,6 +3,7 @@ import re
 import sys
 import inspect
 from collections import namedtuple
+from dataclasses import dataclass
 
 import gradio as gr
 
@@ -21,6 +22,11 @@ class PostprocessBatchListArgs:
         self.images = images
 
 
+@dataclass
+class OnComponent:
+    component: gr.blocks.Block
+
+
 class Script:
     name = None
     """script's internal name derived from title"""
@@ -35,9 +41,13 @@ class Script:
 
     is_txt2img = False
     is_img2img = False
+    tabname = None
 
     group = None
-    """A gr.Group component that has all script's UI inside it"""
+    """A gr.Group component that has all script's UI inside it."""
+
+    create_group = True
+    """If False, for alwayson scripts, a group component will not be created."""
 
     infotext_fields = None
     """if set in ui(), this is a list of pairs of gradio component + text; the text will be used when
@@ -52,6 +62,15 @@ class Script:
     api_info = None
     """Generated value of type modules.api.models.ScriptInfo with information about the script for API"""
 
+    on_before_component_elem_id = None
+    """list of callbacks to be called before a component with an elem_id is created"""
+
+    on_after_component_elem_id = None
+    """list of callbacks to be called after a component with an elem_id is created"""
+
+    setup_for_ui_only = False
+    """If true, the script setup will only be run in Gradio UI, not in API"""
+
     def title(self):
         """this function should return the title of the script. This is what will be displayed in the dropdown menu."""
 
@@ -90,9 +109,16 @@ class Script:
 
         pass
 
+    def setup(self, p, *args):
+        """For AlwaysVisible scripts, this function is called when the processing object is set up, before any processing starts.
+        args contains all values returned by components from ui().
+        """
+        pass
+
+
     def before_process(self, p, *args):
         """
-        This function is called very early before processing begins for AlwaysVisible scripts.
+        This function is called very early during processing begins for AlwaysVisible scripts.
         You can modify the processing object (p) here, inject hooks, etc.
         args contains all values returned by components from ui()
         """
@@ -212,6 +238,29 @@ class Script:
 
         pass
 
+    def on_before_component(self, callback, *, elem_id):
+        """
+        Calls callback before a component is created. The callback function is called with a single argument of type OnComponent.
+
+        May be called in show() or ui() - but it may be too late in latter as some components may already be created.
+
+        This function is an alternative to before_component in that it also cllows to run before a component is created, but
+        it doesn't require to be called for every created component - just for the one you need.
+        """
+        if self.on_before_component_elem_id is None:
+            self.on_before_component_elem_id = []
+
+        self.on_before_component_elem_id.append((elem_id, callback))
+
+    def on_after_component(self, callback, *, elem_id):
+        """
+        Calls callback after a component is created. The callback function is called with a single argument of type OnComponent.
+        """
+        if self.on_after_component_elem_id is None:
+            self.on_after_component_elem_id = []
+
+        self.on_after_component_elem_id.append((elem_id, callback))
+
     def describe(self):
         """unused"""
         return ""
@@ -220,7 +269,7 @@ class Script:
         """helper function to generate id for a HTML element, constructs final id out of script name, tab and user-supplied item_id"""
 
         need_tabname = self.show(True) == self.show(False)
-        tabkind = 'img2img' if self.is_img2img else 'txt2txt'
+        tabkind = 'img2img' if self.is_img2img else 'txt2img'
         tabname = f"{tabkind}_" if need_tabname else ""
         title = re.sub(r'[^a-z_0-9]', '', re.sub(r'\s', '_', self.title().lower()))
 
@@ -232,6 +281,19 @@ class Script:
         """
         pass
 
+
+class ScriptBuiltinUI(Script):
+    setup_for_ui_only = True
+
+    def elem_id(self, item_id):
+        """helper function to generate id for a HTML element, constructs final id out of tab and user-supplied item_id"""
+
+        need_tabname = self.show(True) == self.show(False)
+        tabname = ('img2img' if self.is_img2img else 'txt2img') + "_" if need_tabname else ""
+
+        return f'{tabname}{item_id}'
+
+
 current_basedir = paths.script_path
 
 
@@ -249,19 +311,113 @@ scripts_data = []
 postprocessing_scripts_data = []
 ScriptClassData = namedtuple("ScriptClassData", ["script_class", "path", "basedir", "module"])
 
+def topological_sort(dependencies):
+    """Accepts a dictionary mapping name to its dependencies, returns a list of names ordered according to dependencies.
+    Ignores errors relating to missing dependeencies or circular dependencies
+    """
 
-def list_scripts(scriptdirname, extension):
-    scripts_list = []
+    visited = {}
+    result = []
 
-    basedir = os.path.join(paths.script_path, scriptdirname)
-    if os.path.exists(basedir):
-        for filename in sorted(os.listdir(basedir)):
-            scripts_list.append(ScriptFile(paths.script_path, filename, os.path.join(basedir, filename)))
+    def inner(name):
+        visited[name] = True
 
-    for ext in extensions.active():
-        scripts_list += ext.list_files(scriptdirname, extension)
+        for dep in dependencies.get(name, []):
+            if dep in dependencies and dep not in visited:
+                inner(dep)
 
-    scripts_list = [x for x in scripts_list if os.path.splitext(x.path)[1].lower() == extension and os.path.isfile(x.path)]
+        result.append(name)
+
+    for depname in dependencies:
+        if depname not in visited:
+            inner(depname)
+
+    return result
+
+
+@dataclass
+class ScriptWithDependencies:
+    script_canonical_name: str
+    file: ScriptFile
+    requires: list
+    load_before: list
+    load_after: list
+
+
+def list_scripts(scriptdirname, extension, *, include_extensions=True):
+    scripts = {}
+
+    loaded_extensions = {ext.canonical_name: ext for ext in extensions.active()}
+    loaded_extensions_scripts = {ext.canonical_name: [] for ext in extensions.active()}
+
+    # build script dependency map
+    root_script_basedir = os.path.join(paths.script_path, scriptdirname)
+    if os.path.exists(root_script_basedir):
+        for filename in sorted(os.listdir(root_script_basedir)):
+            if not os.path.isfile(os.path.join(root_script_basedir, filename)):
+                continue
+
+            if os.path.splitext(filename)[1].lower() != extension:
+                continue
+
+            script_file = ScriptFile(paths.script_path, filename, os.path.join(root_script_basedir, filename))
+            scripts[filename] = ScriptWithDependencies(filename, script_file, [], [], [])
+
+    if include_extensions:
+        for ext in extensions.active():
+            extension_scripts_list = ext.list_files(scriptdirname, extension)
+            for extension_script in extension_scripts_list:
+                if not os.path.isfile(extension_script.path):
+                    continue
+
+                script_canonical_name = ("builtin/" if ext.is_builtin else "") + ext.canonical_name + "/" + extension_script.filename
+                relative_path = scriptdirname + "/" + extension_script.filename
+
+                script = ScriptWithDependencies(
+                    script_canonical_name=script_canonical_name,
+                    file=extension_script,
+                    requires=ext.metadata.get_script_requirements("Requires", relative_path, scriptdirname),
+                    load_before=ext.metadata.get_script_requirements("Before", relative_path, scriptdirname),
+                    load_after=ext.metadata.get_script_requirements("After", relative_path, scriptdirname),
+                )
+
+                scripts[script_canonical_name] = script
+                loaded_extensions_scripts[ext.canonical_name].append(script)
+
+    for script_canonical_name, script in scripts.items():
+        # load before requires inverse dependency
+        # in this case, append the script name into the load_after list of the specified script
+        for load_before in script.load_before:
+            # if this requires an individual script to be loaded before
+            other_script = scripts.get(load_before)
+            if other_script:
+                other_script.load_after.append(script_canonical_name)
+
+            # if this requires an extension
+            other_extension_scripts = loaded_extensions_scripts.get(load_before)
+            if other_extension_scripts:
+                for other_script in other_extension_scripts:
+                    other_script.load_after.append(script_canonical_name)
+
+        # if After mentions an extension, remove it and instead add all of its scripts
+        for load_after in list(script.load_after):
+            if load_after not in scripts and load_after in loaded_extensions_scripts:
+                script.load_after.remove(load_after)
+
+                for other_script in loaded_extensions_scripts.get(load_after, []):
+                    script.load_after.append(other_script.script_canonical_name)
+
+    dependencies = {}
+
+    for script_canonical_name, script in scripts.items():
+        for required_script in script.requires:
+            if required_script not in scripts and required_script not in loaded_extensions:
+                errors.report(f'Script "{script_canonical_name}" requires "{required_script}" to be loaded, but it is not.', exc_info=False)
+
+        dependencies[script_canonical_name] = script.load_after
+
+    ordered_scripts = topological_sort(dependencies)
+    scripts_list = [scripts[script_canonical_name].file for script_canonical_name in ordered_scripts]
 
     return scripts_list
 
@@ -288,7 +444,7 @@ def load_scripts():
     postprocessing_scripts_data.clear()
     script_callbacks.clear_callbacks()
 
