disable img preprocess for extra submit

base64 img

.eslintrc.js

@@ -78,6 +78,8 @@ module.exports = {
         //extraNetworks.js
         requestGet: "readonly",
         popup: "readonly",
+        // profilerVisualization.js
+        createVisualizationTable: "readonly",
         // from python
         localization: "readonly",
         // progrssbar.js
@@ -86,8 +88,6 @@ module.exports = {
         // imageviewer.js
         modalPrevImage: "readonly",
         modalNextImage: "readonly",
-        // token-counters.js
-        setupTokenCounters: "readonly",
         // localStorage.js
         localSet: "readonly",
         localGet: "readonly",

.github/workflows/on_pull_request.yaml

@@ -11,8 +11,8 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+        uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: 3.11
           # NB: there's no cache: pip here since we're not installing anything
@@ -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==0.1.6
+        run: pip install ruff==0.3.3
       - name: Run Ruff
         run: ruff .
   lint-js:
@@ -29,9 +29,9 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install Node.js
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18
       - run: npm i --ci

.github/workflows/run_tests.yaml

@@ -11,9 +11,9 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.10.6
           cache: pip
@@ -22,7 +22,7 @@ jobs:
             launch.py
       - name: Cache models
         id: cache-models
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: models
           key: "2023-12-30"
@@ -68,13 +68,13 @@ jobs:
           python -m coverage report -i
           python -m coverage html -i
       - name: Upload main app output
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         if: always()
         with:
           name: output
           path: output.txt
       - name: Upload coverage HTML
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         if: always()
         with:
           name: htmlcov

.gitignore

@@ -38,3 +38,4 @@ notification.mp3
 /package-lock.json
 /.coverage*
 /test/test_outputs
+/cache

CHANGELOG.md

@@ -1,3 +1,291 @@
+## 1.9.3
+
+### Bug Fixes:
+*  fix get_crop_region_v2 ([#15594](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15594)) 
+
+## 1.9.2
+
+### Extensions and API:
+* restore 1.8.0-style naming of scripts
+
+## 1.9.1
+
+### Minor:
+* Add avif support ([#15582](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15582))
+* Add filename patterns: `[sampler_scheduler]` and `[scheduler]` ([#15581](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15581))
+
+### Extensions and API:
+* undo adding scripts to sys.modules
+* Add schedulers API endpoint ([#15577](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15577))
+* Remove API upscaling factor limits ([#15560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15560))
+
+### Bug Fixes:
+* Fix images do not match / Coordinate 'right' is less than 'left' ([#15534](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15534))
+* fix: remove_callbacks_for_function should also remove from the ordered map ([#15533](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15533))
+* fix x1 upscalers ([#15555](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15555))
+* Fix cls.__module__ value in extension script ([#15532](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15532))
+* fix typo in function call (eror -> error) ([#15531](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15531))
+
+### Other:
+* Hide 'No Image data blocks found.' message ([#15567](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15567))
+* Allow webui.sh to be runnable from arbitrary directories containing a .git file ([#15561](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15561))
+* Compatibility with Debian 11, Fedora 34+ and openSUSE 15.4+ ([#15544](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15544))
+* numpy DeprecationWarning product -> prod ([#15547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15547))
+* get_crop_region_v2 ([#15583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15583), [#15587](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15587))
+
+
+## 1.9.0
+
+### Features:
+* Make refiner switchover based on model timesteps instead of sampling steps ([#14978](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14978))
+* add an option to have old-style directory view instead of tree view; stylistic changes for extra network sorting/search controls
+* add UI for reordering callbacks, support for specifying callback order in extension metadata ([#15205](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15205))
+* Sgm uniform scheduler for SDXL-Lightning models ([#15325](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15325))
+* Scheduler selection in main UI ([#15333](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15333), [#15361](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15361), [#15394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15394))
+
+### Minor:
+* "open images directory" button now opens the actual dir ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947))
+* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973))
+* make extra network card description plaintext by default, with an option to re-enable HTML as it was
+* resize handle for extra networks ([#15041](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15041))
+* cmd args: `--unix-filenames-sanitization` and `--filenames-max-length` ([#15031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15031))
+* show extra networks parameters in HTML table rather than raw JSON ([#15131](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15131))
+* Add DoRA (weight-decompose) support for LoRA/LoHa/LoKr ([#15160](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15160), [#15283](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15283))
+* Add '--no-prompt-history' cmd args for disable last generation prompt history ([#15189](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15189))
+* update preview on Replace Preview ([#15201](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15201))
+* only fetch updates for extensions' active git branches ([#15233](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15233))
+* put upscale postprocessing UI into an accordion ([#15223](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15223))
+* Support dragdrop for URLs to read infotext ([#15262](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15262))
+* use diskcache library for caching ([#15287](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15287), [#15299](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15299))
+* Allow PNG-RGBA for Extras Tab ([#15334](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15334))
+* Support cover images embedded in safetensors metadata ([#15319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15319))
+* faster interrupt when using NN upscale ([#15380](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15380))
+* Extras upscaler: an input field to limit maximul side length for the output image ([#15293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15293), [#15415](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15415), [#15417](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15417), [#15425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15425))
+* add an option to hide postprocessing options in Extras tab
+
+### Extensions and API:
+* ResizeHandleRow - allow overriden column scale parametr ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004))
+* call script_callbacks.ui_settings_callback earlier; fix extra-options-section built-in extension killing the ui if using a setting that doesn't exist
+* make it possible to use zoom.js outside webui context ([#15286](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15286), [#15288](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15288))
+* allow variants for extension name in metadata.ini ([#15290](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15290))
+* make reloading UI scripts optional when doing Reload UI, and off by default
+* put request: gr.Request at start of img2img function similar to txt2img
+* open_folder as util ([#15442](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15442))
+* make it possible to import extensions' script files as `import scripts.<filename>` ([#15423](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15423))
+
+### Performance:
+* performance optimization for extra networks HTML pages
+* optimization for extra networks filtering
+* optimization for extra networks sorting
+
+### Bug Fixes:
+* prevent escape button causing an interrupt when no generation has been made yet
+* [bug] avoid doble upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966))
+* possible fix for reload button not appearing in some cases for extra networks.
+* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006))
+* Fix resize-handle visability for vertical layout (mobile) ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010))
+* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012))
+* Protect alphas_cumprod during refiner switchover ([#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979))
+* Fix EXIF orientation in API image loading ([#15062](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15062))
+* Only override emphasis if actually used in prompt ([#15141](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15141))
+* Fix emphasis infotext missing from `params.txt` ([#15142](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15142))
+* fix extract_style_text_from_prompt #15132 ([#15135](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15135))
+* Fix Soft Inpaint for AnimateDiff ([#15148](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15148))
+* edit-attention: deselect surrounding whitespace ([#15178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15178))
+* chore: fix font not loaded ([#15183](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15183))
+* use natural sort in extra networks when ordering by path
+* Fix built-in lora system bugs caused by torch.nn.MultiheadAttention ([#15190](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15190))
+* Avoid error from None in get_learned_conditioning ([#15191](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15191))
+* Add entry to MassFileLister after writing metadata ([#15199](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15199))
+* fix issue with Styles when Hires prompt is used ([#15269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15269), [#15276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15276))
+* Strip comments from hires fix prompt ([#15263](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15263))
+* Make imageviewer event listeners browser consistent ([#15261](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15261))
+* Fix AttributeError in OFT when trying to get MultiheadAttention weight ([#15260](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15260))
+* Add missing .mean() back ([#15239](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15239))
+* fix "Restore progress" button ([#15221](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15221))
+* fix ui-config for InputAccordion [custom_script_source] ([#15231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15231))
+* handle 0 wheel deltaY ([#15268](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15268))
+* prevent alt menu for firefox ([#15267](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15267))
+* fix: fix syntax errors ([#15179](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15179))
+* restore outputs path ([#15307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15307))
+* Escape btn_copy_path filename ([#15316](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15316))
+* Fix extra networks buttons when filename contains an apostrophe ([#15331](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15331))
+* escape brackets in lora random prompt generator ([#15343](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15343))
+* fix: Python version check for PyTorch installation compatibility ([#15390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15390))
+* fix typo in call_queue.py ([#15386](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15386))
+* fix: when find already_loaded model, remove loaded by array index ([#15382](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15382))
+* minor bug fix of sd model memory management ([#15350](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15350))
+* Fix CodeFormer weight ([#15414](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15414))
+* Fix: Remove script callbacks in ordered_callbacks_map ([#15428](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15428))
+* fix limited file write (thanks, Sylwia)
+* Fix extra-single-image API not doing upscale failed ([#15465](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15465))
+* error handling paste_field callables ([#15470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15470))
+
+### Hardware:
+* Add training support and change lspci for Ascend NPU ([#14981](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14981))
+* Update to ROCm5.7 and PyTorch ([#14820](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14820))
+* Better workaround for Navi1, removing --pre for Navi3 ([#15224](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15224))
+* Ascend NPU wiki page ([#15228](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15228))
+
+### Other:
+* Update comment for Pad prompt/negative prompt v0 to add a warning about truncation, make it override the v1 implementation
+* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002))
+* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995))
+* Use `absolute` path for normalized filepath ([#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035))
+* resizeHandle handle double tap ([#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065))
+* --dat-models-path cmd flag ([#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039))
+* Add a direct link to the binary release ([#15059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15059))
+* upscaler_utils: Reduce logging ([#15084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15084))
+* Fix various typos with crate-ci/typos ([#15116](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15116))
+* fix_jpeg_live_preview ([#15102](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15102))
+* [alternative fix] can't load webui if selected wrong extra option in ui ([#15121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15121))
+* Error handling for unsupported transparency ([#14958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14958))
+* Add model description to searched terms ([#15198](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15198))
+* bump action version ([#15272](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15272))
+* PEP 604 annotations ([#15259](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15259))
+* Automatically Set the Scale by value when user selects an Upscale Model ([#15244](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15244))
+* move postprocessing-for-training into builtin extensions ([#15222](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15222))
+* type hinting in shared.py ([#15211](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15211))
+* update ruff to 0.3.3
+* Update pytorch lightning utilities ([#15310](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15310))
+* Add Size as an XYZ Grid option ([#15354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15354))
+* Use HF_ENDPOINT variable for HuggingFace domain with default ([#15443](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15443))
+* re-add update_file_entry ([#15446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15446))
+* create_infotext allow index and callable, re-work Hires prompt infotext ([#15460](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15460))
+* update restricted_opts to include more options for --hide-ui-dir-config ([#15492](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15492))
+
+
+## 1.8.0
+
+### Features:
+* Update torch to version 2.1.2
+* Soft Inpainting ([#14208](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14208))
+* FP8 support ([#14031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14031), [#14327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14327))
+* Support for SDXL-Inpaint Model ([#14390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14390))
+* Use Spandrel for upscaling and face restoration architectures ([#14425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14425), [#14467](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14467), [#14473](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14473), [#14474](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14474), [#14477](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14477), [#14476](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14476), [#14484](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14484), [#14500](https://github.com/AUTOMATIC1111/stable-difusion-webui/pull/14500), [#14501](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14501), [#14504](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14504), [#14524](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14524), [#14809](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14809))
+* Automatic backwards version compatibility (when loading infotexts from old images with program version specified, will add compatibility settings)
+* Implement zero terminal SNR noise schedule option (**[SEED BREAKING CHANGE](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Seed-breaking-changes#180-dev-170-225-2024-01-01---zero-terminal-snr-noise-schedule-option)**, [#14145](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14145), [#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979))
+* Add a [✨] button to run hires fix on selected image in the gallery (with help from [#14598](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14598), [#14626](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14626), [#14728](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14728))
+* [Separate assets repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets); serve fonts locally rather than from google's servers
+* Official LCM Sampler Support ([#14583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14583))
+* Add support for DAT upscaler models ([#14690](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14690), [#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039))
+* Extra Networks Tree View ([#14588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14588), [#14900](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14900))
+* NPU Support ([#14801](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14801))
+* Prompt comments support
+
+### Minor:
+* Allow pasting in WIDTHxHEIGHT strings into the width/height fields ([#14296](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14296))
+* add option: Live preview in full page image viewer ([#14230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14230), [#14307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14307))
+* Add keyboard shortcuts for generate/skip/interrupt ([#14269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14269))
+* Better TCMALLOC support on different platforms ([#14227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14227), [#14883](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14883), [#14910](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14910))
+* Lora not found warning ([#14464](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14464))
+* Adding negative prompts to Loras in extra networks ([#14475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14475))
+* xyz_grid: allow varying the seed along an axis separate from axis options ([#12180](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12180))
+* option to convert VAE to bfloat16 (implementation of [#9295](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9295))
+* Better IPEX support ([#14229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14229), [#14353](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14353), [#14559](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14559), [#14562](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14562), [#14597](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14597))
+* Option to interrupt after current generation rather than immediately ([#13653](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13653), [#14659](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14659))
+* Fullscreen Preview control fading/disable ([#14291](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14291))
+* Finer settings freezing control ([#13789](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13789))
+* Increase Upscaler Limits ([#14589](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14589))
+* Adjust brush size with hotkeys ([#14638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14638))
+* Add checkpoint info to csv log file when saving images ([#14663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14663))
+* Make more columns resizable ([#14740](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14740), [#14884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14884))
+* Add an option to not overlay original image for inpainting for #14727
+* Add Pad conds v0 option to support same generation with DDIM as before 1.6.0
+* Add "Interrupting..." placeholder.
+* Button for refresh extensions list ([#14857](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857))
+* Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874))
+* When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior)
+* Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947))
+* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973))
+* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002))
+
+### Extensions and API:
+* Removed packages from requirements: basicsr, gfpgan, realesrgan; as well as their dependencies: absl-py, addict, beautifulsoup4, future, gdown, grpcio, importlib-metadata, lmdb, lpips, Markdown, platformdirs, PySocks, soupsieve, tb-nightly, tensorboard-data-server, tomli, Werkzeug, yapf, zipp, soupsieve
+* Enable task ids for API ([#14314](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14314))
+* add override_settings support for infotext API
+* rename generation_parameters_copypaste module to infotext_utils
+* prevent crash due to Script __init__ exception ([#14407](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14407))
+* Bump numpy to 1.26.2 ([#14471](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14471))
+* Add utility to inspect a model's dtype/device ([#14478](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14478))
+* Implement general forward method for all method in built-in lora ext ([#14547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14547))
+* Execute model_loaded_callback after moving to target device ([#14563](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14563))
+* Add self to CFGDenoiserParams ([#14573](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14573))
+* Allow TLS with API only mode (--nowebui) ([#14593](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14593))
+* New callback: postprocess_image_after_composite ([#14657](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14657))
+* modules/api/api.py: add api endpoint to refresh embeddings list ([#14715](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14715))
+* set_named_arg ([#14773](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14773))
+* add before_token_counter callback and use it for prompt comments
+* ResizeHandleRow - allow overridden column scale parameter ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004))
+
+### Performance:
+* Massive performance improvement for extra networks directories with a huge number of files in them in an attempt to tackle #14507 ([#14528](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14528))
+* Reduce unnecessary re-indexing extra networks directory ([#14512](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14512))
+* Avoid unnecessary `isfile`/`exists` calls ([#14527](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14527))
+
+### Bug Fixes:
+* fix multiple bugs related to styles multi-file support ([#14203](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14203), [#14276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14276), [#14707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14707))
+* Lora fixes ([#14300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14300), [#14237](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14237), [#14546](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14546), [#14726](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14726))
+* Re-add setting lost as part of e294e46 ([#14266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14266))
+* fix extras caption BLIP ([#14330](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14330))
+* include infotext into saved init image for img2img ([#14452](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14452))
+* xyz grid handle axis_type is None ([#14394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14394))
+* Update Added (Fixed) IPV6 Functionality When there is No Webui Argument Passed webui.py ([#14354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14354))
+* fix API thread safe issues of txt2img and img2img ([#14421](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14421))
+* handle selectable script_index is None ([#14487](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14487))
+* handle config.json failed to load ([#14525](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14525), [#14767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14767))
+* paste infotext cast int as float ([#14523](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14523))
+* Ensure GRADIO_ANALYTICS_ENABLED is set early enough ([#14537](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14537))
+* Fix logging configuration again ([#14538](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14538))
+* Handle CondFunc exception when resolving attributes ([#14560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14560))
+* Fix extras big batch crashes ([#14699](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14699))
+* Fix using wrong model caused by alias ([#14655](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14655))
+* Add # to the invalid_filename_chars list ([#14640](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14640))
+* Fix extension check for requirements ([#14639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14639))
+* Fix tab indexes are reset after restart UI ([#14637](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14637))
+* Fix nested manual cast ([#14689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14689))
+* Keep postprocessing upscale selected tab after restart ([#14702](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14702))
+* XYZ grid: filter out blank vals when axis is int or float type (like int axis seed) ([#14754](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14754))
+* fix CLIP Interrogator topN regex ([#14775](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14775))
+* Fix dtype error in MHA layer/change dtype checking mechanism for manual cast ([#14791](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14791))
+* catch load style.csv error ([#14814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14814))
+* fix error when editing extra networks card
+* fix extra networks metadata failing to work properly when you create the .json file with metadata for the first time.
+* util.walk_files extensions case insensitive ([#14879](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14879))
+* if extensions page not loaded, prevent apply ([#14873](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14873))
+* call the right function for token counter in img2img
+* Fix the bugs that search/reload will disappear when using other ExtraNetworks extensions ([#14939](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14939))
+* Gracefully handle mtime read exception from cache ([#14933](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14933))
+* Only trigger interrupt on `Esc` when interrupt button visible ([#14932](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14932))
+* Disable prompt token counters option actually disables token counting rather than just hiding results.
+* avoid double upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966))
+* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995))
+* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006))
+* Fix resize-handle for mobile ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010), [#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065))
+
+### Other:
+* Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270))
+* change state dict comparison to ref compare ([#14216](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14216))
+* Bump torch-rocm to 5.6/5.7 ([#14293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14293))
+* Base output path off data path ([#14446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14446))
+* reorder training preprocessing modules in extras tab ([#14367](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14367))
+* Remove `cleanup_models` code ([#14472](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14472))
+* only rewrite ui-config when there is change ([#14352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14352))
+* Fix lint issue from 501993eb ([#14495](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14495))
+* Update README.md ([#14548](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14548))
+* hires button, fix seeds ()
+* Logging: set formatter correctly for fallback logger too ([#14618](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14618))
+* Read generation info from infotexts rather than json for internal needs (save, extract seed from generated pic) ([#14645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14645))
+* improve get_crop_region ([#14709](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14709))
+* Bump safetensors' version to 0.4.2 ([#14782](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14782))
+* add tooltip create_submit_box ([#14803](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14803))
+* extensions tab table row hover highlight ([#14885](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14885))
+* Always add timestamp to displayed image ([#14890](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14890))
+* Added core.filemode=false so doesn't track changes in file permission… ([#14930](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14930))
+* Normalize command-line argument paths ([#14934](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14934), [#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035))
+* Use original App Title in progress bar ([#14916](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14916))
+* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012))
+
 ## 1.7.0
 