-    scripts_list = list_scripts("scripts", ".py")
+    scripts_list = list_scripts("scripts", ".py") + list_scripts("modules/processing_scripts", ".py", include_extensions=False)
 
     syspath = sys.path
 
@@ -302,15 +458,9 @@ def load_scripts():
             elif issubclass(script_class, scripts_postprocessing.ScriptPostprocessing):
                 postprocessing_scripts_data.append(ScriptClassData(script_class, scriptfile.path, scriptfile.basedir, module))
 
-    def orderby(basedir):
-        # 1st webui, 2nd extensions-builtin, 3rd extensions
-        priority = {os.path.join(paths.script_path, "extensions-builtin"):1, paths.script_path:0}
-        for key in priority:
-            if basedir.startswith(key):
-                return priority[key]
-        return 9999
-
-    for scriptfile in sorted(scripts_list, key=lambda x: [orderby(x.basedir), x]):
+    # here the scripts_list is already ordered
+    # processing_script is not considered though
+    for scriptfile in scripts_list:
         try:
             if scriptfile.basedir != paths.script_path:
                 sys.path = [scriptfile.basedir] + sys.path
@@ -349,10 +499,17 @@ class ScriptRunner:
         self.selectable_scripts = []
         self.alwayson_scripts = []
         self.titles = []
+        self.title_map = {}
         self.infotext_fields = []
         self.paste_field_names = []
         self.inputs = [None]
 
+        self.on_before_component_elem_id = {}
+        """dict of callbacks to be called before an element is created; key=elem_id, value=list of callbacks"""
+
+        self.on_after_component_elem_id = {}
+        """dict of callbacks to be called after an element is created; key=elem_id, value=list of callbacks"""
+
     def initialize_scripts(self, is_img2img):
         from modules import scripts_auto_postprocessing
 
@@ -367,6 +524,7 @@ class ScriptRunner:
             script.filename = script_data.path
             script.is_txt2img = not is_img2img
             script.is_img2img = is_img2img
+            script.tabname = "img2img" if is_img2img else "txt2img"
 
             visibility = script.show(script.is_img2img)
 
@@ -379,18 +537,48 @@ class ScriptRunner:
                 self.scripts.append(script)
                 self.selectable_scripts.append(script)
 
+        self.apply_on_before_component_callbacks()
+
+    def apply_on_before_component_callbacks(self):
+        for script in self.scripts:
+            on_before = script.on_before_component_elem_id or []
+            on_after = script.on_after_component_elem_id or []
+
+            for elem_id, callback in on_before:
+                if elem_id not in self.on_before_component_elem_id:
+                    self.on_before_component_elem_id[elem_id] = []
+
+                self.on_before_component_elem_id[elem_id].append((callback, script))
+
+            for elem_id, callback in on_after:
+                if elem_id not in self.on_after_component_elem_id:
+                    self.on_after_component_elem_id[elem_id] = []
+
+                self.on_after_component_elem_id[elem_id].append((callback, script))
+
+            on_before.clear()
+            on_after.clear()
+
     def create_script_ui(self, script):
-        import modules.api.models as api_models
 
         script.args_from = len(self.inputs)
         script.args_to = len(self.inputs)
 
+        try:
+            self.create_script_ui_inner(script)
+        except Exception:
+            errors.report(f"Error creating UI for {script.name}: ", exc_info=True)
+
+    def create_script_ui_inner(self, script):
+        import modules.api.models as api_models
+
         controls = wrap_call(script.ui, script.filename, "ui", script.is_img2img)
 
         if controls is None:
             return
 
         script.name = wrap_call(script.title, script.filename, "title", default=script.filename).lower()
+
         api_args = []
 
         for control in controls:
@@ -398,11 +586,15 @@ class ScriptRunner:
 
             arg_info = api_models.ScriptArg(label=control.label or "")
 
-            for field in ("value", "minimum", "maximum", "step", "choices"):
+            for field in ("value", "minimum", "maximum", "step"):
                 v = getattr(control, field, None)
                 if v is not None:
                     setattr(arg_info, field, v)
 
+            choices = getattr(control, 'choices', None)  # as of gradio 3.41, some items in choices are strings, and some are tuples where the first elem is the string
+            if choices is not None:
+                arg_info.choices = [x[0] if isinstance(x, tuple) else x for x in choices]
+
             api_args.append(arg_info)
 
         script.api_info = api_models.ScriptInfo(
@@ -429,15 +621,20 @@ class ScriptRunner:
             if script.alwayson and script.section != section:
                 continue
 
-            with gr.Group(visible=script.alwayson) as group:
-                self.create_script_ui(script)
+            if script.create_group:
+                with gr.Group(visible=script.alwayson) as group:
+                    self.create_script_ui(script)
 
-            script.group = group
+                script.group = group
+            else:
+                self.create_script_ui(script)
 
     def prepare_ui(self):
         self.inputs = [None]
 
     def setup_ui(self):
+        all_titles = [wrap_call(script.title, script.filename, "title") or script.filename for script in self.scripts]
+        self.title_map = {title.lower(): script for title, script in zip(all_titles, self.scripts)}
         self.titles = [wrap_call(script.title, script.filename, "title") or f"{script.filename} [error]" for script in self.selectable_scripts]
 
         self.setup_ui_for_section(None)
@@ -484,6 +681,8 @@ class ScriptRunner:
         self.infotext_fields.append((dropdown, lambda x: gr.update(value=x.get('Script', 'None'))))
         self.infotext_fields.extend([(script.group, onload_script_visibility) for script in self.selectable_scripts])
 
+        self.apply_on_before_component_callbacks()
+
         return self.inputs
 
     def run(self, p, *args):
@@ -577,6 +776,12 @@ class ScriptRunner:
                 errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
 
     def before_component(self, component, **kwargs):
+        for callback, script in self.on_before_component_elem_id.get(kwargs.get("elem_id"), []):
+            try:
+                callback(OnComponent(component=component))
+            except Exception:
+                errors.report(f"Error running on_before_component: {script.filename}", exc_info=True)
+
         for script in self.scripts:
             try:
                 script.before_component(component, **kwargs)
@@ -584,12 +789,21 @@ class ScriptRunner:
                 errors.report(f"Error running before_component: {script.filename}", exc_info=True)
 
     def after_component(self, component, **kwargs):
+        for callback, script in self.on_after_component_elem_id.get(component.elem_id, []):
+            try:
+                callback(OnComponent(component=component))
+            except Exception:
+                errors.report(f"Error running on_after_component: {script.filename}", exc_info=True)
+
         for script in self.scripts:
             try:
                 script.after_component(component, **kwargs)
             except Exception:
                 errors.report(f"Error running after_component: {script.filename}", exc_info=True)
 
+    def script(self, title):
+        return self.title_map.get(title.lower())
+
     def reload_sources(self, cache):
         for si, script in list(enumerate(self.scripts)):
             args_from = script.args_from
@@ -608,7 +822,6 @@ class ScriptRunner:
                     self.scripts[si].args_from = args_from
                     self.scripts[si].args_to = args_to
 
-
     def before_hr(self, p):
         for script in self.alwayson_scripts:
             try:
@@ -617,6 +830,17 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running before_hr: {script.filename}", exc_info=True)
 
+    def setup_scrips(self, p, *, is_ui=True):
+        for script in self.alwayson_scripts:
+            if not is_ui and script.setup_for_ui_only:
+                continue
+
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.setup(p, *script_args)
+            except Exception:
+                errors.report(f"Error running setup: {script.filename}", exc_info=True)
+
 
 scripts_txt2img: ScriptRunner = None
 scripts_img2img: ScriptRunner = None
@@ -631,49 +855,3 @@ def reload_script_body_only():
 
 
 reload_scripts = load_scripts  # compatibility alias
-
-
-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):
-    if scripts_current is not None:
-        scripts_current.before_component(self, **kwargs)
-
-    script_callbacks.before_component_callback(self, **kwargs)
-
-    res = original_IOComponent_init(self, *args, **kwargs)
-
-    add_classes_to_gradio_component(self)
-
-    script_callbacks.after_component_callback(self, **kwargs)
-
-    if scripts_current is not None:
-        scripts_current.after_component(self, **kwargs)
-
-    return res
-
-
-original_IOComponent_init = gr.components.IOComponent.__init__
-gr.components.IOComponent.__init__ = IOComponent_init
-
-
-def BlockContext_init(self, *args, **kwargs):
-    res = original_BlockContext_init(self, *args, **kwargs)
-
-    add_classes_to_gradio_component(self)
-
-    return res
-
-
-original_BlockContext_init = gr.blocks.BlockContext.__init__
-gr.blocks.BlockContext.__init__ = BlockContext_init