 ### Features:
@@ -40,7 +328,8 @@
 * 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))
+* allow use of multiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125))
+* make extra network card description plaintext by default, with an option (Treat card description as HTML) to re-enable HTML as it was (originally by [#13241](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13241))
 
 ### Extensions and API:
 * update gradio to 3.41.2
@@ -176,7 +465,7 @@
  * 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 prompt composition possible (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))
@@ -352,7 +641,7 @@
  * user metadata system for custom networks
  * extended Lora metadata editor: set activation text, default weight, view tags, training info
  * Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)
- * show github stars for extenstions
+ * show github stars for extensions
  * img2img batch mode can read extra stuff from png info
  * img2img batch works with subdirectories
  * hotkeys to move prompt elements: alt+left/right
@@ -571,7 +860,7 @@
  * do not wait for Stable Diffusion model to load at startup
  * add filename patterns: `[denoising]`
  * directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for
- * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metdata of the file, if present, instead of filename (both can be used to activate LoRA)
+ * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metadata of the file, if present, instead of filename (both can be used to activate LoRA)
  * LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
  * LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)
  * LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)
@@ -601,7 +890,7 @@
  * fix gamepad navigation
  * make the lightbox fullscreen image function properly
  * fix squished thumbnails in extras tab
- * keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)
+ * keep "search" filter for extra networks when user refreshes the tab (previously it showed everything after you refreshed)
  * fix webui showing the same image if you configure the generation to always save results into same file
  * fix bug with upscalers not working properly
  * fix MPS on PyTorch 2.0.1, Intel Macs
@@ -619,7 +908,7 @@
  * switch to PyTorch 2.0.0 (except for AMD GPUs)
  * visual improvements to custom code scripts
  * add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`
- * add support for saving init images in img2img, and record their hashes in infotext for reproducability
+ * add support for saving init images in img2img, and record their hashes in infotext for reproducibility
  * automatically select current word when adjusting weight with ctrl+up/down
  * add dropdowns for X/Y/Z plot
  * add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs

README.md

@@ -98,6 +98,7 @@ Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-di
 - [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)
+- [Ascend NPUs](https://github.com/wangshuai09/stable-diffusion-webui/wiki/Install-and-run-on-Ascend-NPUs) (external wiki page)
 
 Alternatively, use online services (like Google Colab):
 

_typos.toml

@@ -0,0 +1,5 @@
+[default.extend-words]
+# Part of "RGBa" (Pillow's pre-multiplied alpha RGB mode)
+Ba = "Ba"
+# HSA is something AMD uses for their GPUs
+HSA = "HSA"

extensions-builtin/LDSR/sd_hijack_ddpm_v1.py

@@ -301,7 +301,7 @@ class DDPMV1(pl.LightningModule):
         elif self.parameterization == "x0":
             target = x_start
         else:
-            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+            raise NotImplementedError(f"Parameterization {self.parameterization} not yet supported")
 
         loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
 
@@ -880,7 +880,7 @@ class LatentDiffusionV1(DDPMV1):
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
-            # hybrid case, cond is exptected to be a dict
+            # hybrid case, cond is expected to be a dict
             pass
         else:
             if not isinstance(cond, list):
@@ -916,7 +916,7 @@ class LatentDiffusionV1(DDPMV1):
                 cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
 
             elif self.cond_stage_key == 'coordinates_bbox':
-                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+                assert 'original_image_size' in self.split_input_params, 'BoundingBoxRescaling is missing original_image_size'
 
                 # assuming padding of unfold is always 0 and its dilation is always 1
                 n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
@@ -926,7 +926,7 @@ class LatentDiffusionV1(DDPMV1):
                 num_downs = self.first_stage_model.encoder.num_resolutions - 1
                 rescale_latent = 2 ** (num_downs)
 
-                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # get top left positions of patches as conforming for the bbbox tokenizer, therefore we
                 # need to rescale the tl patch coordinates to be in between (0,1)
                 tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
                                          rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)

extensions-builtin/Lora/lyco_helpers.py

@@ -30,7 +30,7 @@ def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
     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.
+    Because of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
 
     examples)
     factor

extensions-builtin/Lora/network.py

@@ -29,7 +29,6 @@ class NetworkOnDisk:
 
         def read_metadata():
             metadata = sd_models.read_metadata_from_safetensors(filename)
-            metadata.pop('ssmd_cover_images', None)  # those are cover images, and they are too big to display in UI as text
 
             return metadata
 
@@ -117,6 +116,12 @@ class NetworkModule:
 
         if hasattr(self.sd_module, 'weight'):
             self.shape = self.sd_module.weight.shape
+        elif isinstance(self.sd_module, nn.MultiheadAttention):
+            # For now, only self-attn use Pytorch's MHA
+            # So assume all qkvo proj have same shape
+            self.shape = self.sd_module.out_proj.weight.shape
+        else:
+            self.shape = None
 
         self.ops = None
         self.extra_kwargs = {}
@@ -146,6 +151,9 @@ class NetworkModule:
         self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
         self.scale = weights.w["scale"].item() if "scale" in weights.w else None
 
+        self.dora_scale = weights.w.get("dora_scale", None)
+        self.dora_norm_dims = len(self.shape) - 1
+
     def multiplier(self):
         if 'transformer' in self.sd_key[:20]:
             return self.network.te_multiplier
@@ -160,6 +168,27 @@ class NetworkModule:
 
         return 1.0
 
+    def apply_weight_decompose(self, updown, orig_weight):
+        # Match the device/dtype
+        orig_weight = orig_weight.to(updown.dtype)
+        dora_scale = self.dora_scale.to(device=orig_weight.device, dtype=updown.dtype)
+        updown = updown.to(orig_weight.device)
+
+        merged_scale1 = updown + orig_weight
+        merged_scale1_norm = (
+            merged_scale1.transpose(0, 1)
+            .reshape(merged_scale1.shape[1], -1)
+            .norm(dim=1, keepdim=True)
+            .reshape(merged_scale1.shape[1], *[1] * self.dora_norm_dims)
+            .transpose(0, 1)
+        )
+
+        dora_merged = (
+            merged_scale1 * (dora_scale / merged_scale1_norm)
+        )
+        final_updown = dora_merged - orig_weight
+        return final_updown
+
     def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
         if self.bias is not None:
             updown = updown.reshape(self.bias.shape)
@@ -175,6 +204,9 @@ class NetworkModule:
         if ex_bias is not None:
             ex_bias = ex_bias * self.multiplier()
 
+        if self.dora_scale is not None:
+            updown = self.apply_weight_decompose(updown, orig_weight)
+
         return updown * self.calc_scale() * self.multiplier(), ex_bias
 
     def calc_updown(self, target):

extensions-builtin/Lora/network_oft.py

@@ -1,6 +1,5 @@
 import torch
 import network
-from lyco_helpers import factorization
 from einops import rearrange
 
 
@@ -22,16 +21,17 @@ class NetworkModuleOFT(network.NetworkModule):
         self.org_module: list[torch.Module] = [self.sd_module]
 
         self.scale = 1.0
+        self.is_R = False
+        self.is_boft = False
 
-        # kohya-ss
+        # kohya-ss/New LyCORIS OFT/BOFT
         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.alpha = weights.w.get("alpha", None) # alpha is constraint
             self.dim = self.oft_blocks.shape[0] # lora dim
-        # LyCORIS
+        # Old LyCORIS OFT
         elif "oft_diag" in weights.w.keys():
-            self.is_kohya = False
+            self.is_R = True
             self.oft_blocks = weights.w["oft_diag"]
             # self.alpha is unused
             self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
@@ -47,35 +47,71 @@ class NetworkModuleOFT(network.NetworkModule):
         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:
+        # LyCORIS BOFT
+        if self.oft_blocks.dim() == 4:
+            self.is_boft = True
+        self.rescale = weights.w.get('rescale', None)
+        if self.rescale is not None and not is_other_linear:
+            self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1))
+
+        self.num_blocks = self.dim
+        self.block_size = self.out_dim // self.dim
+        self.constraint = (0 if self.alpha is None else self.alpha) * self.out_dim
+        if self.is_R:
             self.constraint = None
-            self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
+            self.block_size = self.dim
+            self.num_blocks = self.out_dim // self.dim
+        elif self.is_boft:
+            self.boft_m = self.oft_blocks.shape[0]
+            self.num_blocks = self.oft_blocks.shape[1]
+            self.block_size = self.oft_blocks.shape[2]
+            self.boft_b = self.block_size
 
     def calc_updown(self, orig_weight):
         oft_blocks = self.oft_blocks.to(orig_weight.device)
-        eye = torch.eye(self.block_size, device=self.oft_blocks.device)
+        eye = torch.eye(self.block_size, device=oft_blocks.device)
 
-        if self.is_kohya:
-            block_Q = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
-            norm_Q = torch.norm(block_Q.flatten())
-            new_norm_Q = torch.clamp(norm_Q, max=self.constraint)
-            block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
+        if not self.is_R:
+            block_Q = oft_blocks - oft_blocks.transpose(-1, -2) # ensure skew-symmetric orthogonal matrix
+            if self.constraint != 0:
+                norm_Q = torch.norm(block_Q.flatten())
+                new_norm_Q = torch.clamp(norm_Q, max=self.constraint.to(oft_blocks.device))
+                block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
             oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse())
 
         R = oft_blocks.to(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) ...')
+        if not self.is_boft:
+            # 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) ...')
+        else:
+            # TODO: determine correct value for scale
+            scale = 1.0
+            m = self.boft_m
+            b = self.boft_b
+            r_b = b // 2
+            inp = orig_weight
+            for i in range(m):
+                bi = R[i] # b_num, b_size, b_size
+                if i == 0:
+                    # Apply multiplier/scale and rescale into first weight
+                    bi = bi * scale + (1 - scale) * eye
+                inp = rearrange(inp, "(c g k) ... -> (c k g) ...", g=2, k=2**i * r_b)
+                inp = rearrange(inp, "(d b) ... -> d b ...", b=b)
+                inp = torch.einsum("b i j, b j ... -> b i ...", bi, inp)
+                inp = rearrange(inp, "d b ... -> (d b) ...")
+                inp = rearrange(inp, "(c k g) ... -> (c g k) ...", g=2, k=2**i * r_b)
+            merged_weight = inp
+
+        # Rescale mechanism
+        if self.rescale is not None:
+            merged_weight = self.rescale.to(merged_weight) * merged_weight
 
         updown = merged_weight.to(orig_weight.device) - orig_weight.to(merged_weight.dtype)
         output_shape = orig_weight.shape

extensions-builtin/Lora/networks.py

@@ -355,7 +355,7 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
     """
     Applies the currently selected set of networks to the weights of torch layer self.
     If weights already have this particular set of networks applied, does nothing.
-    If not, restores orginal weights from backup and alters weights according to networks.
+    If not, restores original weights from backup and alters weights according to networks.
     """
 
     network_layer_name = getattr(self, 'network_layer_name', None)
@@ -429,9 +429,12 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
             if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
                 try:
                     with torch.no_grad():
-                        updown_q, _ = module_q.calc_updown(self.in_proj_weight)
-                        updown_k, _ = module_k.calc_updown(self.in_proj_weight)
-                        updown_v, _ = module_v.calc_updown(self.in_proj_weight)
+                        # Send "real" orig_weight into MHA's lora module
+                        qw, kw, vw = self.in_proj_weight.chunk(3, 0)
+                        updown_q, _ = module_q.calc_updown(qw)
+                        updown_k, _ = module_k.calc_updown(kw)
+                        updown_v, _ = module_v.calc_updown(vw)
+                        del qw, kw, vw
                         updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
                         updown_out, ex_bias = module_out.calc_updown(self.out_proj.weight)
 

extensions-builtin/Lora/preload.py

@@ -1,7 +1,8 @@
 import os
 from modules import paths
+from modules.paths_internal import normalized_filepath
 
 
 def preload(parser):
-    parser.add_argument("--lora-dir", type=str, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
-    parser.add_argument("--lyco-dir-backcompat", type=str, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))
+    parser.add_argument("--lora-dir", type=normalized_filepath, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
+    parser.add_argument("--lyco-dir-backcompat", type=normalized_filepath, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))

extensions-builtin/Lora/ui_edit_user_metadata.py

@@ -149,6 +149,8 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
 
             v = random.random() * max_count
             if count > v:
+                for x in "({[]})":
+                    tag = tag.replace(x, '\\' + x)
                 res.append(tag)
 
         return ", ".join(sorted(res))