modules/scripts_postprocessing.py

@@ -1,13 +1,56 @@
+import dataclasses
 import os
 import gradio as gr
 
 from modules import errors, shared
 
 
+@dataclasses.dataclass
+class PostprocessedImageSharedInfo:
+    target_width: int = None
+    target_height: int = None
+
+
 class PostprocessedImage:
     def __init__(self, image):
         self.image = image
         self.info = {}
+        self.shared = PostprocessedImageSharedInfo()
+        self.extra_images = []
+        self.nametags = []
+        self.disable_processing = False
+        self.caption = None
+
+    def get_suffix(self, used_suffixes=None):
+        used_suffixes = {} if used_suffixes is None else used_suffixes
+        suffix = "-".join(self.nametags)
+        if suffix:
+            suffix = "-" + suffix
+
+        if suffix not in used_suffixes:
+            used_suffixes[suffix] = 1
+            return suffix
+
+        for i in range(1, 100):
+            proposed_suffix = suffix + "-" + str(i)
+
+            if proposed_suffix not in used_suffixes:
+                used_suffixes[proposed_suffix] = 1
+                return proposed_suffix
+
+        return suffix
+
+    def create_copy(self, new_image, *, nametags=None, disable_processing=False):
+        pp = PostprocessedImage(new_image)
+        pp.shared = self.shared
+        pp.nametags = self.nametags.copy()
+        pp.info = self.info.copy()
+        pp.disable_processing = disable_processing
+
+        if nametags is not None:
+            pp.nametags += nametags
+
+        return pp
 
 
 class ScriptPostprocessing:
@@ -42,10 +85,17 @@ class ScriptPostprocessing:
 
         pass
 
-    def image_changed(self):
+    def process_firstpass(self, pp: PostprocessedImage, **args):
+        """
+        Called for all scripts before calling process(). Scripts can examine the image here and set fields
+        of the pp object to communicate things to other scripts.
+        args contains a dictionary with all values returned by components from ui()
+        """
+
         pass
 
-
+    def image_changed(self):
+        pass
 
 
 def wrap_call(func, filename, funcname, *args, default=None, **kwargs):
@@ -118,16 +168,42 @@ class ScriptPostprocessingRunner:
         return inputs
 
     def run(self, pp: PostprocessedImage, args):
-        for script in self.scripts_in_preferred_order():
-            shared.state.job = script.name
+        scripts = []
 
+        for script in self.scripts_in_preferred_order():
             script_args = args[script.args_from:script.args_to]
 
             process_args = {}
             for (name, _component), value in zip(script.controls.items(), script_args):
                 process_args[name] = value
 
-            script.process(pp, **process_args)
+            scripts.append((script, process_args))
+
+        for script, process_args in scripts:
+            script.process_firstpass(pp, **process_args)
+
+        all_images = [pp]
+
+        for script, process_args in scripts:
+            if shared.state.skipped:
+                break
+
+            shared.state.job = script.name
+
+            for single_image in all_images.copy():
+
+                if not single_image.disable_processing:
+                    script.process(single_image, **process_args)
+
+                for extra_image in single_image.extra_images:
+                    if not isinstance(extra_image, PostprocessedImage):
+                        extra_image = single_image.create_copy(extra_image)
+
+                    all_images.append(extra_image)
+
+                single_image.extra_images.clear()
+
+        pp.extra_images = all_images[1:]
 
     def create_args_for_run(self, scripts_args):
         if not self.ui_created:

modules/sd_disable_initialization.py

@@ -3,8 +3,31 @@ import open_clip
 import torch
 import transformers.utils.hub
 
+from modules import shared
 
-class DisableInitialization:
+
+class ReplaceHelper:
+    def __init__(self):
+        self.replaced = []
+
+    def replace(self, obj, field, func):
+        original = getattr(obj, field, None)
+        if original is None:
+            return None
+
+        self.replaced.append((obj, field, original))
+        setattr(obj, field, func)
+
+        return original
+
+    def restore(self):
+        for obj, field, original in self.replaced:
+            setattr(obj, field, original)
+
+        self.replaced.clear()
+
+
+class DisableInitialization(ReplaceHelper):
     """
     When an object of this class enters a `with` block, it starts:
     - preventing torch's layer initialization functions from working
@@ -21,7 +44,7 @@ class DisableInitialization:
     """
 
     def __init__(self, disable_clip=True):
-        self.replaced = []
+        super().__init__()
         self.disable_clip = disable_clip
 
     def replace(self, obj, field, func):
@@ -86,8 +109,124 @@ class DisableInitialization:
             self.transformers_utils_hub_get_from_cache = self.replace(transformers.utils.hub, 'get_from_cache', transformers_utils_hub_get_from_cache)
 
     def __exit__(self, exc_type, exc_val, exc_tb):
-        for obj, field, original in self.replaced:
-            setattr(obj, field, original)
+        self.restore()
 
-        self.replaced.clear()
 
+class InitializeOnMeta(ReplaceHelper):
+    """
+    Context manager that causes all parameters for linear/conv2d/mha layers to be allocated on meta device,
+    which results in those parameters having no values and taking no memory. model.to() will be broken and
+    will need to be repaired by using LoadStateDictOnMeta below when loading params from state dict.
+
+    Usage:
+    ```
+    with sd_disable_initialization.InitializeOnMeta():
+        sd_model = instantiate_from_config(sd_config.model)
+    ```
+    """
+
+    def __enter__(self):
+        if shared.cmd_opts.disable_model_loading_ram_optimization:
+            return
+
+        def set_device(x):
+            x["device"] = "meta"
+            return x
+
+        linear_init = self.replace(torch.nn.Linear, '__init__', lambda *args, **kwargs: linear_init(*args, **set_device(kwargs)))
+        conv2d_init = self.replace(torch.nn.Conv2d, '__init__', lambda *args, **kwargs: conv2d_init(*args, **set_device(kwargs)))
+        mha_init = self.replace(torch.nn.MultiheadAttention, '__init__', lambda *args, **kwargs: mha_init(*args, **set_device(kwargs)))
+        self.replace(torch.nn.Module, 'to', lambda *args, **kwargs: None)
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.restore()
+
+
+class LoadStateDictOnMeta(ReplaceHelper):
+    """
+    Context manager that allows to read parameters from state_dict into a model that has some of its parameters in the meta device.
+    As those parameters are read from state_dict, they will be deleted from it, so by the end state_dict will be mostly empty, to save memory.
+    Meant to be used together with InitializeOnMeta above.
+
+    Usage:
+    ```
+    with sd_disable_initialization.LoadStateDictOnMeta(state_dict):
+        model.load_state_dict(state_dict, strict=False)
+    ```
+    """
+
+    def __init__(self, state_dict, device, weight_dtype_conversion=None):
+        super().__init__()
+        self.state_dict = state_dict
+        self.device = device
+        self.weight_dtype_conversion = weight_dtype_conversion or {}
+        self.default_dtype = self.weight_dtype_conversion.get('')
+
+    def get_weight_dtype(self, key):
+        key_first_term, _ = key.split('.', 1)
+        return self.weight_dtype_conversion.get(key_first_term, self.default_dtype)
+
+    def __enter__(self):
+        if shared.cmd_opts.disable_model_loading_ram_optimization:
+            return
+
+        sd = self.state_dict
+        device = self.device
+
+        def load_from_state_dict(original, module, state_dict, prefix, *args, **kwargs):
+            used_param_keys = []
+
+            for name, param in module._parameters.items():
+                if param is None:
+                    continue
+
+                key = prefix + name
+                sd_param = sd.pop(key, None)
+                if sd_param is not None:
+                    state_dict[key] = sd_param.to(dtype=self.get_weight_dtype(key))
+                    used_param_keys.append(key)
+
+                if param.is_meta:
+                    dtype = sd_param.dtype if sd_param is not None else param.dtype
+                    module._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
+
+            for name in module._buffers:
+                key = prefix + name
+
+                sd_param = sd.pop(key, None)
+                if sd_param is not None:
+                    state_dict[key] = sd_param
+                    used_param_keys.append(key)
+
+            original(module, state_dict, prefix, *args, **kwargs)
+
+            for key in used_param_keys:
+                state_dict.pop(key, None)
+
+        def load_state_dict(original, module, state_dict, strict=True):
+            """torch makes a lot of copies of the dictionary with weights, so just deleting entries from state_dict does not help
+            because the same values are stored in multiple copies of the dict. The trick used here is to give torch a dict with
+            all weights on meta device, i.e. deleted, and then it doesn't matter how many copies torch makes.
+
+            In _load_from_state_dict, the correct weight will be obtained from a single dict with the right weights (sd).
+
+            The dangerous thing about this is if _load_from_state_dict is not called, (if some exotic module overloads
+            the function and does not call the original) the state dict will just fail to load because weights
+            would be on the meta device.
+            """
+
+            if state_dict == sd:
+                state_dict = {k: v.to(device="meta", dtype=v.dtype) for k, v in state_dict.items()}
+
+            original(module, state_dict, strict=strict)
+
+        module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
+        module_load_from_state_dict = self.replace(torch.nn.Module, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(module_load_from_state_dict, *args, **kwargs))
+        linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
+        conv2d_load_from_state_dict = self.replace(torch.nn.Conv2d, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(conv2d_load_from_state_dict, *args, **kwargs))
+        mha_load_from_state_dict = self.replace(torch.nn.MultiheadAttention, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(mha_load_from_state_dict, *args, **kwargs))
+        layer_norm_load_from_state_dict = self.replace(torch.nn.LayerNorm, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(layer_norm_load_from_state_dict, *args, **kwargs))
+        group_norm_load_from_state_dict = self.replace(torch.nn.GroupNorm, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(group_norm_load_from_state_dict, *args, **kwargs))
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.restore()

modules/sd_hijack.py

@@ -2,15 +2,15 @@ import torch
 from torch.nn.functional import silu
 from types import MethodType
 