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -24,13 +24,16 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
 
         alias = lora_on_disk.get_alias()
 
+        search_terms = [self.search_terms_from_path(lora_on_disk.filename)]
+        if lora_on_disk.hash:
+            search_terms.append(lora_on_disk.hash)
         item = {
             "name": name,
             "filename": lora_on_disk.filename,
             "shorthash": lora_on_disk.shorthash,
-            "preview": self.find_preview(path),
+            "preview": self.find_preview(path) or self.find_embedded_preview(path, name, lora_on_disk.metadata),
             "description": self.find_description(path),
-            "search_term": self.search_terms_from_path(lora_on_disk.filename) + " " + (lora_on_disk.hash or ""),
+            "search_terms": search_terms,
             "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)},

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

@@ -29,6 +29,7 @@ onUiLoaded(async() => {
     });
 
     function getActiveTab(elements, all = false) {
+        if (!elements.img2imgTabs) return null;
         const tabs = elements.img2imgTabs.querySelectorAll("button");
 
         if (all) return tabs;
@@ -43,6 +44,7 @@ onUiLoaded(async() => {
     // Get tab ID
     function getTabId(elements) {
         const activeTab = getActiveTab(elements);
+        if (!activeTab) return null;
         return tabNameToElementId[activeTab.innerText];
     }
 
@@ -252,6 +254,7 @@ onUiLoaded(async() => {
     let isMoving = false;
     let mouseX, mouseY;
     let activeElement;
+    let interactedWithAltKey = false;
 
     const elements = Object.fromEntries(
         Object.keys(elementIDs).map(id => [
@@ -277,7 +280,7 @@ onUiLoaded(async() => {
         const targetElement = gradioApp().querySelector(elemId);
 
         if (!targetElement) {
-            console.log("Element not found");
+            console.log("Element not found", elemId);
             return;
         }
 
@@ -292,7 +295,7 @@ onUiLoaded(async() => {
 
         // Create tooltip
         function createTooltip() {
-            const toolTipElemnt =
+            const toolTipElement =
                 targetElement.querySelector(".image-container");
             const tooltip = document.createElement("div");
             tooltip.className = "canvas-tooltip";
@@ -355,7 +358,7 @@ onUiLoaded(async() => {
             tooltip.appendChild(tooltipContent);
 
             // Add a hint element to the target element
-            toolTipElemnt.appendChild(tooltip);
+            toolTipElement.appendChild(tooltip);
         }
 
         //Show tool tip if setting enable
@@ -365,9 +368,9 @@ onUiLoaded(async() => {
 
         // In the course of research, it was found that the tag img is very harmful when zooming and creates white canvases. This hack allows you to almost never think about this problem, it has no effect on webui.
         function fixCanvas() {
-            const activeTab = getActiveTab(elements).textContent.trim();
+            const activeTab = getActiveTab(elements)?.textContent.trim();
 
-            if (activeTab !== "img2img") {
+            if (activeTab && activeTab !== "img2img") {
                 const img = targetElement.querySelector(`${elemId} img`);
 
                 if (img && img.style.display !== "none") {
@@ -508,6 +511,10 @@ onUiLoaded(async() => {
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
                 e.preventDefault();
 
+                if (hotkeysConfig.canvas_hotkey_zoom === "Alt") {
+                    interactedWithAltKey = true;
+                }
+
                 let zoomPosX, zoomPosY;
                 let delta = 0.2;
                 if (elemData[elemId].zoomLevel > 7) {
@@ -783,23 +790,29 @@ onUiLoaded(async() => {
         targetElement.addEventListener("mouseleave", handleMouseLeave);
 
         // Reset zoom when click on another tab
-        elements.img2imgTabs.addEventListener("click", resetZoom);
-        elements.img2imgTabs.addEventListener("click", () => {
-            // targetElement.style.width = "";
-            if (parseInt(targetElement.style.width) > 865) {
-                setTimeout(fitToElement, 0);
-            }
-        });
+        if (elements.img2imgTabs) {
+            elements.img2imgTabs.addEventListener("click", resetZoom);
+            elements.img2imgTabs.addEventListener("click", () => {
+                // targetElement.style.width = "";
+                if (parseInt(targetElement.style.width) > 865) {
+                    setTimeout(fitToElement, 0);
+                }
+            });
+        }
 
         targetElement.addEventListener("wheel", e => {
             // change zoom level
-            const operation = e.deltaY > 0 ? "-" : "+";
+            const operation = (e.deltaY || -e.wheelDelta) > 0 ? "-" : "+";
             changeZoomLevel(operation, e);
 
             // Handle brush size adjustment with ctrl key pressed
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
                 e.preventDefault();
 
+                if (hotkeysConfig.canvas_hotkey_adjust === "Alt") {
+                    interactedWithAltKey = true;
+                }
+
                 // Increase or decrease brush size based on scroll direction
                 adjustBrushSize(elemId, e.deltaY);
             }
@@ -839,6 +852,20 @@ onUiLoaded(async() => {
         document.addEventListener("keydown", handleMoveKeyDown);
         document.addEventListener("keyup", handleMoveKeyUp);
 
+
+        // Prevent firefox from opening main menu when alt is used as a hotkey for zoom or brush size
+        function handleAltKeyUp(e) {
+            if (e.key !== "Alt" || !interactedWithAltKey) {
+                return;
+            }
+
+            e.preventDefault();
+            interactedWithAltKey = false;
+        }
+
+        document.addEventListener("keyup", handleAltKeyUp);
+
+
         // Detect zoom level and update the pan speed.
         function updatePanPosition(movementX, movementY) {
             let panSpeed = 2;

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

@@ -8,8 +8,8 @@ shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas
     "canvas_hotkey_grow_brush": shared.OptionInfo("W", "Enlarge the brush size"),
     "canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas").info("To work correctly in firefox, turn off 'Automatically search the page text when typing' in the browser settings"),
     "canvas_hotkey_fullscreen": shared.OptionInfo("S", "Fullscreen Mode, maximizes the picture so that it fits into the screen and stretches it to its full width "),
-    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas positon"),
-    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, neededs for testing"),
+    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas position"),
+    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, needed 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"),

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

@@ -1,7 +1,7 @@
 import math
 
 import gradio as gr
-from modules import scripts, shared, ui_components, ui_settings, infotext_utils
+from modules import scripts, shared, ui_components, ui_settings, infotext_utils, errors
 from modules.ui_components import FormColumn
 
 
@@ -42,7 +42,11 @@ class ExtraOptionsSection(scripts.Script):
                             setting_name = extra_options[index]
 
                             with FormColumn():
-                                comp = ui_settings.create_setting_component(setting_name)
+                                try:
+                                    comp = ui_settings.create_setting_component(setting_name)
+                                except KeyError:
+                                    errors.report(f"Can't add extra options for {setting_name} in ui")
+                                    continue
 
                             self.comps.append(comp)
                             self.setting_names.append(setting_name)

extensions-builtin/postprocessing-for-training/scripts/postprocessing_split_oversized.py

@@ -61,7 +61,7 @@ class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostproces
             ratio = (pp.image.height * width) / (pp.image.width * height)
             inverse_xy = True
 
-        if ratio >= 1.0 and ratio > split_threshold:
+        if ratio >= 1.0 or ratio > split_threshold:
             return
 
         result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio)

extensions-builtin/soft-inpainting/scripts/soft_inpainting.py

@@ -57,10 +57,14 @@ def latent_blend(settings, a, b, t):
 
     # NOTE: We use inplace operations wherever possible.
 
-    # [4][w][h] to [1][4][w][h]
-    t2 = t.unsqueeze(0)
-    # [4][w][h] to [1][1][w][h] - the [4] seem redundant.
-    t3 = t[0].unsqueeze(0).unsqueeze(0)
+    if len(t.shape) == 3:
+        # [4][w][h] to [1][4][w][h]
+        t2 = t.unsqueeze(0)
+        # [4][w][h] to [1][1][w][h] - the [4] seem redundant.
+        t3 = t[0].unsqueeze(0).unsqueeze(0)
+    else:
+        t2 = t
+        t3 = t[:, 0][:, None]
 
     one_minus_t2 = 1 - t2
     one_minus_t3 = 1 - t3
@@ -104,7 +108,7 @@ def latent_blend(settings, a, b, t):
 
 def get_modified_nmask(settings, nmask, sigma):
     """
-    Converts a negative mask representing the transparency of the original latent vectors being overlayed
+    Converts a negative mask representing the transparency of the original latent vectors being overlaid
     to a mask that is scaled according to the denoising strength for this step.
 
     Where:
@@ -135,7 +139,10 @@ def apply_adaptive_masks(
     from PIL import Image, ImageOps, ImageFilter
 
     # TODO: Bias the blending according to the latent mask, add adjustable parameter for bias control.
-    latent_mask = nmask[0].float()
+    if len(nmask.shape) == 3:
+        latent_mask = nmask[0].float()
+    else:
+        latent_mask = nmask[:, 0].float()
     # convert the original mask into a form we use to scale distances for thresholding
     mask_scalar = 1 - (torch.clamp(latent_mask, min=0, max=1) ** (settings.mask_blend_scale / 2))
     mask_scalar = (0.5 * (1 - settings.composite_mask_influence)
@@ -157,7 +164,14 @@ def apply_adaptive_masks(
                                                    percentile_min=0.25, percentile_max=0.75, min_width=1)
 
         # The distance at which opacity of original decreases to 50%
-        half_weighted_distance = settings.composite_difference_threshold * mask_scalar
+        if len(mask_scalar.shape) == 3:
+            if mask_scalar.shape[0] > i:
+                half_weighted_distance = settings.composite_difference_threshold * mask_scalar[i]
+            else:
+                half_weighted_distance = settings.composite_difference_threshold * mask_scalar[0]
+        else:
+            half_weighted_distance = settings.composite_difference_threshold * mask_scalar
+
         converted_mask = converted_mask / half_weighted_distance
 
         converted_mask = 1 / (1 + converted_mask ** settings.composite_difference_contrast)

html/extra-networks-card.html

@@ -1,14 +1,9 @@
-<div class='card' style={style} onclick={card_clicked} data-name="{name}" {sort_keys}>
+<div class="card" style="{style}" onclick="{card_clicked}" data-name="{name}" {sort_keys}>
 	{background_image}
-	<div class="button-row">
-		{metadata_button}
-		{edit_button}
-	</div>
-	<div class='actions'>
-		<div class='additional'>
-			<span style="display:none" class='search_term{search_only}'>{search_term}</span>
-		</div>
-		<span class='name'>{name}</span>
-		<span class='description'>{description}</span>
+	<div class="button-row">{copy_path_button}{metadata_button}{edit_button}</div>
+	<div class="actions">
+		<div class="additional">{search_terms}</div>
+		<span class="name">{name}</span>
+		<span class="description">{description}</span>
 	</div>
 </div>

html/extra-networks-copy-path-button.html

@@ -0,0 +1,5 @@
+<div class="copy-path-button card-button"
+    title="Copy path to clipboard"
+    onclick="extraNetworksCopyCardPath(event)"
+    data-clipboard-text="{filename}">
+</div>

html/extra-networks-edit-item-button.html

@@ -0,0 +1,4 @@
+<div class="edit-button card-button"
+    title="Edit metadata"
+    onclick="extraNetworksEditUserMetadata(event, '{tabname}', '{extra_networks_tabname}')">
+</div>

html/extra-networks-metadata-button.html

@@ -0,0 +1,4 @@
+<div class="metadata-button card-button"
+    title="Show internal metadata"
+    onclick="extraNetworksRequestMetadata(event, '{extra_networks_tabname}')">
+</div>

html/extra-networks-pane-dirs.html

@@ -0,0 +1,8 @@
+    <div class="extra-network-pane-content-dirs">
+        <div id='{tabname}_{extra_networks_tabname}_dirs' class='extra-network-dirs'>
+            {dirs_html}
+        </div>
+        <div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards'>
+            {items_html}
+        </div>
+    </div>

html/extra-networks-pane-tree.html

@@ -0,0 +1,8 @@
+    <div class="extra-network-pane-content-tree resize-handle-row">
+        <div id='{tabname}_{extra_networks_tabname}_tree' class='extra-network-tree' style='flex-basis: {extra_networks_tree_view_default_width}px'>
+            {tree_html}
+        </div>
+        <div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards' style='flex-grow: 1;'>
+            {items_html}
+        </div>
+    </div>

html/extra-networks-pane.html

@@ -0,0 +1,81 @@
+<div id='{tabname}_{extra_networks_tabname}_pane' class='extra-network-pane {tree_view_div_default_display_class}'>
+    <div class="extra-network-control" id="{tabname}_{extra_networks_tabname}_controls" style="display:none" >
+        <div class="extra-network-control--search">
+            <input
+                id="{tabname}_{extra_networks_tabname}_extra_search"
+                class="extra-network-control--search-text"
+                type="search"
+                placeholder="Search"
+            >
+        </div>
+
+        <small>Sort: </small>
+        <div 
+            id="{tabname}_{extra_networks_tabname}_extra_sort_path"
+            class="extra-network-control--sort{sort_path_active}"
+            data-sortkey="default"
+            title="Sort by path"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_name"
+            class="extra-network-control--sort{sort_name_active}"
+            data-sortkey="name"
+            title="Sort by name"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_date_created"
+            class="extra-network-control--sort{sort_date_created_active}"
+            data-sortkey="date_created"
+            title="Sort by date created"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_date_modified"
+            class="extra-network-control--sort{sort_date_modified_active}"
+            data-sortkey="date_modified"
+            title="Sort by date modified"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+
+        <small> </small>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_dir"
+            class="extra-network-control--sort-dir"
+            data-sortdir="{data_sortdir}"
+            title="Sort ascending"
+            onclick="extraNetworksControlSortDirOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-dir-icon"></i>
+        </div>
+
+
+        <small> </small>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_tree_view"
+            class="extra-network-control--tree-view {tree_view_btn_extra_class}"
+            title="Enable Tree View"
+            onclick="extraNetworksControlTreeViewOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--tree-view-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_refresh"
+            class="extra-network-control--refresh"
+            title="Refresh page"
+            onclick="extraNetworksControlRefreshOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--refresh-icon"></i>
+        </div>
+    </div>
+    {pane_content}
+</div>

html/extra-networks-tree-button.html

@@ -0,0 +1,23 @@
+<span data-filterable-item-text hidden>{search_terms}</span>
+<div class="tree-list-content {subclass}"
+    type="button"
+    onclick="extraNetworksTreeOnClick(event, '{tabname}', '{extra_networks_tabname}');{onclick_extra}"
+    data-path="{data_path}"
+    data-hash="{data_hash}"
+>
+    <span class='tree-list-item-action tree-list-item-action--leading'>
+        {action_list_item_action_leading}
+    </span>
+    <span class="tree-list-item-visual tree-list-item-visual--leading">
+        {action_list_item_visual_leading}
+    </span>
+    <span class="tree-list-item-label tree-list-item-label--truncate">
+        {action_list_item_label}
+    </span>
+    <span class="tree-list-item-visual tree-list-item-visual--trailing">
+        {action_list_item_visual_trailing}
+    </span>
+    <span class="tree-list-item-action tree-list-item-action--trailing">
+        {action_list_item_action_trailing}
+    </span>
+</div>

javascript/aspectRatioOverlay.js

@@ -50,17 +50,17 @@ function dimensionChange(e, is_width, is_height) {
         var scaledx = targetElement.naturalWidth * viewportscale;
         var scaledy = targetElement.naturalHeight * viewportscale;
 