-import modules.textual_inversion.textual_inversion
-from modules import devices, sd_hijack_optimizations, shared, script_callbacks, errors, sd_unet
+from modules import devices, sd_hijack_optimizations, shared, script_callbacks, errors, sd_unet, patches
 from modules.hypernetworks import hypernetwork
 from modules.shared import cmd_opts
-from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
+from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr, xlmr_m18
 
 import ldm.modules.attention
 import ldm.modules.diffusionmodules.model
 import ldm.modules.diffusionmodules.openaimodel
+import ldm.models.diffusion.ddpm
 import ldm.models.diffusion.ddim
 import ldm.models.diffusion.plms
 import ldm.modules.encoders.modules
@@ -30,12 +30,20 @@ ldm.modules.attention.MemoryEfficientCrossAttention = ldm.modules.attention.Cros
 ldm.modules.attention.BasicTransformerBlock.ATTENTION_MODES["softmax-xformers"] = ldm.modules.attention.CrossAttention
 
 # silence new console spam from SD2
-ldm.modules.attention.print = lambda *args: None
-ldm.modules.diffusionmodules.model.print = lambda *args: None
+ldm.modules.attention.print = shared.ldm_print
+ldm.modules.diffusionmodules.model.print = shared.ldm_print
+ldm.util.print = shared.ldm_print
+ldm.models.diffusion.ddpm.print = shared.ldm_print
 
 optimizers = []
 current_optimizer: sd_hijack_optimizations.SdOptimization = None
 
+ldm_patched_forward = sd_unet.create_unet_forward(ldm.modules.diffusionmodules.openaimodel.UNetModel.forward)
+ldm_original_forward = patches.patch(__file__, ldm.modules.diffusionmodules.openaimodel.UNetModel, "forward", ldm_patched_forward)
+
+sgm_patched_forward = sd_unet.create_unet_forward(sgm.modules.diffusionmodules.openaimodel.UNetModel.forward)
+sgm_original_forward = patches.patch(__file__, sgm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sgm_patched_forward)
+
 
 def list_optimizers():
     new_optimizers = script_callbacks.list_optimizers_callback()
@@ -164,12 +172,13 @@ class StableDiffusionModelHijack:
     clip = None
     optimization_method = None
 
-    embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase()
-
     def __init__(self):
+        import modules.textual_inversion.textual_inversion
+
         self.extra_generation_params = {}
         self.comments = []
 
+        self.embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase()
         self.embedding_db.add_embedding_dir(cmd_opts.embeddings_dir)
 
     def apply_optimizations(self, option=None):
@@ -179,6 +188,20 @@ class StableDiffusionModelHijack:
             errors.display(e, "applying cross attention optimization")
             undo_optimizations()
 
+    def convert_sdxl_to_ssd(self, m):
+        """Converts an SDXL model to a Segmind Stable Diffusion model (see https://huggingface.co/segmind/SSD-1B)"""
+
+        delattr(m.model.diffusion_model.middle_block, '1')
+        delattr(m.model.diffusion_model.middle_block, '2')
+        for i in ['9', '8', '7', '6', '5', '4']:
+            delattr(m.model.diffusion_model.input_blocks[7][1].transformer_blocks, i)
+            delattr(m.model.diffusion_model.input_blocks[8][1].transformer_blocks, i)
+            delattr(m.model.diffusion_model.output_blocks[0][1].transformer_blocks, i)
+            delattr(m.model.diffusion_model.output_blocks[1][1].transformer_blocks, i)
+        delattr(m.model.diffusion_model.output_blocks[4][1].transformer_blocks, '1')
+        delattr(m.model.diffusion_model.output_blocks[5][1].transformer_blocks, '1')
+        devices.torch_gc()
+
     def hijack(self, m):
         conditioner = getattr(m, 'conditioner', None)
         if conditioner:
@@ -197,7 +220,7 @@ class StableDiffusionModelHijack:
                     conditioner.embedders[i] = sd_hijack_clip.FrozenCLIPEmbedderForSDXLWithCustomWords(embedder, self)
                     text_cond_models.append(conditioner.embedders[i])
                 if typename == 'FrozenOpenCLIPEmbedder2':
-                    embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self)
+                    embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self, textual_inversion_key='clip_g')
                     conditioner.embedders[i] = sd_hijack_open_clip.FrozenOpenCLIPEmbedder2WithCustomWords(embedder, self)
                     text_cond_models.append(conditioner.embedders[i])
 
@@ -206,7 +229,7 @@ class StableDiffusionModelHijack:
             else:
                 m.cond_stage_model = conditioner
 
-        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation or type(m.cond_stage_model) == xlmr_m18.BertSeriesModelWithTransformation:
             model_embeddings = m.cond_stage_model.roberta.embeddings
             model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
             m.cond_stage_model = sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords(m.cond_stage_model, self)
@@ -237,13 +260,34 @@ class StableDiffusionModelHijack:
 
         self.layers = flatten(m)
 
-        if not hasattr(ldm.modules.diffusionmodules.openaimodel, 'copy_of_UNetModel_forward_for_webui'):
-            ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui = ldm.modules.diffusionmodules.openaimodel.UNetModel.forward
+        import modules.models.diffusion.ddpm_edit
+
+        if isinstance(m, ldm.models.diffusion.ddpm.LatentDiffusion):
+            sd_unet.original_forward = ldm_original_forward
+        elif isinstance(m, modules.models.diffusion.ddpm_edit.LatentDiffusion):
+            sd_unet.original_forward = ldm_original_forward
+        elif isinstance(m, sgm.models.diffusion.DiffusionEngine):
+            sd_unet.original_forward = sgm_original_forward
+        else:
+            sd_unet.original_forward = None
 
-        ldm.modules.diffusionmodules.openaimodel.UNetModel.forward = sd_unet.UNetModel_forward
 
     def undo_hijack(self, m):
-        if type(m.cond_stage_model) == sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords:
+        conditioner = getattr(m, 'conditioner', None)
+        if conditioner:
+            for i in range(len(conditioner.embedders)):
+                embedder = conditioner.embedders[i]
+                if isinstance(embedder, (sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords, sd_hijack_open_clip.FrozenOpenCLIPEmbedder2WithCustomWords)):
+                    embedder.wrapped.model.token_embedding = embedder.wrapped.model.token_embedding.wrapped
+                    conditioner.embedders[i] = embedder.wrapped
+                if isinstance(embedder, sd_hijack_clip.FrozenCLIPEmbedderForSDXLWithCustomWords):
+                    embedder.wrapped.transformer.text_model.embeddings.token_embedding = embedder.wrapped.transformer.text_model.embeddings.token_embedding.wrapped
+                    conditioner.embedders[i] = embedder.wrapped
+
+            if hasattr(m, 'cond_stage_model'):
+                delattr(m, 'cond_stage_model')
+
+        elif type(m.cond_stage_model) == sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords:
             m.cond_stage_model = m.cond_stage_model.wrapped
 
         elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
@@ -263,7 +307,6 @@ class StableDiffusionModelHijack:
         self.layers = None
         self.clip = None
 
-        ldm.modules.diffusionmodules.openaimodel.UNetModel.forward = ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui
 
     def apply_circular(self, enable):
         if self.circular_enabled == enable:
@@ -292,10 +335,11 @@ class StableDiffusionModelHijack:
 
 
 class EmbeddingsWithFixes(torch.nn.Module):
-    def __init__(self, wrapped, embeddings):
+    def __init__(self, wrapped, embeddings, textual_inversion_key='clip_l'):
         super().__init__()
         self.wrapped = wrapped
         self.embeddings = embeddings
+        self.textual_inversion_key = textual_inversion_key
 
     def forward(self, input_ids):
         batch_fixes = self.embeddings.fixes
@@ -309,7 +353,8 @@ class EmbeddingsWithFixes(torch.nn.Module):
         vecs = []
         for fixes, tensor in zip(batch_fixes, inputs_embeds):
             for offset, embedding in fixes:
-                emb = devices.cond_cast_unet(embedding.vec)
+                vec = embedding.vec[self.textual_inversion_key] if isinstance(embedding.vec, dict) else embedding.vec
+                emb = devices.cond_cast_unet(vec)
                 emb_len = min(tensor.shape[0] - offset - 1, emb.shape[0])
                 tensor = torch.cat([tensor[0:offset + 1], emb[0:emb_len], tensor[offset + 1 + emb_len:]])
 

modules/sd_hijack_clip.py

@@ -161,7 +161,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
                     position += 1
                     continue
 