-        var cleintRectTop = (viewportOffset.top + window.scrollY);
-        var cleintRectLeft = (viewportOffset.left + window.scrollX);
-        var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight / 2);
-        var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth / 2);
+        var clientRectTop = (viewportOffset.top + window.scrollY);
+        var clientRectLeft = (viewportOffset.left + window.scrollX);
+        var clientRectCentreY = clientRectTop + (targetElement.clientHeight / 2);
+        var clientRectCentreX = clientRectLeft + (targetElement.clientWidth / 2);
 
         var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
         var arscaledx = currentWidth * arscale;
         var arscaledy = currentHeight * arscale;
 
-        var arRectTop = cleintRectCentreY - (arscaledy / 2);
-        var arRectLeft = cleintRectCentreX - (arscaledx / 2);
+        var arRectTop = clientRectCentreY - (arscaledy / 2);
+        var arRectLeft = clientRectCentreX - (arscaledx / 2);
         var arRectWidth = arscaledx;
         var arRectHeight = arscaledy;
 

javascript/dragdrop.js

@@ -74,22 +74,39 @@ window.document.addEventListener('dragover', e => {
     e.dataTransfer.dropEffect = 'copy';
 });
 
-window.document.addEventListener('drop', e => {
+window.document.addEventListener('drop', async e => {
     const target = e.composedPath()[0];
-    if (!eventHasFiles(e)) return;
+    const url = e.dataTransfer.getData('text/uri-list') || e.dataTransfer.getData('text/plain');
+    if (!eventHasFiles(e) && !url) return;
 
     if (dragDropTargetIsPrompt(target)) {
         e.stopPropagation();
         e.preventDefault();
 
-        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
+        const isImg2img = get_tab_index('tabs') == 1;
+        let prompt_image_target = isImg2img ? "img2img_prompt_image" : "txt2img_prompt_image";
 
-        const imgParent = gradioApp().getElementById(prompt_target);
+        const imgParent = gradioApp().getElementById(prompt_image_target);
         const files = e.dataTransfer.files;
         const fileInput = imgParent.querySelector('input[type="file"]');
-        if (fileInput) {
+        if (eventHasFiles(e) && fileInput) {
             fileInput.files = files;
             fileInput.dispatchEvent(new Event('change'));
+        } else if (url) {
+            try {
+                const request = await fetch(url);
+                if (!request.ok) {
+                    console.error('Error fetching URL:', url, request.status);
+                    return;
+                }
+                const data = new DataTransfer();
+                data.items.add(new File([await request.blob()], 'image.png'));
+                fileInput.files = data.files;
+                fileInput.dispatchEvent(new Event('change'));
+            } catch (error) {
+                console.error('Error fetching URL:', url, error);
+                return;
+            }
         }
     }
 

javascript/edit-attention.js

@@ -64,6 +64,14 @@ function keyupEditAttention(event) {
             selectionEnd++;
         }
 
+        // deselect surrounding whitespace
+        while (text[selectionStart] == " " && selectionStart < selectionEnd) {
+            selectionStart++;
+        }
+        while (text[selectionEnd - 1] == " " && selectionEnd > selectionStart) {
+            selectionEnd--;
+        }
+
         target.setSelectionRange(selectionStart, selectionEnd);
         return true;
     }

javascript/extensions.js

@@ -2,8 +2,11 @@
 function extensions_apply(_disabled_list, _update_list, disable_all) {
     var disable = [];
     var update = [];
-
-    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
+    const extensions_input = gradioApp().querySelectorAll('#extensions input[type="checkbox"]');
+    if (extensions_input.length == 0) {
+        throw Error("Extensions page not yet loaded.");
+    }
+    extensions_input.forEach(function(x) {
         if (x.name.startsWith("enable_") && !x.checked) {
             disable.push(x.name.substring(7));
         }

javascript/extraNetworks.js

@@ -16,99 +16,116 @@ function toggleCss(key, css, enable) {
 }
 
 function setupExtraNetworksForTab(tabname) {
-    gradioApp().querySelector('#' + tabname + '_extra_tabs').classList.add('extra-networks');
+    function registerPrompt(tabname, id) {
+        var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
 
-    var tabs = gradioApp().querySelector('#' + tabname + '_extra_tabs > div');
-    var searchDiv = gradioApp().getElementById(tabname + '_extra_search');
-    var search = searchDiv.querySelector('textarea');
-    var sort = gradioApp().getElementById(tabname + '_extra_sort');
-    var sortOrder = gradioApp().getElementById(tabname + '_extra_sortorder');
-    var refresh = gradioApp().getElementById(tabname + '_extra_refresh');
-    var showDirsDiv = gradioApp().getElementById(tabname + '_extra_show_dirs');
-    var showDirs = gradioApp().querySelector('#' + tabname + '_extra_show_dirs input');
-    var promptContainer = gradioApp().querySelector('.prompt-container-compact#' + tabname + '_prompt_container');
-    var negativePrompt = gradioApp().querySelector('#' + tabname + '_neg_prompt');
+        if (!activePromptTextarea[tabname]) {
+            activePromptTextarea[tabname] = textarea;
+        }
 
-    tabs.appendChild(searchDiv);
-    tabs.appendChild(sort);
-    tabs.appendChild(sortOrder);
-    tabs.appendChild(refresh);
-    tabs.appendChild(showDirsDiv);
+        textarea.addEventListener("focus", function() {
+            activePromptTextarea[tabname] = textarea;
+        });
+    }
 
-    var applyFilter = function() {
-        var searchTerm = search.value.toLowerCase();
+    var tabnav = gradioApp().querySelector('#' + tabname + '_extra_tabs > div.tab-nav');
+    var controlsDiv = document.createElement('DIV');
+    controlsDiv.classList.add('extra-networks-controls-div');
+    tabnav.appendChild(controlsDiv);
+    tabnav.insertBefore(controlsDiv, null);
 
-        gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
-            var searchOnly = elem.querySelector('.search_only');
-            var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase();
+    var this_tab = gradioApp().querySelector('#' + tabname + '_extra_tabs');
+    this_tab.querySelectorAll(":scope > [id^='" + tabname + "_']").forEach(function(elem) {
+        // tabname_full = {tabname}_{extra_networks_tabname}
+        var tabname_full = elem.id;
+        var search = gradioApp().querySelector("#" + tabname_full + "_extra_search");
+        var sort_dir = gradioApp().querySelector("#" + tabname_full + "_extra_sort_dir");
+        var refresh = gradioApp().querySelector("#" + tabname_full + "_extra_refresh");
+        var currentSort = '';
 
-            var visible = text.indexOf(searchTerm) != -1;
+        // If any of the buttons above don't exist, we want to skip this iteration of the loop.
+        if (!search || !sort_dir || !refresh) {
+            return; // `return` is equivalent of `continue` but for forEach loops.
+        }
 
-            if (searchOnly && searchTerm.length < 4) {
-                visible = false;
+        var applyFilter = function(force) {
+            var searchTerm = search.value.toLowerCase();
+            gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
+                var searchOnly = elem.querySelector('.search_only');
+                var text = Array.prototype.map.call(elem.querySelectorAll('.search_terms, .description'), function(t) {
+                    return t.textContent.toLowerCase();
+                }).join(" ");
+
+                var visible = text.indexOf(searchTerm) != -1;
+                if (searchOnly && searchTerm.length < 4) {
+                    visible = false;
+                }
+                if (visible) {
+                    elem.classList.remove("hidden");
+                } else {
+                    elem.classList.add("hidden");
+                }
+            });
+
+            applySort(force);
+        };
+
+        var applySort = function(force) {
+            var cards = gradioApp().querySelectorAll('#' + tabname_full + ' div.card');
+            var parent = gradioApp().querySelector('#' + tabname_full + "_cards");
+            var reverse = sort_dir.dataset.sortdir == "Descending";
+            var activeSearchElem = gradioApp().querySelector('#' + tabname_full + "_controls .extra-network-control--sort.extra-network-control--enabled");
+            var sortKey = activeSearchElem ? activeSearchElem.dataset.sortkey : "default";
+            var sortKeyDataField = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
+            var sortKeyStore = sortKey + "-" + sort_dir.dataset.sortdir + "-" + cards.length;
+
+            if (sortKeyStore == currentSort && !force) {
+                return;
+            }
+            currentSort = sortKeyStore;
+
+            var sortedCards = Array.from(cards);
+            sortedCards.sort(function(cardA, cardB) {
+                var a = cardA.dataset[sortKeyDataField];
+                var b = cardB.dataset[sortKeyDataField];
+                if (!isNaN(a) && !isNaN(b)) {
+                    return parseInt(a) - parseInt(b);
+                }
+
+                return (a < b ? -1 : (a > b ? 1 : 0));
+            });
+
+            if (reverse) {
+                sortedCards.reverse();
             }
 
-            elem.style.display = visible ? "" : "none";
-        });
+            parent.innerHTML = '';
 
+            var frag = document.createDocumentFragment();
+            sortedCards.forEach(function(card) {
+                frag.appendChild(card);
+            });
+            parent.appendChild(frag);
+        };
+
+        search.addEventListener("input", function() {
+            applyFilter();
+        });
         applySort();
-    };
+        applyFilter();
+        extraNetworksApplySort[tabname_full] = applySort;
+        extraNetworksApplyFilter[tabname_full] = applyFilter;
 
-    var applySort = function() {
-        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
+        var controls = gradioApp().querySelector("#" + tabname_full + "_controls");
+        controlsDiv.insertBefore(controls, null);
 
-        var reverse = sortOrder.classList.contains("sortReverse");
-        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;
+        if (elem.style.display != "none") {
+            extraNetworksShowControlsForPage(tabname, tabname_full);
         }
-        sort.dataset.sortkey = sortKeyStore;
-
-        cards.forEach(function(card) {
-            card.originalParentElement = card.parentElement;
-        });
-        var sortedCards = Array.from(cards);
-        sortedCards.sort(function(cardA, cardB) {
-            var a = cardA.dataset[sortKey];
-            var b = cardB.dataset[sortKey];
-            if (!isNaN(a) && !isNaN(b)) {
-                return parseInt(a) - parseInt(b);
-            }
-
-            return (a < b ? -1 : (a > b ? 1 : 0));
-        });
-        if (reverse) {
-            sortedCards.reverse();
-        }
-        cards.forEach(function(card) {
-            card.remove();
-        });
-        sortedCards.forEach(function(card) {
-            card.originalParentElement.appendChild(card);
-        });
-    };
-
-    search.addEventListener("input", applyFilter);
-    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();
+    registerPrompt(tabname, tabname + "_prompt");
+    registerPrompt(tabname, tabname + "_neg_prompt");
 }
 
 function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt) {
@@ -137,21 +154,42 @@ function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePromp
 }
 
 
-function extraNetworksUrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
-    extraNetworksMovePromptToTab(tabname, '', false, false);
+function extraNetworksShowControlsForPage(tabname, tabname_full) {
+    gradioApp().querySelectorAll('#' + tabname + '_extra_tabs .extra-networks-controls-div > div').forEach(function(elem) {
+        var targetId = tabname_full + "_controls";
+        elem.style.display = elem.id == targetId ? "" : "none";
+    });
 }
 
-function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt) { // called from python when user selects an extra networks tab
+
+function extraNetworksUnrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
+    extraNetworksMovePromptToTab(tabname, '', false, false);
+
+    extraNetworksShowControlsForPage(tabname, null);
+}
+
+function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt, tabname_full) { // called from python when user selects an extra networks tab
     extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt);
 
+    extraNetworksShowControlsForPage(tabname, tabname_full);
 }
 
-function applyExtraNetworkFilter(tabname) {
-    setTimeout(extraNetworksApplyFilter[tabname], 1);
+function applyExtraNetworkFilter(tabname_full) {
+    var doFilter = function() {
+        var applyFunction = extraNetworksApplyFilter[tabname_full];
+
+        if (applyFunction) {
+            applyFunction(true);
+        }
+    };
+    setTimeout(doFilter, 1);
 }
 
-function applyExtraNetworkSort(tabname) {
-    setTimeout(extraNetworksApplySort[tabname], 1);
+function applyExtraNetworkSort(tabname_full) {
+    var doSort = function() {
+        extraNetworksApplySort[tabname_full](true);
+    };
+    setTimeout(doSort, 1);
 }
 
 var extraNetworksApplyFilter = {};
@@ -161,27 +199,8 @@ var activePromptTextarea = {};
 function setupExtraNetworks() {
     setupExtraNetworksForTab('txt2img');
     setupExtraNetworksForTab('img2img');
-
-    function registerPrompt(tabname, id) {
-        var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
-
-        if (!activePromptTextarea[tabname]) {
-            activePromptTextarea[tabname] = textarea;
-        }
-
-        textarea.addEventListener("focus", function() {
-            activePromptTextarea[tabname] = textarea;
-        });
-    }
-
-    registerPrompt('txt2img', 'txt2img_prompt');
-    registerPrompt('txt2img', 'txt2img_neg_prompt');
-    registerPrompt('img2img', 'img2img_prompt');
-    registerPrompt('img2img', 'img2img_neg_prompt');
 }
 
-onUiLoaded(setupExtraNetworks);
-
 var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
 var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
 
@@ -191,8 +210,8 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
     var m = text.match(isNeg ? re_extranet_neg : re_extranet);
     var replaced = false;
     var newTextareaText;
+    var extraTextBeforeNet = opts.extra_networks_add_text_separator;
     if (m) {
-        var extraTextBeforeNet = opts.extra_networks_add_text_separator;
         var extraTextAfterNet = m[2];
         var partToSearch = m[1];
         var foundAtPosition = -1;
@@ -205,7 +224,6 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
             }
             return found;
         });
-
         if (foundAtPosition >= 0) {
             if (extraTextAfterNet && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
                 newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
@@ -215,13 +233,8 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
             }
         }
     } else {
-        newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) {
-            if (found == text) {
-                replaced = true;
-                return "";
-            }
-            return found;
-        });
+        newTextareaText = textarea.value.replaceAll(new RegExp(`((?:${extraTextBeforeNet})?${text})`, "g"), "");
+        replaced = (newTextareaText != textarea.value);
     }
 
     if (replaced) {
@@ -233,7 +246,6 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
 }
 
 function updatePromptArea(text, textArea, isNeg) {
-
     if (!tryToRemoveExtraNetworkFromPrompt(textArea, text, isNeg)) {
         textArea.value = textArea.value + opts.extra_networks_add_text_separator + text;
     }
@@ -264,8 +276,8 @@ function saveCardPreview(event, tabname, filename) {
     event.preventDefault();
 }
 