-                emb_len = int(embedding.vec.shape[0])
+                emb_len = int(embedding.vectors)
                 if len(chunk.tokens) + emb_len > self.chunk_length:
                     next_chunk()
 
@@ -245,6 +245,8 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
                 hashes.append(f"{name}: {shorthash}")
 
             if hashes:
+                if self.hijack.extra_generation_params.get("TI hashes"):
+                    hashes.append(self.hijack.extra_generation_params.get("TI hashes"))
                 self.hijack.extra_generation_params["TI hashes"] = ", ".join(hashes)
 
         if getattr(self.wrapped, 'return_pooled', False):

modules/sd_hijack_inpainting.py

@@ -1,97 +0,0 @@
-import torch
-
-import ldm.models.diffusion.ddpm
-import ldm.models.diffusion.ddim
-import ldm.models.diffusion.plms
-
-from ldm.models.diffusion.ddim import noise_like
-from ldm.models.diffusion.sampling_util import norm_thresholding
-
-
-@torch.no_grad()
-def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
-                  temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
-                  unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None, dynamic_threshold=None):
-    b, *_, device = *x.shape, x.device
-
-    def get_model_output(x, t):
-        if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
-            e_t = self.model.apply_model(x, t, c)
-        else:
-            x_in = torch.cat([x] * 2)
-            t_in = torch.cat([t] * 2)
-
-            if isinstance(c, dict):
-                assert isinstance(unconditional_conditioning, dict)
-                c_in = {}
-                for k in c:
-                    if isinstance(c[k], list):
-                        c_in[k] = [
-                            torch.cat([unconditional_conditioning[k][i], c[k][i]])
-                            for i in range(len(c[k]))
-                        ]
-                    else:
-                        c_in[k] = torch.cat([unconditional_conditioning[k], c[k]])
-            else:
-                c_in = torch.cat([unconditional_conditioning, c])
-
-            e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
-            e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
-
-        if score_corrector is not None:
-            assert self.model.parameterization == "eps"
-            e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
-
-        return e_t
-
-    alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
-    alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
-    sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
-    sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
-
-    def get_x_prev_and_pred_x0(e_t, index):
-        # select parameters corresponding to the currently considered timestep
-        a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
-        a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
-        sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
-        sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
-
-        # current prediction for x_0
-        pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
-        if quantize_denoised:
-            pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
-        if dynamic_threshold is not None:
-            pred_x0 = norm_thresholding(pred_x0, dynamic_threshold)
-        # direction pointing to x_t
-        dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
-        noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
-        if noise_dropout > 0.:
-            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
-        x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
-        return x_prev, pred_x0
-
-    e_t = get_model_output(x, t)
-    if len(old_eps) == 0:
-        # Pseudo Improved Euler (2nd order)
-        x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t, index)
-        e_t_next = get_model_output(x_prev, t_next)
-        e_t_prime = (e_t + e_t_next) / 2
-    elif len(old_eps) == 1:
-        # 2nd order Pseudo Linear Multistep (Adams-Bashforth)
-        e_t_prime = (3 * e_t - old_eps[-1]) / 2
-    elif len(old_eps) == 2:
-        # 3nd order Pseudo Linear Multistep (Adams-Bashforth)
-        e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
-    elif len(old_eps) >= 3:
-        # 4nd order Pseudo Linear Multistep (Adams-Bashforth)
-        e_t_prime = (55 * e_t - 59 * old_eps[-1] + 37 * old_eps[-2] - 9 * old_eps[-3]) / 24
-
-    x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index)
-
-    return x_prev, pred_x0, e_t
-
-
-def do_inpainting_hijack():
-    # p_sample_plms is needed because PLMS can't work with dicts as conditionings
-
-    ldm.models.diffusion.plms.PLMSSampler.p_sample_plms = p_sample_plms

modules/sd_hijack_optimizations.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 import math
 import psutil
+import platform
 
 import torch
 from torch import einsum
@@ -94,7 +95,10 @@ class SdOptimizationSdp(SdOptimizationSdpNoMem):
 class SdOptimizationSubQuad(SdOptimization):
     name = "sub-quadratic"
     cmd_opt = "opt_sub_quad_attention"
-    priority = 10
+
+    @property
+    def priority(self):
+        return 1000 if shared.device.type == 'mps' else 10
 
     def apply(self):
         ldm.modules.attention.CrossAttention.forward = sub_quad_attention_forward
@@ -120,7 +124,7 @@ class SdOptimizationInvokeAI(SdOptimization):
 
     @property
     def priority(self):
-        return 1000 if not torch.cuda.is_available() else 10
+        return 1000 if shared.device.type != 'mps' and not torch.cuda.is_available() else 10
 
     def apply(self):
         ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_invokeAI
@@ -427,7 +431,10 @@ def sub_quad_attention(q, k, v, q_chunk_size=1024, kv_chunk_size=None, kv_chunk_
     qk_matmul_size_bytes = batch_x_heads * bytes_per_token * q_tokens * k_tokens
 
     if chunk_threshold is None:
-        chunk_threshold_bytes = int(get_available_vram() * 0.9) if q.device.type == 'mps' else int(get_available_vram() * 0.7)
+        if q.device.type == 'mps':
+            chunk_threshold_bytes = 268435456 * (2 if platform.processor() == 'i386' else bytes_per_token)
+        else:
+            chunk_threshold_bytes = int(get_available_vram() * 0.7)
     elif chunk_threshold == 0:
         chunk_threshold_bytes = None
     else:

modules/sd_models.py

@@ -1,23 +1,22 @@
 import collections
 import os.path
 import sys
-import gc
 import threading
 
 import torch
 import re
 import safetensors.torch
-from omegaconf import OmegaConf
+from omegaconf import OmegaConf, ListConfig
 from os import mkdir
 from urllib import request
 import ldm.modules.midas as midas
 
 from ldm.util import instantiate_from_config
 
-from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl
-from modules.sd_hijack_inpainting import do_inpainting_hijack
+from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl, cache, extra_networks, processing, lowvram, sd_hijack, patches
 from modules.timer import Timer
 import tomesd
+import numpy as np
 
 model_dir = "Stable-diffusion"
 model_path = os.path.abspath(os.path.join(paths.models_path, model_dir))
@@ -28,13 +27,34 @@ checkpoint_alisases = checkpoint_aliases  # for compatibility with old name
 checkpoints_loaded = collections.OrderedDict()
 
 
+def replace_key(d, key, new_key, value):
+    keys = list(d.keys())
+
+    d[new_key] = value
+
+    if key not in keys:
+        return d
+
+    index = keys.index(key)
+    keys[index] = new_key
+
+    new_d = {k: d[k] for k in keys}
+
+    d.clear()
+    d.update(new_d)
+    return d
+
+
 class CheckpointInfo:
     def __init__(self, filename):
         self.filename = filename
         abspath = os.path.abspath(filename)
+        abs_ckpt_dir = os.path.abspath(shared.cmd_opts.ckpt_dir) if shared.cmd_opts.ckpt_dir is not None else None
 
-        if shared.cmd_opts.ckpt_dir is not None and abspath.startswith(shared.cmd_opts.ckpt_dir):
-            name = abspath.replace(shared.cmd_opts.ckpt_dir, '')
+        self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
+
+        if abs_ckpt_dir and abspath.startswith(abs_ckpt_dir):
+            name = abspath.replace(abs_ckpt_dir, '')
         elif abspath.startswith(model_path):
             name = abspath.replace(model_path, '')
         else:
@@ -43,6 +63,19 @@ class CheckpointInfo:
         if name.startswith("\\") or name.startswith("/"):
             name = name[1:]
 
+        def read_metadata():
+            metadata = read_metadata_from_safetensors(filename)
+            self.modelspec_thumbnail = metadata.pop('modelspec.thumbnail', None)
+
+            return metadata
+
+        self.metadata = {}
+        if self.is_safetensors:
+            try:
+                self.metadata = cache.cached_data_for_file('safetensors-metadata', "checkpoint/" + name, filename, read_metadata)
+            except Exception as e:
+                errors.display(e, f"reading metadata for {filename}")
+
         self.name = name
         self.name_for_extra = os.path.splitext(os.path.basename(filename))[0]
         self.model_name = os.path.splitext(name.replace("/", "_").replace("\\", "_"))[0]
@@ -52,17 +85,11 @@ class CheckpointInfo:
         self.shorthash = self.sha256[0:10] if self.sha256 else None
 
         self.title = name if self.shorthash is None else f'{name} [{self.shorthash}]'
+        self.short_title = self.name_for_extra if self.shorthash is None else f'{self.name_for_extra} [{self.shorthash}]'
 