-function extraNetworksSearchButton(tabs_id, event) {
-    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > label > textarea');
+function extraNetworksSearchButton(tabname, extra_networks_tabname, event) {
+    var searchTextarea = gradioApp().querySelector("#" + tabname + "_" + extra_networks_tabname + "_extra_search");
     var button = event.target;
     var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
 
@@ -273,6 +285,187 @@ function extraNetworksSearchButton(tabs_id, event) {
     updateInput(searchTextarea);
 }
 
+function extraNetworksTreeProcessFileClick(event, btn, tabname, extra_networks_tabname) {
+    /**
+     * Processes `onclick` events when user clicks on files in tree.
+     *
+     * @param event                     The generated event.
+     * @param btn                       The clicked `tree-list-item` button.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    // NOTE: Currently unused.
+    return;
+}
+
+function extraNetworksTreeProcessDirectoryClick(event, btn, tabname, extra_networks_tabname) {
+    /**
+     * Processes `onclick` events when user clicks on directories in tree.
+     *
+     * Here is how the tree reacts to clicks for various states:
+     * unselected unopened directory: Directory is selected and expanded.
+     * unselected opened directory: Directory is selected.
+     * selected opened directory: Directory is collapsed and deselected.
+     * chevron is clicked: Directory is expanded or collapsed. Selected state unchanged.
+     *
+     * @param event                     The generated event.
+     * @param btn                       The clicked `tree-list-item` button.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var ul = btn.nextElementSibling;
+    // This is the actual target that the user clicked on within the target button.
+    // We use this to detect if the chevron was clicked.
+    var true_targ = event.target;
+
+    function _expand_or_collapse(_ul, _btn) {
+        // Expands <ul> if it is collapsed, collapses otherwise. Updates button attributes.
+        if (_ul.hasAttribute("hidden")) {
+            _ul.removeAttribute("hidden");
+            _btn.dataset.expanded = "";
+        } else {
+            _ul.setAttribute("hidden", "");
+            delete _btn.dataset.expanded;
+        }
+    }
+
+    function _remove_selected_from_all() {
+        // Removes the `selected` attribute from all buttons.
+        var sels = document.querySelectorAll("div.tree-list-content");
+        [...sels].forEach(el => {
+            delete el.dataset.selected;
+        });
+    }
+
+    function _select_button(_btn) {
+        // Removes `data-selected` attribute from all buttons then adds to passed button.
+        _remove_selected_from_all();
+        _btn.dataset.selected = "";
+    }
+
+    function _update_search(_tabname, _extra_networks_tabname, _search_text) {
+        // Update search input with select button's path.
+        var search_input_elem = gradioApp().querySelector("#" + tabname + "_" + extra_networks_tabname + "_extra_search");
+        search_input_elem.value = _search_text;
+        updateInput(search_input_elem);
+    }
+
+
+    // If user clicks on the chevron, then we do not select the folder.
+    if (true_targ.matches(".tree-list-item-action--leading, .tree-list-item-action-chevron")) {
+        _expand_or_collapse(ul, btn);
+    } else {
+        // User clicked anywhere else on the button.
+        if ("selected" in btn.dataset && !(ul.hasAttribute("hidden"))) {
+            // If folder is select and open, collapse and deselect button.
+            _expand_or_collapse(ul, btn);
+            delete btn.dataset.selected;
+            _update_search(tabname, extra_networks_tabname, "");
+        } else if (!(!("selected" in btn.dataset) && !(ul.hasAttribute("hidden")))) {
+            // If folder is open and not selected, then we don't collapse; just select.
+            // NOTE: Double inversion sucks but it is the clearest way to show the branching here.
+            _expand_or_collapse(ul, btn);
+            _select_button(btn, tabname, extra_networks_tabname);
+            _update_search(tabname, extra_networks_tabname, btn.dataset.path);
+        } else {
+            // All other cases, just select the button.
+            _select_button(btn, tabname, extra_networks_tabname);
+            _update_search(tabname, extra_networks_tabname, btn.dataset.path);
+        }
+    }
+}
+
+function extraNetworksTreeOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for buttons within an `extra-network-tree .tree-list--tree`.
+     *
+     * Determines whether the clicked button in the tree is for a file entry or a directory
+     * then calls the appropriate function.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var btn = event.currentTarget;
+    var par = btn.parentElement;
+    if (par.dataset.treeEntryType === "file") {
+        extraNetworksTreeProcessFileClick(event, btn, tabname, extra_networks_tabname);
+    } else {
+        extraNetworksTreeProcessDirectoryClick(event, btn, tabname, extra_networks_tabname);
+    }
+}
+
+function extraNetworksControlSortOnClick(event, tabname, extra_networks_tabname) {
+    /** Handles `onclick` events for Sort Mode buttons. */
+
+    var self = event.currentTarget;
+    var parent = event.currentTarget.parentElement;
+
+    parent.querySelectorAll('.extra-network-control--sort').forEach(function(x) {
+        x.classList.remove('extra-network-control--enabled');
+    });
+
+    self.classList.add('extra-network-control--enabled');
+
+    applyExtraNetworkSort(tabname + "_" + extra_networks_tabname);
+}
+
+function extraNetworksControlSortDirOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for the Sort Direction button.
+     *
+     * Modifies the data attributes of the Sort Direction button to cycle between
+     * ascending and descending sort directions.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    if (event.currentTarget.dataset.sortdir == "Ascending") {
+        event.currentTarget.dataset.sortdir = "Descending";
+        event.currentTarget.setAttribute("title", "Sort descending");
+    } else {
+        event.currentTarget.dataset.sortdir = "Ascending";
+        event.currentTarget.setAttribute("title", "Sort ascending");
+    }
+    applyExtraNetworkSort(tabname + "_" + extra_networks_tabname);
+}
+
+function extraNetworksControlTreeViewOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for the Tree View button.
+     *
+     * Toggles the tree view in the extra networks pane.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var button = event.currentTarget;
+    button.classList.toggle("extra-network-control--enabled");
+    var show = !button.classList.contains("extra-network-control--enabled");
+
+    var pane = gradioApp().getElementById(tabname + "_" + extra_networks_tabname + "_pane");
+    pane.classList.toggle("extra-network-dirs-hidden", show);
+}
+
+function extraNetworksControlRefreshOnClick(event, tabname, extra_networks_tabname) {
+    /**
+     * Handles `onclick` events for the Refresh Page button.
+     *
+     * In order to actually call the python functions in `ui_extra_networks.py`
+     * to refresh the page, we created an empty gradio button in that file with an
+     * event handler that refreshes the page. So what this function here does
+     * is it manually raises a `click` event on that button.
+     *
+     * @param event                     The generated event.
+     * @param tabname                   The name of the active tab in the sd webui. Ex: txt2img, img2img, etc.
+     * @param extra_networks_tabname    The id of the active extraNetworks tab. Ex: lora, checkpoints, etc.
+     */
+    var btn_refresh_internal = gradioApp().getElementById(tabname + "_" + extra_networks_tabname + "_extra_refresh_internal");
+    btn_refresh_internal.dispatchEvent(new Event("click"));
+}
+
 var globalPopup = null;
 var globalPopupInner = null;
 
@@ -314,12 +507,76 @@ function popupId(id) {
     popup(storedPopupIds[id]);
 }
 
+function extraNetworksFlattenMetadata(obj) {
+    const result = {};
+
+    // Convert any stringified JSON objects to actual objects
+    for (const key of Object.keys(obj)) {
+        if (typeof obj[key] === 'string') {
+            try {
+                const parsed = JSON.parse(obj[key]);
+                if (parsed && typeof parsed === 'object') {
+                    obj[key] = parsed;
+                }
+            } catch (error) {
+                continue;
+            }
+        }
+    }
+
+    // Flatten the object
+    for (const key of Object.keys(obj)) {
+        if (typeof obj[key] === 'object' && obj[key] !== null) {
+            const nested = extraNetworksFlattenMetadata(obj[key]);
+            for (const nestedKey of Object.keys(nested)) {
+                result[`${key}/${nestedKey}`] = nested[nestedKey];
+            }
+        } else {
+            result[key] = obj[key];
+        }
+    }
+
+    // Special case for handling modelspec keys
+    for (const key of Object.keys(result)) {
+        if (key.startsWith("modelspec.")) {
+            result[key.replaceAll(".", "/")] = result[key];
+            delete result[key];
+        }
+    }
+
+    // Add empty keys to designate hierarchy
+    for (const key of Object.keys(result)) {
+        const parts = key.split("/");
+        for (let i = 1; i < parts.length; i++) {
+            const parent = parts.slice(0, i).join("/");
+            if (!result[parent]) {
+                result[parent] = "";
+            }
+        }
+    }
+
+    return result;
+}
+
 function extraNetworksShowMetadata(text) {
+    try {
+        let parsed = JSON.parse(text);
+        if (parsed && typeof parsed === 'object') {
+            parsed = extraNetworksFlattenMetadata(parsed);
+            const table = createVisualizationTable(parsed, 0);
+            popup(table);
+            return;
+        }
+    } catch (error) {
+        console.error(error);
+    }
+
     var elem = document.createElement('pre');
     elem.classList.add('popup-metadata');
     elem.textContent = text;
 
     popup(elem);
+    return;
 }
 
 function requestGet(url, data, handler, errorHandler) {
@@ -348,11 +605,18 @@ function requestGet(url, data, handler, errorHandler) {
     xhr.send(js);
 }
 
-function extraNetworksRequestMetadata(event, extraPage, cardName) {
+function extraNetworksCopyCardPath(event) {
+    navigator.clipboard.writeText(event.target.getAttribute("data-clipboard-text"));
+    event.stopPropagation();
+}
+
+function extraNetworksRequestMetadata(event, extraPage) {
     var showError = function() {
         extraNetworksShowMetadata("there was an error getting metadata");
     };
 
+    var cardName = event.target.parentElement.parentElement.getAttribute("data-name");
+
     requestGet("./sd_extra_networks/metadata", {page: extraPage, item: cardName}, function(data) {
         if (data && data.metadata) {
             extraNetworksShowMetadata(data.metadata);
@@ -366,7 +630,7 @@ function extraNetworksRequestMetadata(event, extraPage, cardName) {
 
 var extraPageUserMetadataEditors = {};
 
-function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
+function extraNetworksEditUserMetadata(event, tabname, extraPage) {
     var id = tabname + '_' + extraPage + '_edit_user_metadata';
 
     var editor = extraPageUserMetadataEditors[id];
@@ -378,6 +642,7 @@ function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
         extraPageUserMetadataEditors[id] = editor;
     }
 
+    var cardName = event.target.parentElement.parentElement.getAttribute("data-name");
     editor.nameTextarea.value = cardName;
     updateInput(editor.nameTextarea);
 
@@ -409,3 +674,39 @@ window.addEventListener("keydown", function(event) {
         closePopup();
     }
 });
+
+/**
+ * Setup custom loading for this script.
+ * We need to wait for all of our HTML to be generated in the extra networks tabs
+ * before we can actually run the `setupExtraNetworks` function.
+ * The `onUiLoaded` function actually runs before all of our extra network tabs are
+ * finished generating. Thus we needed this new method.
+ *
+ */
+
+var uiAfterScriptsCallbacks = [];
+var uiAfterScriptsTimeout = null;
+var executedAfterScripts = false;
+
+function scheduleAfterScriptsCallbacks() {
+    clearTimeout(uiAfterScriptsTimeout);
+    uiAfterScriptsTimeout = setTimeout(function() {
+        executeCallbacks(uiAfterScriptsCallbacks);
+    }, 200);
+}
+
+onUiLoaded(function() {
+    var mutationObserver = new MutationObserver(function(m) {
+        let existingSearchfields = gradioApp().querySelectorAll("[id$='_extra_search']").length;
+        let neededSearchfields = gradioApp().querySelectorAll("[id$='_extra_tabs'] > .tab-nav > button").length - 2;
+
+        if (!executedAfterScripts && existingSearchfields >= neededSearchfields) {
+            mutationObserver.disconnect();
+            executedAfterScripts = true;
+            scheduleAfterScriptsCallbacks();
+        }
+    });
+    mutationObserver.observe(gradioApp(), {childList: true, subtree: true});
+});
+
+uiAfterScriptsCallbacks.push(setupExtraNetworks);

javascript/imageviewer.js

@@ -131,19 +131,15 @@ function setupImageForLightbox(e) {
     e.style.cursor = 'pointer';
     e.style.userSelect = 'none';
 
-    var isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1;
-
-    // For Firefox, listening on click first switched to next image then shows the lightbox.
-    // If you know how to fix this without switching to mousedown event, please.
-    // For other browsers the event is click to make it possiblr to drag picture.
-    var event = isFirefox ? 'mousedown' : 'click';
-
-    e.addEventListener(event, function(evt) {
+    e.addEventListener('mousedown', function(evt) {
         if (evt.button == 1) {
             open(evt.target.src);
             evt.preventDefault();
             return;
         }
+    }, true);
+
+    e.addEventListener('click', function(evt) {
         if (!opts.js_modal_lightbox || evt.button != 0) return;
 
         modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed);

javascript/profilerVisualization.js

@@ -33,120 +33,141 @@ function createRow(table, cellName, items) {
     return res;
 }
 
-function showProfile(path, cutoff = 0.05) {
-    requestGet(path, {}, function(data) {
-        var table = document.createElement('table');
-        table.className = 'popup-table';
+function createVisualizationTable(data, cutoff = 0, sort = "") {
+    var table = document.createElement('table');
+    table.className = 'popup-table';
 
-        data.records['total'] = data.total;
-        var keys = Object.keys(data.records).sort(function(a, b) {
-            return data.records[b] - data.records[a];
+    var keys = Object.keys(data);
+    if (sort === "number") {
+        keys = keys.sort(function(a, b) {
+            return data[b] - data[a];
         });
-        var items = keys.map(function(x) {
-            return {key: x, parts: x.split('/'), time: data.records[x]};
+    } else {
+        keys = keys.sort();
+    }
+    var items = keys.map(function(x) {
+        return {key: x, parts: x.split('/'), value: data[x]};
+    });
+    var maxLength = items.reduce(function(a, b) {
+        return Math.max(a, b.parts.length);
+    }, 0);
+
+    var cols = createRow(
+        table,
+        'th',
+        [
+            cutoff === 0 ? 'key' : 'record',
+            cutoff === 0 ? 'value' : 'seconds'
+        ]
+    );
+    cols[0].colSpan = maxLength;
+
+    function arraysEqual(a, b) {
+        return !(a < b || b < a);
+    }
+
+    var addLevel = function(level, parent, hide) {
+        var matching = items.filter(function(x) {
+            return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
         });
-        var maxLength = items.reduce(function(a, b) {
-            return Math.max(a, b.parts.length);
-        }, 0);
-
-        var cols = createRow(table, 'th', ['record', 'seconds']);
-        cols[0].colSpan = maxLength;
-
-        function arraysEqual(a, b) {
-            return !(a < b || b < a);
+        if (sort === "number") {
+            matching = matching.sort(function(a, b) {
+                return b.value - a.value;
+            });
+        } else {
+            matching = matching.sort();
         }
+        var othersTime = 0;
+        var othersList = [];
+        var othersRows = [];
+        var childrenRows = [];
+        matching.forEach(function(x) {
+            var visible = (cutoff === 0 && !hide) || (x.value >= cutoff && !hide);
 
-        var addLevel = function(level, parent, hide) {
-            var matching = items.filter(function(x) {
-                return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
-            });
-            var sorted = matching.sort(function(a, b) {
-                return b.time - a.time;
-            });
-            var othersTime = 0;
-            var othersList = [];
-            var othersRows = [];
-            var childrenRows = [];
-            sorted.forEach(function(x) {
-                var visible = x.time >= cutoff && !hide;
+            var cells = [];
+            for (var i = 0; i < maxLength; i++) {
+                cells.push(x.parts[i]);
+            }
+            cells.push(cutoff === 0 ? x.value : x.value.toFixed(3));
+            var cols = createRow(table, 'td', cells);
+            for (i = 0; i < level; i++) {
+                cols[i].className = 'muted';
+            }
 
-                var cells = [];
-                for (var i = 0; i < maxLength; i++) {
-                    cells.push(x.parts[i]);
-                }
-                cells.push(x.time.toFixed(3));
-                var cols = createRow(table, 'td', cells);
-                for (i = 0; i < level; i++) {
-                    cols[i].className = 'muted';
-                }
+            var tr = cols[0].parentNode;
+            if (!visible) {
+                tr.classList.add("hidden");
+            }
 
-                var tr = cols[0].parentNode;
-                if (!visible) {
-                    tr.classList.add("hidden");
-                }
-
-                if (x.time >= cutoff) {
-                    childrenRows.push(tr);
-                } else {
-                    othersTime += x.time;
-                    othersList.push(x.parts[level]);
-                    othersRows.push(tr);
-                }
-
-                var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
-                if (children.length > 0) {
-                    var cell = cols[level];
-                    var onclick = function() {
-                        cell.classList.remove("link");
-                        cell.removeEventListener("click", onclick);
-                        children.forEach(function(x) {
-                            x.classList.remove("hidden");
-                        });
-                    };
-                    cell.classList.add("link");
-                    cell.addEventListener("click", onclick);
-                }
-            });
-
-            if (othersTime > 0) {
-                var cells = [];
-                for (var i = 0; i < maxLength; i++) {
-                    cells.push(parent[i]);
-                }
-                cells.push(othersTime.toFixed(3));
-                cells[level] = 'others';
-                var cols = createRow(table, 'td', cells);
-                for (i = 0; i < level; i++) {
-                    cols[i].className = 'muted';
-                }
+            if (cutoff === 0 || x.value >= cutoff) {
+                childrenRows.push(tr);
+            } else {
+                othersTime += x.value;
+                othersList.push(x.parts[level]);
+                othersRows.push(tr);
+            }
 
+            var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
+            if (children.length > 0) {
                 var cell = cols[level];
-                var tr = cell.parentNode;
                 var onclick = function() {
-                    tr.classList.add("hidden");
                     cell.classList.remove("link");
                     cell.removeEventListener("click", onclick);
-                    othersRows.forEach(function(x) {
+                    children.forEach(function(x) {
                         x.classList.remove("hidden");
                     });
                 };
-
-                cell.title = othersList.join(", ");
                 cell.classList.add("link");
                 cell.addEventListener("click", onclick);
+            }
+        });
 
-                if (hide) {
-                    tr.classList.add("hidden");
-                }
-
-                childrenRows.push(tr);
+        if (othersTime > 0) {
+            var cells = [];
+            for (var i = 0; i < maxLength; i++) {
+                cells.push(parent[i]);
+            }
+            cells.push(othersTime.toFixed(3));
+            cells[level] = 'others';
+            var cols = createRow(table, 'td', cells);
+            for (i = 0; i < level; i++) {
+                cols[i].className = 'muted';
             }
 
-            return childrenRows;
-        };
+            var cell = cols[level];
+            var tr = cell.parentNode;
+            var onclick = function() {
+                tr.classList.add("hidden");
+                cell.classList.remove("link");
+                cell.removeEventListener("click", onclick);
+                othersRows.forEach(function(x) {
+                    x.classList.remove("hidden");
+                });
+            };
 
-        addLevel(0, []);
+            cell.title = othersList.join(", ");
+            cell.classList.add("link");
+            cell.addEventListener("click", onclick);
 
+            if (hide) {
+                tr.classList.add("hidden");
+            }
+
+            childrenRows.push(tr);
+        }
+
+        return childrenRows;
+    };
+
+    addLevel(0, []);
+
+    return table;
+}
+
+function showProfile(path, cutoff = 0.05) {
+    requestGet(path, {}, function(data) {
+        data.records['total'] = data.total;
+        const table = createVisualizationTable(data.records, cutoff, "number");
         popup(table);
     });
 }

javascript/progressbar.js

@@ -45,8 +45,15 @@ function formatTime(secs) {
     }
 }
 
+
+var originalAppTitle = undefined;
+
+onUiLoaded(function() {
+    originalAppTitle = document.title;
+});
+
 function setTitle(progress) {
-    var title = 'Stable Diffusion';
+    var title = originalAppTitle;
 
     if (opts.show_progress_in_title && progress) {
         title = '[' + progress.trim() + '] ' + title;

javascript/resizeHandle.js

@@ -1,8 +1,8 @@
 (function() {
     const GRADIO_MIN_WIDTH = 320;
-    const GRID_TEMPLATE_COLUMNS = '1fr 16px 1fr';
     const PAD = 16;
     const DEBOUNCE_TIME = 100;
+    const DOUBLE_TAP_DELAY = 200; //ms
 
     const R = {
         tracking: false,
@@ -11,6 +11,7 @@
         leftCol: null,
         leftColStartWidth: null,
         screenX: null,
+        lastTapTime: null,
     };
 
     let resizeTimer;
@@ -21,30 +22,29 @@
     }
 
     function displayResizeHandle(parent) {
+        if (!parent.needHideOnMoblie) {
+            return true;
+        }
         if (window.innerWidth < GRADIO_MIN_WIDTH * 2 + PAD * 4) {
             parent.style.display = 'flex';
-            if (R.handle != null) {
-                R.handle.style.opacity = '0';
-            }
+            parent.resizeHandle.style.display = "none";
             return false;
         } else {
             parent.style.display = 'grid';
-            if (R.handle != null) {
-                R.handle.style.opacity = '100';
-            }
+            parent.resizeHandle.style.display = "block";
             return true;
         }
     }
 
     function afterResize(parent) {
-        if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != GRID_TEMPLATE_COLUMNS) {
+        if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != parent.style.originalGridTemplateColumns) {
             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);
+            const newWidthL = Math.max(Math.floor(ratio * widthL), parent.minLeftColWidth);
             setLeftColGridTemplate(parent, newWidthL);
 
             R.parentWidth = newParentWidth;
@@ -52,6 +52,14 @@
     }
 
     function setup(parent) {
+
+        function onDoubleClick(evt) {
+            evt.preventDefault();
+            evt.stopPropagation();
+
+            parent.style.gridTemplateColumns = parent.style.originalGridTemplateColumns;
+        }
+
         const leftCol = parent.firstElementChild;
         const rightCol = parent.lastElementChild;
 
@@ -59,63 +67,114 @@
 
         parent.style.display = 'grid';
         parent.style.gap = '0';
-        parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS;
+        let leftColTemplate = "";
+        if (parent.children[0].style.flexGrow) {
+            leftColTemplate = `${parent.children[0].style.flexGrow}fr`;
+            parent.minLeftColWidth = GRADIO_MIN_WIDTH;
+            parent.minRightColWidth = GRADIO_MIN_WIDTH;
+            parent.needHideOnMoblie = true;
+        } else {
+            leftColTemplate = parent.children[0].style.flexBasis;
+            parent.minLeftColWidth = parent.children[0].style.flexBasis.slice(0, -2) / 2;
+            parent.minRightColWidth = 0;
+            parent.needHideOnMoblie = false;
+        }
+
+        if (!leftColTemplate) {
+            leftColTemplate = '1fr';
+        }
+
+        const gridTemplateColumns = `${leftColTemplate} ${PAD}px ${parent.children[1].style.flexGrow}fr`;
+        parent.style.gridTemplateColumns = gridTemplateColumns;
+        parent.style.originalGridTemplateColumns = gridTemplateColumns;
 
         const resizeHandle = document.createElement('div');
         resizeHandle.classList.add('resize-handle');
         parent.insertBefore(resizeHandle, rightCol);
+        parent.resizeHandle = resizeHandle;
 
-        resizeHandle.addEventListener('mousedown', (evt) => {
-            if (evt.button !== 0) return;
+        ['mousedown', 'touchstart'].forEach((eventType) => {
+            resizeHandle.addEventListener(eventType, (evt) => {
+                if (eventType.startsWith('mouse')) {
+                    if (evt.button !== 0) return;
+                } else {
+                    if (evt.changedTouches.length !== 1) return;
 
-            evt.preventDefault();
-            evt.stopPropagation();
+                    const currentTime = new Date().getTime();
+                    if (R.lastTapTime && currentTime - R.lastTapTime <= DOUBLE_TAP_DELAY) {
+                        onDoubleClick(evt);
+                        return;
+                    }
 
-            document.body.classList.add('resizing');
+                    R.lastTapTime = currentTime;
+                }
 
-            R.tracking = true;
-            R.parent = parent;
-            R.parentWidth = parent.offsetWidth;
-            R.handle = resizeHandle;
-            R.leftCol = leftCol;
-            R.leftColStartWidth = leftCol.offsetWidth;
-            R.screenX = evt.screenX;
+                evt.preventDefault();
+                evt.stopPropagation();
+
+                document.body.classList.add('resizing');
+
+                R.tracking = true;
+                R.parent = parent;
+                R.parentWidth = parent.offsetWidth;
+                R.leftCol = leftCol;
+                R.leftColStartWidth = leftCol.offsetWidth;
+                if (eventType.startsWith('mouse')) {
+                    R.screenX = evt.screenX;
+                } else {
+                    R.screenX = evt.changedTouches[0].screenX;
+                }
+            });
         });
 
-        resizeHandle.addEventListener('dblclick', (evt) => {
-            evt.preventDefault();
-            evt.stopPropagation();
-
-            parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS;
-        });
+        resizeHandle.addEventListener('dblclick', onDoubleClick);
 
         afterResize(parent);
     }
 
-    window.addEventListener('mousemove', (evt) => {
-        if (evt.button !== 0) return;
+    ['mousemove', 'touchmove'].forEach((eventType) => {
+        window.addEventListener(eventType, (evt) => {
+            if (eventType.startsWith('mouse')) {
+                if (evt.button !== 0) return;
+            } else {
+                if (evt.changedTouches.length !== 1) return;
+            }
 
-        if (R.tracking) {
-            evt.preventDefault();
-            evt.stopPropagation();
+            if (R.tracking) {
+                if (eventType.startsWith('mouse')) {
+                    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);
-        }
+                let delta = 0;
+                if (eventType.startsWith('mouse')) {
+                    delta = R.screenX - evt.screenX;
+                } else {
+                    delta = R.screenX - evt.changedTouches[0].screenX;
+                }
+                const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - R.parent.minRightColWidth - PAD), R.parent.minLeftColWidth);
+                setLeftColGridTemplate(R.parent, leftColWidth);
+            }
+        });
     });
 
-    window.addEventListener('mouseup', (evt) => {
-        if (evt.button !== 0) return;
+    ['mouseup', 'touchend'].forEach((eventType) => {
+        window.addEventListener(eventType, (evt) => {
+            if (eventType.startsWith('mouse')) {
+                if (evt.button !== 0) return;
+            } else {
+                if (evt.changedTouches.length !== 1) return;
+            }
 
-        if (R.tracking) {
-            evt.preventDefault();
-            evt.stopPropagation();
+            if (R.tracking) {
+                evt.preventDefault();
+                evt.stopPropagation();
 
-            R.tracking = false;
+                R.tracking = false;
 
-            document.body.classList.remove('resizing');
-        }
+                document.body.classList.remove('resizing');
+            }
+        });
     });
 
 
@@ -132,10 +191,15 @@
     setupResizeHandle = setup;
 })();
 
-onUiLoaded(function() {
+
+function setupAllResizeHandles() {
     for (var elem of gradioApp().querySelectorAll('.resize-handle-row')) {
-        if (!elem.querySelector('.resize-handle')) {
+        if (!elem.querySelector('.resize-handle') && !elem.children[0].classList.contains("hidden")) {
             setupResizeHandle(elem);
         }
     }
-});
+}
+
+
+onUiLoaded(setupAllResizeHandles);
+

javascript/settings.js

@@ -55,8 +55,8 @@ onOptionsChanged(function() {
     });
 
     opts._categories.forEach(function(x) {
-        var section = x[0];
-        var category = x[1];
+        var section = localization[x[0]] ?? x[0];
+        var category = localization[x[1]] ?? x[1];
 
         var span = document.createElement('SPAN');
         span.textContent = category;

javascript/token-counters.js

@@ -48,11 +48,6 @@ function setupTokenCounting(id, id_counter, id_button) {
     var counter = gradioApp().getElementById(id_counter);
     var textarea = gradioApp().querySelector(`#${id} > label > textarea`);
 
-    if (opts.disable_token_counters) {
-        counter.style.display = "none";
-        return;
-    }
-
     if (counter.parentElement == prompt.parentElement) {
         return;
     }
@@ -61,15 +56,32 @@ function setupTokenCounting(id, id_counter, id_button) {
     prompt.parentElement.style.position = "relative";
 
     var func = onEdit(id, textarea, 800, function() {
-        gradioApp().getElementById(id_button)?.click();
+        if (counter.classList.contains("token-counter-visible")) {
+            gradioApp().getElementById(id_button)?.click();
+        }
     });
     promptTokenCountUpdateFunctions[id] = func;
     promptTokenCountUpdateFunctions[id_button] = func;
 }
 