-        self.ids = [self.hash, self.model_name, self.title, name, f'{name} [{self.hash}]'] + ([self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]'] if self.shorthash else [])
-
-        self.metadata = {}
-
-        _, ext = os.path.splitext(self.filename)
-        if ext.lower() == ".safetensors":
-            try:
-                self.metadata = read_metadata_from_safetensors(filename)
-            except Exception as e:
-                errors.display(e, f"reading checkpoint metadata: {filename}")
+        self.ids = [self.hash, self.model_name, self.title, name, self.name_for_extra, f'{name} [{self.hash}]']
+        if self.shorthash:
+            self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]', f'{self.name_for_extra} [{self.shorthash}]']
 
     def register(self):
         checkpoints_list[self.title] = self
@@ -74,13 +101,20 @@ class CheckpointInfo:
         if self.sha256 is None:
             return
 
-        self.shorthash = self.sha256[0:10]
+        shorthash = self.sha256[0:10]
+        if self.shorthash == self.sha256[0:10]:
+            return self.shorthash
+
+        self.shorthash = shorthash
 
         if self.shorthash not in self.ids:
-            self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]']
+            self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]', f'{self.name_for_extra} [{self.shorthash}]']
 
-        checkpoints_list.pop(self.title)
+        old_title = self.title
         self.title = f'{self.name} [{self.shorthash}]'
+        self.short_title = f'{self.name_for_extra} [{self.shorthash}]'
+
+        replace_key(checkpoints_list, old_title, self.title, self)
         self.register()
 
         return self.shorthash
@@ -96,19 +130,16 @@ except Exception:
 
 
 def setup_model():
+    """called once at startup to do various one-time tasks related to SD models"""
+
     os.makedirs(model_path, exist_ok=True)
 
     enable_midas_autodownload()
+    patch_given_betas()
 
 
-def checkpoint_tiles():
-    def convert(name):
-        return int(name) if name.isdigit() else name.lower()
-
-    def alphanumeric_key(key):
-        return [convert(c) for c in re.split('([0-9]+)', key)]
-
-    return sorted([x.title for x in checkpoints_list.values()], key=alphanumeric_key)
+def checkpoint_tiles(use_short=False):
+    return [x.short_title if use_short else x.title for x in checkpoints_list.values()]
 
 
 def list_models():
@@ -131,12 +162,18 @@ def list_models():
     elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:
         print(f"Checkpoint in --ckpt argument not found (Possible it was moved to {model_path}: {cmd_ckpt}", file=sys.stderr)
 
-    for filename in sorted(model_list, key=str.lower):
+    for filename in model_list:
         checkpoint_info = CheckpointInfo(filename)
         checkpoint_info.register()
 
 
+re_strip_checksum = re.compile(r"\s*\[[^]]+]\s*$")
+
+
 def get_closet_checkpoint_match(search_string):
+    if not search_string:
+        return None
+
     checkpoint_info = checkpoint_aliases.get(search_string, None)
     if checkpoint_info is not None:
         return checkpoint_info
@@ -145,6 +182,11 @@ def get_closet_checkpoint_match(search_string):
     if found:
         return found[0]
 
+    search_string_without_checksum = re.sub(re_strip_checksum, '', search_string)
+    found = sorted([info for info in checkpoints_list.values() if search_string_without_checksum in info.title], key=lambda x: len(x.title))
+    if found:
+        return found[0]
+
     return None
 
 
@@ -188,15 +230,19 @@ def select_checkpoint():
     return checkpoint_info
 
 
-checkpoint_dict_replacements = {
+checkpoint_dict_replacements_sd1 = {
     'cond_stage_model.transformer.embeddings.': 'cond_stage_model.transformer.text_model.embeddings.',
     'cond_stage_model.transformer.encoder.': 'cond_stage_model.transformer.text_model.encoder.',
     'cond_stage_model.transformer.final_layer_norm.': 'cond_stage_model.transformer.text_model.final_layer_norm.',
 }
 
+checkpoint_dict_replacements_sd2_turbo = { # Converts SD 2.1 Turbo from SGM to LDM format.
+    'conditioner.embedders.0.': 'cond_stage_model.',
+}
 
-def transform_checkpoint_dict_key(k):
-    for text, replacement in checkpoint_dict_replacements.items():
+
+def transform_checkpoint_dict_key(k, replacements):
+    for text, replacement in replacements.items():
         if k.startswith(text):
             k = replacement + k[len(text):]
 
@@ -207,9 +253,14 @@ def get_state_dict_from_checkpoint(pl_sd):
     pl_sd = pl_sd.pop("state_dict", pl_sd)
     pl_sd.pop("state_dict", None)
 
+    is_sd2_turbo = 'conditioner.embedders.0.model.ln_final.weight' in pl_sd and pl_sd['conditioner.embedders.0.model.ln_final.weight'].size()[0] == 1024
+
     sd = {}
     for k, v in pl_sd.items():
-        new_key = transform_checkpoint_dict_key(k)
+        if is_sd2_turbo:
+            new_key = transform_checkpoint_dict_key(k, checkpoint_dict_replacements_sd2_turbo)
+        else:
+            new_key = transform_checkpoint_dict_key(k, checkpoint_dict_replacements_sd1)
 
         if new_key is not None:
             sd[new_key] = v
@@ -271,6 +322,8 @@ def get_checkpoint_state_dict(checkpoint_info: CheckpointInfo, timer):
     if checkpoint_info in checkpoints_loaded:
         # use checkpoint cache
         print(f"Loading weights [{sd_model_hash}] from cache")
+        # move to end as latest
+        checkpoints_loaded.move_to_end(checkpoint_info)
         return checkpoints_loaded[checkpoint_info]
 
     print(f"Loading weights [{sd_model_hash}] from {checkpoint_info.filename}")
@@ -280,11 +333,27 @@ def get_checkpoint_state_dict(checkpoint_info: CheckpointInfo, timer):
     return res
 
 
+class SkipWritingToConfig:
+    """This context manager prevents load_model_weights from writing checkpoint name to the config when it loads weight."""
+
+    skip = False
+    previous = None
+
+    def __enter__(self):
+        self.previous = SkipWritingToConfig.skip
+        SkipWritingToConfig.skip = True
+        return self
+
+    def __exit__(self, exc_type, exc_value, exc_traceback):
+        SkipWritingToConfig.skip = self.previous
+
+
 def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer):
     sd_model_hash = checkpoint_info.calculate_shorthash()
     timer.record("calculate hash")
 
-    shared.opts.data["sd_model_checkpoint"] = checkpoint_info.title
+    if not SkipWritingToConfig.skip:
+        shared.opts.data["sd_model_checkpoint"] = checkpoint_info.title
 
     if state_dict is None:
         state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
@@ -292,23 +361,31 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
     model.is_sdxl = hasattr(model, 'conditioner')
     model.is_sd2 = not model.is_sdxl and hasattr(model.cond_stage_model, 'model')
     model.is_sd1 = not model.is_sdxl and not model.is_sd2
-
+    model.is_ssd = model.is_sdxl and 'model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight' not in state_dict.keys()
     if model.is_sdxl:
         sd_models_xl.extend_sdxl(model)
 
-    model.load_state_dict(state_dict, strict=False)
-    del state_dict
-    timer.record("apply weights to model")
+    if model.is_ssd:
+        sd_hijack.model_hijack.convert_sdxl_to_ssd(model)
 
     if shared.opts.sd_checkpoint_cache > 0:
         # cache newly loaded model
-        checkpoints_loaded[checkpoint_info] = model.state_dict().copy()
+        checkpoints_loaded[checkpoint_info] = state_dict.copy()
+
+    model.load_state_dict(state_dict, strict=False)
+    timer.record("apply weights to model")
+
+    del state_dict
 
     if shared.cmd_opts.opt_channelslast:
         model.to(memory_format=torch.channels_last)
         timer.record("apply channels_last")
 
-    if not shared.cmd_opts.no_half:
+    if shared.cmd_opts.no_half:
+        model.float()
+        devices.dtype_unet = torch.float32
+        timer.record("apply float()")
+    else:
         vae = model.first_stage_model
         depth_model = getattr(model, 'depth_model', None)
 
@@ -324,9 +401,9 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
         if depth_model:
             model.depth_model = depth_model
 
+        devices.dtype_unet = torch.float16
         timer.record("apply half()")
 
-    devices.dtype_unet = torch.float16 if model.is_sdxl and not shared.cmd_opts.no_half else model.model.diffusion_model.dtype
     devices.unet_needs_upcast = shared.cmd_opts.upcast_sampling and devices.dtype == torch.float16 and devices.dtype_unet == torch.float16
 
     model.first_stage_model.to(devices.dtype_vae)
@@ -346,7 +423,7 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
 
     sd_vae.delete_base_vae()
     sd_vae.clear_loaded_vae()
-    vae_file, vae_source = sd_vae.resolve_vae(checkpoint_info.filename)
+    vae_file, vae_source = sd_vae.resolve_vae(checkpoint_info.filename).tuple()
     sd_vae.load_vae(model, vae_file, vae_source)
     timer.record("load VAE")
 