-function setupTokenCounters() {
-    setupTokenCounting('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button');
-    setupTokenCounting('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button');
-    setupTokenCounting('img2img_prompt', 'img2img_token_counter', 'img2img_token_button');
-    setupTokenCounting('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button');
+function toggleTokenCountingVisibility(id, id_counter, id_button) {
+    var counter = gradioApp().getElementById(id_counter);
+
+    counter.style.display = opts.disable_token_counters ? "none" : "block";
+    counter.classList.toggle("token-counter-visible", !opts.disable_token_counters);
 }
+
+function runCodeForTokenCounters(fun) {
+    fun('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button');
+    fun('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button');
+    fun('img2img_prompt', 'img2img_token_counter', 'img2img_token_button');
+    fun('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button');
+}
+
+onUiLoaded(function() {
+    runCodeForTokenCounters(setupTokenCounting);
+});
+
+onOptionsChanged(function() {
+    runCodeForTokenCounters(toggleTokenCountingVisibility);
+});

javascript/ui.js

@@ -119,16 +119,24 @@ function create_submit_args(args) {
     return res;
 }
 
+function setSubmitButtonsVisibility(tabname, showInterrupt, showSkip, showInterrupting) {
+    gradioApp().getElementById(tabname + '_interrupt').style.display = showInterrupt ? "block" : "none";
+    gradioApp().getElementById(tabname + '_skip').style.display = showSkip ? "block" : "none";
+    gradioApp().getElementById(tabname + '_interrupting').style.display = showInterrupting ? "block" : "none";
+}
+
 function showSubmitButtons(tabname, show) {
-    gradioApp().getElementById(tabname + '_interrupt').style.display = show ? "none" : "block";
-    gradioApp().getElementById(tabname + '_skip').style.display = show ? "none" : "block";
+    setSubmitButtonsVisibility(tabname, !show, !show, false);
+}
+
+function showSubmitInterruptingPlaceholder(tabname) {
+    setSubmitButtonsVisibility(tabname, false, true, true);
 }
 
 function showRestoreProgressButton(tabname, show) {
     var button = gradioApp().getElementById(tabname + "_restore_progress");
     if (!button) return;
-
-    button.style.display = show ? "flex" : "none";
+    button.style.setProperty('display', show ? 'flex' : 'none', 'important');
 }
 
 function submit() {
@@ -200,6 +208,7 @@ function restoreProgressTxt2img() {
     var id = localGet("txt2img_task_id");
 
     if (id) {
+        showSubmitInterruptingPlaceholder('txt2img');
         requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
             showSubmitButtons('txt2img', true);
         }, null, 0);
@@ -214,6 +223,7 @@ function restoreProgressImg2img() {
     var id = localGet("img2img_task_id");
 
     if (id) {
+        showSubmitInterruptingPlaceholder('img2img');
         requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
             showSubmitButtons('img2img', true);
         }, null, 0);
@@ -310,8 +320,6 @@ onAfterUiUpdate(function() {
     });
 
     json_elem.parentElement.style.display = "none";
-
-    setupTokenCounters();
 });
 
 onOptionsChanged(function() {
@@ -404,7 +412,7 @@ function switchWidthHeight(tabname) {
 
 var onEditTimers = {};
 
-// calls func after afterMs milliseconds has passed since the input elem has beed enited by user
+// calls func after afterMs milliseconds has passed since the input elem has been edited by user
 function onEdit(editId, elem, afterMs, func) {
     var edited = function() {
         var existingTimer = onEditTimers[editId];

modules/api/api.py

@@ -17,13 +17,13 @@ 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, shared_items, script_callbacks, infotext_utils, sd_models
+from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items, script_callbacks, infotext_utils, sd_models, sd_schedulers
 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.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
-from PIL import PngImagePlugin, Image
+from PIL import PngImagePlugin
 from modules.sd_models_config import find_checkpoint_config_near_filename
 from modules.realesrgan_model import get_realesrgan_models
 from modules import devices
@@ -85,7 +85,7 @@ def decode_base64_to_image(encoding):
         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))
+            image = images.read(BytesIO(response.content))
             return image
         except Exception as e:
             raise HTTPException(status_code=500, detail="Invalid image url") from e
@@ -93,7 +93,7 @@ def decode_base64_to_image(encoding):
     if encoding.startswith("data:image/"):
         encoding = encoding.split(";")[1].split(",")[1]
     try:
-        image = Image.open(BytesIO(base64.b64decode(encoding)))
+        image = images.read(BytesIO(base64.b64decode(encoding)))
         return image
     except Exception as e:
         raise HTTPException(status_code=500, detail="Invalid encoded image") from e
@@ -221,6 +221,7 @@ class Api:
         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/schedulers", self.get_schedulers, methods=["GET"], response_model=list[models.SchedulerItem])
         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])
@@ -230,6 +231,7 @@ class Api:
         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-embeddings", self.refresh_embeddings, methods=["POST"])
         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)
@@ -359,7 +361,7 @@ class Api:
         return script_args
 
     def apply_infotext(self, request, tabname, *, script_runner=None, mentioned_script_args=None):
-        """Processes `infotext` field from the `request`, and sets other fields of the `request` accoring to what's in infotext.
+        """Processes `infotext` field from the `request`, and sets other fields of the `request` according to what's in infotext.
 
         If request already has a field set, and that field is encountered in infotext too, the value from infotext is ignored.
 
@@ -408,8 +410,8 @@ class Api:
         if request.override_settings is None:
             request.override_settings = {}
 
-        overriden_settings = infotext_utils.get_override_settings(params)
-        for _, setting_name, value in overriden_settings:
+        overridden_settings = infotext_utils.get_override_settings(params)
+        for _, setting_name, value in overridden_settings:
             if setting_name not in request.override_settings:
                 request.override_settings[setting_name] = value
 
@@ -682,6 +684,17 @@ class Api:
     def get_samplers(self):
         return [{"name": sampler[0], "aliases":sampler[2], "options":sampler[3]} for sampler in sd_samplers.all_samplers]
 
+    def get_schedulers(self):
+        return [
+            {
+                "name": scheduler.name,
+                "label": scheduler.label,
+                "aliases": scheduler.aliases,
+                "default_rho": scheduler.default_rho,
+                "need_inner_model": scheduler.need_inner_model,
+            }
+            for scheduler in sd_schedulers.schedulers]
+
     def get_upscalers(self):
         return [
             {
@@ -747,6 +760,10 @@ class Api:
             "skipped": convert_embeddings(db.skipped_embeddings),
         }
 
+    def refresh_embeddings(self):
+        with self.queue_lock:
+            sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
+
     def refresh_checkpoints(self):
         with self.queue_lock:
             shared.refresh_checkpoints()

modules/api/models.py

@@ -147,7 +147,7 @@ class ExtrasBaseRequest(BaseModel):
     gfpgan_visibility: float = Field(default=0, title="GFPGAN Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of GFPGAN, values should be between 0 and 1.")
     codeformer_visibility: float = Field(default=0, title="CodeFormer Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of CodeFormer, values should be between 0 and 1.")
     codeformer_weight: float = Field(default=0, title="CodeFormer Weight", ge=0, le=1, allow_inf_nan=False, description="Sets the weight of CodeFormer, values should be between 0 and 1.")
-    upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=8, description="By how much to upscale the image, only used when resize_mode=0.")
+    upscaling_resize: float = Field(default=2, title="Upscaling Factor", gt=0, description="By how much to upscale the image, only used when resize_mode=0.")
     upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.")
     upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.")
     upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the chosen size?")
@@ -235,6 +235,13 @@ class SamplerItem(BaseModel):
     aliases: list[str] = Field(title="Aliases")
     options: dict[str, str] = Field(title="Options")
 
+class SchedulerItem(BaseModel):
+    name: str = Field(title="Name")
+    label: str = Field(title="Label")
+    aliases: Optional[list[str]] = Field(title="Aliases")
+    default_rho: Optional[float] = Field(title="Default Rho")
+    need_inner_model: Optional[bool] = Field(title="Needs Inner Model")
+
 class UpscalerItem(BaseModel):
     name: str = Field(title="Name")
     model_name: Optional[str] = Field(title="Model Name")

modules/cache.py

@@ -2,48 +2,55 @@ import json
 import os
 import os.path
 import threading
-import time
+
+import diskcache
+import tqdm
 
 from modules.paths import data_path, script_path
 
 cache_filename = os.environ.get('SD_WEBUI_CACHE_FILE', os.path.join(data_path, "cache.json"))
-cache_data = None
+cache_dir = os.environ.get('SD_WEBUI_CACHE_DIR', os.path.join(data_path, "cache"))
+caches = {}
 cache_lock = threading.Lock()
 
-dump_cache_after = None
-dump_cache_thread = None
-
 
 def dump_cache():
-    """
-    Marks cache for writing to disk. 5 seconds after no one else flags the cache for writing, it is written.
-    """
+    """old function for dumping cache to disk; does nothing since diskcache."""
 
-    global dump_cache_after
-    global dump_cache_thread
+    pass
 
-    def thread_func():
-        global dump_cache_after
-        global dump_cache_thread
 
-        while dump_cache_after is not None and time.time() < dump_cache_after:
-            time.sleep(1)
+def make_cache(subsection: str) -> diskcache.Cache:
+    return diskcache.Cache(
+        os.path.join(cache_dir, subsection),
+        size_limit=2**32,  # 4 GB, culling oldest first
+        disk_min_file_size=2**18,  # keep up to 256KB in Sqlite
+    )
 
-        with cache_lock:
-            cache_filename_tmp = cache_filename + "-"
-            with open(cache_filename_tmp, "w", encoding="utf8") as file:
-                json.dump(cache_data, file, indent=4, ensure_ascii=False)
 
-            os.replace(cache_filename_tmp, cache_filename)
+def convert_old_cached_data():
+    try:
+        with open(cache_filename, "r", encoding="utf8") as file:
+            data = json.load(file)
+    except FileNotFoundError:
+        return
+    except Exception:
+        os.replace(cache_filename, os.path.join(script_path, "tmp", "cache.json"))
+        print('[ERROR] issue occurred while trying to read cache.json; old cache has been moved to tmp/cache.json')
+        return
 
-            dump_cache_after = None
-            dump_cache_thread = None
+    total_count = sum(len(keyvalues) for keyvalues in data.values())
 
-    with cache_lock:
-        dump_cache_after = time.time() + 5
-        if dump_cache_thread is None:
-            dump_cache_thread = threading.Thread(name='cache-writer', target=thread_func)
-            dump_cache_thread.start()
+    with tqdm.tqdm(total=total_count, desc="converting cache") as progress:
+        for subsection, keyvalues in data.items():
+            cache_obj = caches.get(subsection)
+            if cache_obj is None:
+                cache_obj = make_cache(subsection)
+                caches[subsection] = cache_obj
+
+            for key, value in keyvalues.items():
+                cache_obj[key] = value
+                progress.update(1)
 
 
 def cache(subsection):
@@ -54,28 +61,21 @@ def cache(subsection):
         subsection (str): The subsection identifier for the cache.
 
     Returns:
-        dict: The cache data for the specified subsection.
+        diskcache.Cache: The cache data for the specified subsection.
     """
 
-    global cache_data
-
-    if cache_data is None:
+    cache_obj = caches.get(subsection)
+    if not cache_obj:
         with cache_lock:
-            if cache_data is None:
-                try:
-                    with open(cache_filename, "r", encoding="utf8") as file:
-                        cache_data = json.load(file)
-                except FileNotFoundError:
-                    cache_data = {}
-                except Exception:
-                    os.replace(cache_filename, os.path.join(script_path, "tmp", "cache.json"))
-                    print('[ERROR] issue occurred while trying to read cache.json, move current cache to tmp/cache.json and create new cache')
-                    cache_data = {}
+            if not os.path.exists(cache_dir) and os.path.isfile(cache_filename):
+                convert_old_cached_data()
 
-    s = cache_data.get(subsection, {})
-    cache_data[subsection] = s
+            cache_obj = caches.get(subsection)
+            if not cache_obj:
+                cache_obj = make_cache(subsection)
+                caches[subsection] = cache_obj
 
-    return s
+    return cache_obj
 
 
 def cached_data_for_file(subsection, title, filename, func):

modules/call_queue.py

@@ -100,8 +100,8 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
             sys_pct = sys_peak/max(sys_total, 1) * 100
 
             toltip_a = "Active: peak amount of video memory used during generation (excluding cached data)"
-            toltip_r = "Reserved: total amout of video memory allocated by the Torch library "
-            toltip_sys = "System: peak amout of video memory allocated by all running programs, out of total capacity"
+            toltip_r = "Reserved: total amount of video memory allocated by the Torch library "
+            toltip_sys = "System: peak amount of video memory allocated by all running programs, out of total capacity"
 
             text_a = f"<abbr title='{toltip_a}'>A</abbr>: <span class='measurement'>{active_peak/1024:.2f} GB</span>"
             text_r = f"<abbr title='{toltip_r}'>R</abbr>: <span class='measurement'>{reserved_peak/1024:.2f} GB</span>"

modules/cmd_args.py

@@ -1,7 +1,7 @@
 import argparse
 import json
 import os
-from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file  # noqa: F401
+from modules.paths_internal import normalized_filepath, models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file  # noqa: F401
 
 parser = argparse.ArgumentParser()
 
@@ -19,21 +19,21 @@ parser.add_argument("--skip-install", action='store_true', help="launch.py argum
 parser.add_argument("--dump-sysinfo", action='store_true', help="launch.py argument: dump limited sysinfo file (without information about extensions, options) to disk and quit")
 parser.add_argument("--loglevel", type=str, help="log level; one of: CRITICAL, ERROR, WARNING, INFO, DEBUG", default=None)
 parser.add_argument("--do-not-download-clip", action='store_true', help="do not download CLIP model even if it's not included in the checkpoint")
-parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
-parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
-parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
-parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
-parser.add_argument("--vae-dir", type=str, default=None, help="Path to directory with VAE files")
-parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
-parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default=None)
+parser.add_argument("--data-dir", type=normalized_filepath, 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=normalized_filepath, default=sd_default_config, help="path to config which constructs model",)
+parser.add_argument("--ckpt", type=normalized_filepath, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
+parser.add_argument("--ckpt-dir", type=normalized_filepath, default=None, help="Path to directory with stable diffusion checkpoints")
+parser.add_argument("--vae-dir", type=normalized_filepath, default=None, help="Path to directory with VAE files")
+parser.add_argument("--gfpgan-dir", type=normalized_filepath, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
+parser.add_argument("--gfpgan-model", type=normalized_filepath, help="GFPGAN model file name", default=None)
 parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")
 parser.add_argument("--no-half-vae", action='store_true', help="do not switch the VAE model to 16-bit floats")
 parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
 parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
-parser.add_argument("--embeddings-dir", type=str, default=os.path.join(data_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
-parser.add_argument("--textual-inversion-templates-dir", type=str, default=os.path.join(script_path, 'textual_inversion_templates'), help="directory with textual inversion templates")
-parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
-parser.add_argument("--localizations-dir", type=str, default=os.path.join(script_path, 'localizations'), help="localizations directory")
+parser.add_argument("--embeddings-dir", type=normalized_filepath, default=os.path.join(data_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
+parser.add_argument("--textual-inversion-templates-dir", type=normalized_filepath, default=os.path.join(script_path, 'textual_inversion_templates'), help="directory with textual inversion templates")
+parser.add_argument("--hypernetwork-dir", type=normalized_filepath, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
+parser.add_argument("--localizations-dir", type=normalized_filepath, 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")
@@ -48,12 +48,13 @@ parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to g
 parser.add_argument("--ngrok-region", type=str, help="does not do anything.", default="")
 parser.add_argument("--ngrok-options", type=json.loads, help='The options to pass to ngrok in JSON format, e.g.: \'{"authtoken_from_env":true, "basic_auth":"user:password", "oauth_provider":"google", "oauth_allow_emails":"user@asdf.com"}\'', default=dict())
 parser.add_argument("--enable-insecure-extension-access", action='store_true', help="enable extensions tab regardless of other options")
-parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
-parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
-parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
-parser.add_argument("--bsrgan-models-path", type=str, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN'))
-parser.add_argument("--realesrgan-models-path", type=str, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN'))
-parser.add_argument("--clip-models-path", type=str, help="Path to directory with CLIP model file(s).", default=None)
+parser.add_argument("--codeformer-models-path", type=normalized_filepath, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
+parser.add_argument("--gfpgan-models-path", type=normalized_filepath, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
+parser.add_argument("--esrgan-models-path", type=normalized_filepath, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
+parser.add_argument("--bsrgan-models-path", type=normalized_filepath, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN'))
+parser.add_argument("--realesrgan-models-path", type=normalized_filepath, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN'))
+parser.add_argument("--dat-models-path", type=normalized_filepath, help="Path to directory with DAT model file(s).", default=os.path.join(models_path, 'DAT'))
+parser.add_argument("--clip-models-path", type=normalized_filepath, help="Path to directory with CLIP model file(s).", default=None)
 parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
 parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
 parser.add_argument("--xformers-flash-attention", action='store_true', help="enable xformers with Flash Attention to improve reproducibility (supported for SD2.x or variant only)")
@@ -83,18 +84,18 @@ parser.add_argument("--freeze-specific-settings", type=str, help='disable editin
 parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default=os.path.join(data_path, 'config.json'))
 parser.add_argument("--gradio-debug",  action='store_true', help="launch gradio with --debug option")
 parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
-parser.add_argument("--gradio-auth-path", type=str, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
+parser.add_argument("--gradio-auth-path", type=normalized_filepath, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
 parser.add_argument("--gradio-img2img-tool", type=str, help='does not do anything')
 parser.add_argument("--gradio-inpaint-tool", type=str, help="does not do anything")
 parser.add_argument("--gradio-allowed-path", action='append', help="add path to gradio's allowed_paths, make it possible to serve files from it", default=[data_path])
 parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
-parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(data_path, 'styles.csv'))
+parser.add_argument("--styles-file", type=str, action='append', help="path or wildcard path of styles files, allow multiple entries.", default=[])
 parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
 parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
 parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
 parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
 parser.add_argument("--enable-console-prompts", action='store_true', help="does not do anything", default=False)  # Legacy compatibility, use as default value shared.opts.enable_console_prompts
-parser.add_argument('--vae-path', type=str, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
+parser.add_argument('--vae-path', type=normalized_filepath, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
 parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
 parser.add_argument("--api", action='store_true', help="use api=True to launch the API together with the webui (use --nowebui instead for only the API)")
 parser.add_argument("--api-auth", type=str, help='Set authentication for API like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
@@ -120,4 +121,7 @@ parser.add_argument('--api-server-stop', action='store_true', help='enable serve
 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", )
+parser.add_argument("--skip-load-model-at-start", action='store_true', help="if load a model at web start, only take effect when --nowebui")
+parser.add_argument("--unix-filenames-sanitization", action='store_true', help="allow any symbols except '/' in filenames. May conflict with your browser and file system")
+parser.add_argument("--filenames-max-length", type=int, default=128, help='maximal length of filenames of saved images. If you override it, it can conflict with your file system')
+parser.add_argument("--no-prompt-history", action='store_true', help="disable read prompt from last generation feature; settings this argument will not create '--data_path/params.txt' file")