@@ -394,6 +471,20 @@ def enable_midas_autodownload():
     midas.api.load_model = load_model_wrapper
 
 
+def patch_given_betas():
+    import ldm.models.diffusion.ddpm
+
+    def patched_register_schedule(*args, **kwargs):
+        """a modified version of register_schedule function that converts plain list from Omegaconf into numpy"""
+
+        if isinstance(args[1], ListConfig):
+            args = (args[0], np.array(args[1]), *args[2:])
+
+        original_register_schedule(*args, **kwargs)
+
+    original_register_schedule = patches.patch(__name__, ldm.models.diffusion.ddpm.DDPM, 'register_schedule', patched_register_schedule)
+
+
 def repair_config(sd_config):
 
     if not hasattr(sd_config.model.params, "use_ema"):
@@ -423,6 +514,7 @@ sdxl_refiner_clip_weight = 'conditioner.embedders.0.model.ln_final.weight'
 class SdModelData:
     def __init__(self):
         self.sd_model = None
+        self.loaded_sd_models = []
         self.was_loaded_at_least_once = False
         self.lock = threading.Lock()
 
@@ -437,6 +529,7 @@ class SdModelData:
 
                 try:
                     load_model()
+
                 except Exception as e:
                     errors.display(e, "loading stable diffusion model", full_traceback=True)
                     print("", file=sys.stderr)
@@ -445,14 +538,30 @@ class SdModelData:
 
         return self.sd_model
 
-    def set_sd_model(self, v):
+    def set_sd_model(self, v, already_loaded=False):
         self.sd_model = v
+        if already_loaded:
+            sd_vae.base_vae = getattr(v, "base_vae", None)
+            sd_vae.loaded_vae_file = getattr(v, "loaded_vae_file", None)
+            sd_vae.checkpoint_info = v.sd_checkpoint_info
+
+        try:
+            self.loaded_sd_models.remove(v)
+        except ValueError:
+            pass
+
+        if v is not None:
+            self.loaded_sd_models.insert(0, v)
 
 
 model_data = SdModelData()
 
 
 def get_empty_cond(sd_model):
+
+    p = processing.StableDiffusionProcessingTxt2Img()
+    extra_networks.activate(p, {})
+
     if hasattr(sd_model, 'conditioner'):
         d = sd_model.get_learned_conditioning([""])
         return d['crossattn']
@@ -460,20 +569,46 @@ def get_empty_cond(sd_model):
         return sd_model.cond_stage_model([""])
 
 
+def send_model_to_cpu(m):
+    if m.lowvram:
+        lowvram.send_everything_to_cpu()
+    else:
+        m.to(devices.cpu)
+
+    devices.torch_gc()
+
+
+def model_target_device(m):
+    if lowvram.is_needed(m):
+        return devices.cpu
+    else:
+        return devices.device
+
+
+def send_model_to_device(m):
+    lowvram.apply(m)
+
+    if not m.lowvram:
+        m.to(shared.device)
+
+
+def send_model_to_trash(m):
+    m.to(device="meta")
+    devices.torch_gc()
+
 
 def load_model(checkpoint_info=None, already_loaded_state_dict=None):
-    from modules import lowvram, sd_hijack
+    from modules import sd_hijack
     checkpoint_info = checkpoint_info or select_checkpoint()
 
+    timer = Timer()
+
     if model_data.sd_model:
-        sd_hijack.model_hijack.undo_hijack(model_data.sd_model)
+        send_model_to_trash(model_data.sd_model)
         model_data.sd_model = None
-        gc.collect()
         devices.torch_gc()
 
-    do_inpainting_hijack()
-
-    timer = Timer()
+    timer.record("unload existing model")
 
     if already_loaded_state_dict is not None:
         state_dict = already_loaded_state_dict
@@ -495,25 +630,35 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None):
     sd_model = None
     try:
         with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd or shared.cmd_opts.do_not_download_clip):
-            sd_model = instantiate_from_config(sd_config.model)
-    except Exception:
-        pass
+            with sd_disable_initialization.InitializeOnMeta():
+                sd_model = instantiate_from_config(sd_config.model)
+
+    except Exception as e:
+        errors.display(e, "creating model quickly", full_traceback=True)
 
     if sd_model is None:
         print('Failed to create model quickly; will retry using slow method.', file=sys.stderr)
-        sd_model = instantiate_from_config(sd_config.model)
+
+        with sd_disable_initialization.InitializeOnMeta():
+            sd_model = instantiate_from_config(sd_config.model)
 
     sd_model.used_config = checkpoint_config
 
     timer.record("create model")
 
-    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
-
-    if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
-        lowvram.setup_for_low_vram(sd_model, shared.cmd_opts.medvram)
+    if shared.cmd_opts.no_half:
+        weight_dtype_conversion = None
     else:
-        sd_model.to(shared.device)
+        weight_dtype_conversion = {
+            'first_stage_model': None,
+            '': torch.float16,
+        }
 
+    with sd_disable_initialization.LoadStateDictOnMeta(state_dict, device=model_target_device(sd_model), weight_dtype_conversion=weight_dtype_conversion):
+        load_model_weights(sd_model, checkpoint_info, state_dict, timer)
+    timer.record("load weights from state dict")
+
+    send_model_to_device(sd_model)
     timer.record("move model to device")
 
     sd_hijack.model_hijack.hijack(sd_model)
@@ -521,7 +666,7 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None):
     timer.record("hijack")
 
     sd_model.eval()
-    model_data.sd_model = sd_model
+    model_data.set_sd_model(sd_model)
     model_data.was_loaded_at_least_once = True
 
     sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)  # Reload embeddings after model load as they may or may not fit the model
@@ -542,10 +687,70 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None):
     return sd_model
 
 
+def reuse_model_from_already_loaded(sd_model, checkpoint_info, timer):
+    """
+    Checks if the desired checkpoint from checkpoint_info is not already loaded in model_data.loaded_sd_models.
+    If it is loaded, returns that (moving it to GPU if necessary, and moving the currently loadded model to CPU if necessary).
+    If not, returns the model that can be used to load weights from checkpoint_info's file.
+    If no such model exists, returns None.
+    Additionaly deletes loaded models that are over the limit set in settings (sd_checkpoints_limit).
+    """
+
+    already_loaded = None
+    for i in reversed(range(len(model_data.loaded_sd_models))):
+        loaded_model = model_data.loaded_sd_models[i]
+        if loaded_model.sd_checkpoint_info.filename == checkpoint_info.filename:
+            already_loaded = loaded_model
+            continue
+
+        if len(model_data.loaded_sd_models) > shared.opts.sd_checkpoints_limit > 0:
+            print(f"Unloading model {len(model_data.loaded_sd_models)} over the limit of {shared.opts.sd_checkpoints_limit}: {loaded_model.sd_checkpoint_info.title}")
+            model_data.loaded_sd_models.pop()
+            send_model_to_trash(loaded_model)
+            timer.record("send model to trash")
+
+        if shared.opts.sd_checkpoints_keep_in_cpu:
+            send_model_to_cpu(sd_model)
+            timer.record("send model to cpu")
+
+    if already_loaded is not None:
+        send_model_to_device(already_loaded)
+        timer.record("send model to device")
+
+        model_data.set_sd_model(already_loaded, already_loaded=True)
+
+        if not SkipWritingToConfig.skip:
+            shared.opts.data["sd_model_checkpoint"] = already_loaded.sd_checkpoint_info.title
+            shared.opts.data["sd_checkpoint_hash"] = already_loaded.sd_checkpoint_info.sha256
+
+        print(f"Using already loaded model {already_loaded.sd_checkpoint_info.title}: done in {timer.summary()}")
+        sd_vae.reload_vae_weights(already_loaded)
+        return model_data.sd_model
+    elif shared.opts.sd_checkpoints_limit > 1 and len(model_data.loaded_sd_models) < shared.opts.sd_checkpoints_limit:
+        print(f"Loading model {checkpoint_info.title} ({len(model_data.loaded_sd_models) + 1} out of {shared.opts.sd_checkpoints_limit})")
+
+        model_data.sd_model = None
+        load_model(checkpoint_info)
+        return model_data.sd_model
+    elif len(model_data.loaded_sd_models) > 0:
+        sd_model = model_data.loaded_sd_models.pop()
+        model_data.sd_model = sd_model
+
+        sd_vae.base_vae = getattr(sd_model, "base_vae", None)
+        sd_vae.loaded_vae_file = getattr(sd_model, "loaded_vae_file", None)
+        sd_vae.checkpoint_info = sd_model.sd_checkpoint_info
+
+        print(f"Reusing loaded model {sd_model.sd_checkpoint_info.title} to load {checkpoint_info.title}")
+        return sd_model
+    else:
+        return None
+
+
 def reload_model_weights(sd_model=None, info=None):
-    from modules import lowvram, devices, sd_hijack
     checkpoint_info = info or select_checkpoint()
 
+    timer = Timer()
+
     if not sd_model:
         sd_model = model_data.sd_model
 
@@ -554,19 +759,17 @@ def reload_model_weights(sd_model=None, info=None):
     else:
         current_checkpoint_info = sd_model.sd_checkpoint_info
         if sd_model.sd_model_checkpoint == checkpoint_info.filename:
-            return
+            return sd_model
 
+    sd_model = reuse_model_from_already_loaded(sd_model, checkpoint_info, timer)
+    if sd_model is not None and sd_model.sd_checkpoint_info.filename == checkpoint_info.filename:
+        return sd_model
+
+    if sd_model is not None:
         sd_unet.apply_unet("None")
-
-        if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
-            lowvram.send_everything_to_cpu()
-        else:
-            sd_model.to(devices.cpu)
-
+        send_model_to_cpu(sd_model)
         sd_hijack.model_hijack.undo_hijack(sd_model)
 
-    timer = Timer()
-
     state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
 
     checkpoint_config = sd_models_config.find_checkpoint_config(state_dict, checkpoint_info)
@@ -574,7 +777,9 @@ def reload_model_weights(sd_model=None, info=None):
     timer.record("find config")
 
     if sd_model is None or checkpoint_config != sd_model.used_config:
-        del sd_model
+        if sd_model is not None:
+            send_model_to_trash(sd_model)
+
         load_model(checkpoint_info, already_loaded_state_dict=state_dict)
         return model_data.sd_model
 
@@ -591,28 +796,20 @@ def reload_model_weights(sd_model=None, info=None):
         script_callbacks.model_loaded_callback(sd_model)
         timer.record("script callbacks")
 
-        if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram:
+        if not sd_model.lowvram:
             sd_model.to(devices.device)
             timer.record("move model to device")
 
     print(f"Weights loaded in {timer.summary()}.")
 
+    model_data.set_sd_model(sd_model)
+    sd_unet.apply_unet()
+
     return sd_model
 
 
 def unload_model_weights(sd_model=None, info=None):
-    from modules import devices, sd_hijack
-    timer = Timer()
-
-    if model_data.sd_model:
-        model_data.sd_model.to(devices.cpu)
-        sd_hijack.model_hijack.undo_hijack(model_data.sd_model)
-        model_data.sd_model = None
-        sd_model = None
-        gc.collect()
-        devices.torch_gc()
-
-    print(f"Unloaded weights {timer.summary()}.")
+    send_model_to_cpu(sd_model or shared.sd_model)
 
     return sd_model
 

modules/sd_models_config.py

@@ -2,7 +2,7 @@ import os
 
 import torch
 
-from modules import shared, paths, sd_disable_initialization
+from modules import shared, paths, sd_disable_initialization, devices
 
 sd_configs_path = shared.sd_configs_path
 sd_repo_configs_path = os.path.join(paths.paths['Stable Diffusion'], "configs", "stable-diffusion")
@@ -21,7 +21,7 @@ config_unopenclip = os.path.join(sd_repo_configs_path, "v2-1-stable-unclip-h-inf
 config_inpainting = os.path.join(sd_configs_path, "v1-inpainting-inference.yaml")
 config_instruct_pix2pix = os.path.join(sd_configs_path, "instruct-pix2pix.yaml")
 config_alt_diffusion = os.path.join(sd_configs_path, "alt-diffusion-inference.yaml")
-
+config_alt_diffusion_m18 = os.path.join(sd_configs_path, "alt-diffusion-m18-inference.yaml")
 
 def is_using_v_parameterization_for_sd2(state_dict):
     """
@@ -29,7 +29,6 @@ def is_using_v_parameterization_for_sd2(state_dict):
     """
 
     import ldm.modules.diffusionmodules.openaimodel
-    from modules import devices
 
     device = devices.cpu
 
@@ -96,7 +95,10 @@ def guess_model_config_from_state_dict(sd, filename):
         if diffusion_model_input.shape[1] == 8:
             return config_instruct_pix2pix
 
+
     if sd.get('cond_stage_model.roberta.embeddings.word_embeddings.weight', None) is not None:
+        if sd.get('cond_stage_model.transformation.weight').size()[0] == 1024:
+            return config_alt_diffusion_m18
         return config_alt_diffusion
 
     return config_default

modules/sd_models_types.py

@@ -0,0 +1,34 @@
+from ldm.models.diffusion.ddpm import LatentDiffusion
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from modules.sd_models import CheckpointInfo
+
+
+class WebuiSdModel(LatentDiffusion):
+    """This class is not actually instantinated, but its fields are created and fieeld by webui"""
+
+    lowvram: bool
+    """True if lowvram/medvram optimizations are enabled -- see modules.lowvram for more info"""
+
+    sd_model_hash: str
+    """short hash, 10 first characters of SHA1 hash of the model file; may be None if --no-hashing flag is used"""
+
+    sd_model_checkpoint: str
+    """path to the file on disk that model weights were obtained from"""
+
+    sd_checkpoint_info: 'CheckpointInfo'
+    """structure with additional information about the file with model's weights"""
+
+    is_sdxl: bool
+    """True if the model's architecture is SDXL or SSD"""
+
+    is_ssd: bool
+    """True if the model is SSD"""
+
+    is_sd2: bool
+    """True if the model's architecture is SD 2.x"""
+
+    is_sd1: bool
+    """True if the model's architecture is SD 1.x"""

modules/sd_models_xl.py

@@ -56,6 +56,14 @@ def encode_embedding_init_text(self: sgm.modules.GeneralConditioner, init_text,
     return torch.cat(res, dim=1)
 
 
+def tokenize(self: sgm.modules.GeneralConditioner, texts):
+    for embedder in [embedder for embedder in self.embedders if hasattr(embedder, 'tokenize')]:
+        return embedder.tokenize(texts)
+
+    raise AssertionError('no tokenizer available')
+
+
+
 def process_texts(self, texts):
     for embedder in [embedder for embedder in self.embedders if hasattr(embedder, 'process_texts')]:
         return embedder.process_texts(texts)
@@ -68,6 +76,7 @@ def get_target_prompt_token_count(self, token_count):
 
 # those additions to GeneralConditioner make it possible to use it as model.cond_stage_model from SD1.5 in exist
 sgm.modules.GeneralConditioner.encode_embedding_init_text = encode_embedding_init_text
+sgm.modules.GeneralConditioner.tokenize = tokenize
 sgm.modules.GeneralConditioner.process_texts = process_texts
 sgm.modules.GeneralConditioner.get_target_prompt_token_count = get_target_prompt_token_count
 
@@ -89,10 +98,10 @@ def extend_sdxl(model):
     model.conditioner.wrapped = torch.nn.Module()
 
 
-sgm.modules.attention.print = lambda *args: None
-sgm.modules.diffusionmodules.model.print = lambda *args: None
-sgm.modules.diffusionmodules.openaimodel.print = lambda *args: None
-sgm.modules.encoders.modules.print = lambda *args: None
+sgm.modules.attention.print = shared.ldm_print
+sgm.modules.diffusionmodules.model.print = shared.ldm_print
+sgm.modules.diffusionmodules.openaimodel.print = shared.ldm_print
+sgm.modules.encoders.modules.print = shared.ldm_print
 
 # this gets the code to load the vanilla attention that we override
 sgm.modules.attention.SDP_IS_AVAILABLE = True

modules/sd_samplers.py

@@ -1,17 +1,18 @@
-from modules import sd_samplers_compvis, sd_samplers_kdiffusion, shared
+from modules import sd_samplers_kdiffusion, sd_samplers_timesteps, shared
 
 # imports for functions that previously were here and are used by other modules
 from modules.sd_samplers_common import samples_to_image_grid, sample_to_image  # noqa: F401
 
 all_samplers = [
     *sd_samplers_kdiffusion.samplers_data_k_diffusion,
-    *sd_samplers_compvis.samplers_data_compvis,
+    *sd_samplers_timesteps.samplers_data_timesteps,
 ]
 all_samplers_map = {x.name: x for x in all_samplers}
 
 samplers = []
 samplers_for_img2img = []
 samplers_map = {}
+samplers_hidden = {}
 
 
 def find_sampler_config(name):
@@ -38,13 +39,11 @@ def create_sampler(name, model):
 
 
 def set_samplers():
-    global samplers, samplers_for_img2img
+    global samplers, samplers_for_img2img, samplers_hidden
 
-    hidden = set(shared.opts.hide_samplers)
-    hidden_img2img = set(shared.opts.hide_samplers + ['PLMS', 'UniPC'])
-
-    samplers = [x for x in all_samplers if x.name not in hidden]
-    samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]
+    samplers_hidden = set(shared.opts.hide_samplers)
+    samplers = all_samplers
+    samplers_for_img2img = all_samplers
 
     samplers_map.clear()
     for sampler in all_samplers:
@@ -53,4 +52,8 @@ def set_samplers():
             samplers_map[alias.lower()] = sampler.name
 
 
+def visible_sampler_names():
+    return [x.name for x in samplers if x.name not in samplers_hidden]
+
+
 set_samplers()