modules/codeformer_model.py

@@ -50,7 +50,7 @@ class FaceRestorerCodeFormer(face_restoration_utils.CommonFaceRestoration):
 
         def restore_face(cropped_face_t):
             assert self.net is not None
-            return self.net(cropped_face_t, w=w, adain=True)[0]
+            return self.net(cropped_face_t, weight=w, adain=True)[0]
 
         return self.restore_with_helper(np_image, restore_face)
 

modules/devices.py

@@ -3,8 +3,7 @@ import contextlib
 from functools import lru_cache
 
 import torch
-from modules import errors, shared
-from modules import torch_utils
+from modules import errors, shared, npu_specific
 
 if sys.platform == "darwin":
     from modules import mac_specific
@@ -58,6 +57,9 @@ def get_optimal_device_name():
     if has_xpu():
         return xpu_specific.get_xpu_device_string()
 
+    if npu_specific.has_npu:
+        return npu_specific.get_npu_device_string()
+
     return "cpu"
 
 
@@ -85,6 +87,16 @@ def torch_gc():
     if has_xpu():
         xpu_specific.torch_xpu_gc()
 
+    if npu_specific.has_npu:
+        torch_npu_set_device()
+        npu_specific.torch_npu_gc()
+
+
+def torch_npu_set_device():
+    # Work around due to bug in torch_npu, revert me after fixed, @see https://gitee.com/ascend/pytorch/issues/I8KECW?from=project-issue
+    if npu_specific.has_npu:
+        torch.npu.set_device(0)
+
 
 def enable_tf32():
     if torch.cuda.is_available():
@@ -141,7 +153,12 @@ def manual_cast_forward(target_dtype):
             args = [arg.to(target_dtype) if isinstance(arg, torch.Tensor) else arg for arg in args]
             kwargs = {k: v.to(target_dtype) if isinstance(v, torch.Tensor) else v for k, v in kwargs.items()}
 
-        org_dtype = torch_utils.get_param(self).dtype
+        org_dtype = target_dtype
+        for param in self.parameters():
+            if param.dtype != target_dtype:
+                org_dtype = param.dtype
+                break
+
         if org_dtype != target_dtype:
             self.to(target_dtype)
         result = self.org_forward(*args, **kwargs)
@@ -170,7 +187,7 @@ def manual_cast(target_dtype):
             continue
         applied = True
         org_forward = module_type.forward
-        if module_type == torch.nn.MultiheadAttention and has_xpu():
+        if module_type == torch.nn.MultiheadAttention:
             module_type.forward = manual_cast_forward(torch.float32)
         else:
             module_type.forward = manual_cast_forward(target_dtype)
@@ -242,7 +259,7 @@ def test_for_nans(x, where):
 def first_time_calculation():
     """
     just do any calculation with pytorch layers - the first time this is done it allocaltes about 700MB of memory and
-    spends about 2.7 seconds doing that, at least wih NVidia.
+    spends about 2.7 seconds doing that, at least with NVidia.
     """
 
     x = torch.zeros((1, 1)).to(device, dtype)
@@ -252,4 +269,3 @@ 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/extensions.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import configparser
+import dataclasses
 import os
 import threading
 import re
@@ -9,6 +10,10 @@ 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: list[Extension] = []
+extension_paths: dict[str, Extension] = {}
+loaded_extensions: dict[str, Exception] = {}
+
 
 os.makedirs(extensions_dir, exist_ok=True)
 
@@ -22,6 +27,13 @@ def active():
         return [x for x in extensions if x.enabled]
 
 
+@dataclasses.dataclass
+class CallbackOrderInfo:
+    name: str
+    before: list
+    after: list
+
+
 class ExtensionMetadata:
     filename = "metadata.ini"
     config: configparser.ConfigParser
@@ -42,7 +54,7 @@ class ExtensionMetadata:
         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")
+        self.requires = None
 
     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,
@@ -54,7 +66,15 @@ class ExtensionMetadata:
         if extra_section:
             x = x + ', ' + self.config.get(extra_section, field, fallback='')
 
-        return self.parse_list(x.lower())
+        listed_requirements = self.parse_list(x.lower())
+        res = []
+
+        for requirement in listed_requirements:
+            loaded_requirements = (x for x in requirement.split("|") if x in loaded_extensions)
+            relevant_requirement = next(loaded_requirements, requirement)
+            res.append(relevant_requirement)
+
+        return res
 
     def parse_list(self, text):
         """converts a line from config ("ext1 ext2, ext3  ") into a python list (["ext1", "ext2", "ext3"])"""
@@ -65,6 +85,22 @@ class ExtensionMetadata:
         # both "," and " " are accepted as separator
         return [x for x in re.split(r"[,\s]+", text.strip()) if x]
 
+    def list_callback_order_instructions(self):
+        for section in self.config.sections():
+            if not section.startswith("callbacks/"):
+                continue
+
+            callback_name = section[10:]
+
+            if not callback_name.startswith(self.canonical_name):
+                errors.report(f"Callback order section for extension {self.canonical_name} is referencing the wrong extension: {section}")
+                continue
+
+            before = self.parse_list(self.config.get(section, 'Before', fallback=''))
+            after = self.parse_list(self.config.get(section, 'After', fallback=''))
+
+            yield CallbackOrderInfo(callback_name, before, after)
+
 
 class Extension:
     lock = threading.Lock()
@@ -156,6 +192,8 @@ class Extension:
     def check_updates(self):
         repo = Repo(self.path)
         for fetch in repo.remote().fetch(dry_run=True):
+            if self.branch and fetch.name != f'{repo.remote().name}/{self.branch}':
+                continue
             if fetch.flags != fetch.HEAD_UPTODATE:
                 self.can_update = True
                 self.status = "new commits"
@@ -186,6 +224,8 @@ class Extension:
 
 def list_extensions():
     extensions.clear()
+    extension_paths.clear()
+    loaded_extensions.clear()
 
     if shared.cmd_opts.disable_all_extensions:
         print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
@@ -196,7 +236,6 @@ def list_extensions():
     elif shared.opts.disable_all_extensions == "extra":
         print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
 
-    loaded_extensions = {}
 
     # scan through extensions directory and load metadata
     for dirname in [extensions_builtin_dir, extensions_dir]:
@@ -220,8 +259,12 @@ def list_extensions():
             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)
+            extension_paths[extension.path] = extension
             loaded_extensions[canonical_name] = extension
 
+    for extension in extensions:
+        extension.metadata.requires = extension.metadata.get_script_requirements("Requires", "Extension")
+
     # check for requirements
     for extension in extensions:
         if not extension.enabled:
@@ -238,4 +281,16 @@ def list_extensions():
                 continue
 
 
-extensions: list[Extension] = []
+def find_extension(filename):
+    parentdir = os.path.dirname(os.path.realpath(filename))
+
+    while parentdir != filename:
+        extension = extension_paths.get(parentdir)
+        if extension is not None:
+            return extension
+
+        filename = parentdir
+        parentdir = os.path.dirname(filename)
+
+    return None
+

modules/extra_networks.py

@@ -60,7 +60,7 @@ class ExtraNetwork:
         Where name matches the name of this ExtraNetwork object, and arg1:arg2:arg3 are any natural number of text arguments
         separated by colon.
 
-        Even if the user does not mention this ExtraNetwork in his prompt, the call will stil be made, with empty params_list -
+        Even if the user does not mention this ExtraNetwork in his prompt, the call will still be made, with empty params_list -
         in this case, all effects of this extra networks should be disabled.
 
         Can be called multiple times before deactivate() - each new call should override the previous call completely.

modules/hashes.py

@@ -21,7 +21,10 @@ def calculate_sha256(filename):
 
 def sha256_from_cache(filename, title, use_addnet_hash=False):
     hashes = cache("hashes-addnet") if use_addnet_hash else cache("hashes")
-    ondisk_mtime = os.path.getmtime(filename)
+    try:
+        ondisk_mtime = os.path.getmtime(filename)
+    except FileNotFoundError:
+        return None
 
     if title not in hashes:
         return None

modules/hypernetworks/hypernetwork.py

@@ -11,7 +11,7 @@ import tqdm
 from einops import rearrange, repeat
 from ldm.util import default
 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 import textual_inversion, saving_settings
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 from torch import einsum
 from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_
@@ -95,6 +95,7 @@ class HypernetworkModule(torch.nn.Module):
                         zeros_(b)
                     else:
                         raise KeyError(f"Key {weight_init} is not defined as initialization!")
+        devices.torch_npu_set_device()
         self.to(devices.device)
 
     def fix_old_state_dict(self, state_dict):
@@ -532,7 +533,7 @@ def train_hypernetwork(id_task, hypernetwork_name: str, learn_rate: float, batch
             model_name=checkpoint.model_name, model_hash=checkpoint.shorthash, num_of_dataset_images=len(ds),
             **{field: getattr(hypernetwork, field) for field in ['layer_structure', 'activation_func', 'weight_init', 'add_layer_norm', 'use_dropout', ]}
         )
-        logging.save_settings_to_file(log_directory, {**saved_params, **locals()})
+        saving_settings.save_settings_to_file(log_directory, {**saved_params, **locals()})
 
     latent_sampling_method = ds.latent_sampling_method
 

modules/images.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import datetime
-
+import functools
 import pytz
 import io
 import math
@@ -12,7 +12,9 @@ import re
 import numpy as np
 import piexif
 import piexif.helper
-from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin
+from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin, ImageOps
+# pillow_avif needs to be imported somewhere in code for it to work
+import pillow_avif # noqa: F401
 import string
 import json
 import hashlib
@@ -321,13 +323,16 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
     return res
 
 
-invalid_filename_chars = '#<>:"/\\|?*\n\r\t'
+if not shared.cmd_opts.unix_filenames_sanitization:
+    invalid_filename_chars = '#<>:"/\\|?*\n\r\t'
+else:
+    invalid_filename_chars = '/'
 invalid_filename_prefix = ' '
 invalid_filename_postfix = ' .'
 re_nonletters = re.compile(r'[\s' + string.punctuation + ']+')
 re_pattern = re.compile(r"(.*?)(?:\[([^\[\]]+)\]|$)")
 re_pattern_arg = re.compile(r"(.*)<([^>]*)>$")
-max_filename_part_length = 128
+max_filename_part_length = shared.cmd_opts.filenames_max_length
 NOTHING_AND_SKIP_PREVIOUS_TEXT = object()
 
 
@@ -344,6 +349,32 @@ def sanitize_filename_part(text, replace_spaces=True):
     return text
 
 
+@functools.cache
+def get_scheduler_str(sampler_name, scheduler_name):
+    """Returns {Scheduler} if the scheduler is applicable to the sampler"""
+    if scheduler_name == 'Automatic':
+        config = sd_samplers.find_sampler_config(sampler_name)
+        scheduler_name = config.options.get('scheduler', 'Automatic')
+    return scheduler_name.capitalize()
+
+
+@functools.cache
+def get_sampler_scheduler_str(sampler_name, scheduler_name):
+    """Returns the '{Sampler} {Scheduler}' if the scheduler is applicable to the sampler"""
+    return f'{sampler_name} {get_scheduler_str(sampler_name, scheduler_name)}'
+
+
+def get_sampler_scheduler(p, sampler):
+    """Returns '{Sampler} {Scheduler}' / '{Scheduler}' / 'NOTHING_AND_SKIP_PREVIOUS_TEXT'"""
+    if hasattr(p, 'scheduler') and hasattr(p, 'sampler_name'):
+        if sampler:
+            sampler_scheduler = get_sampler_scheduler_str(p.sampler_name, p.scheduler)
+        else:
+            sampler_scheduler = get_scheduler_str(p.sampler_name, p.scheduler)
+        return sanitize_filename_part(sampler_scheduler, replace_spaces=False)
+    return NOTHING_AND_SKIP_PREVIOUS_TEXT
+
+
 class FilenameGenerator:
     replacements = {
         'seed': lambda self: self.seed if self.seed is not None else '',
@@ -355,6 +386,8 @@ class FilenameGenerator:
         'height': lambda self: self.image.height,
         'styles': lambda self: self.p and sanitize_filename_part(", ".join([style for style in self.p.styles if not style == "None"]) or "None", replace_spaces=False),
         'sampler': lambda self: self.p and sanitize_filename_part(self.p.sampler_name, replace_spaces=False),
+        'sampler_scheduler': lambda self: self.p and get_sampler_scheduler(self.p, True),
+        'scheduler': lambda self: self.p and get_sampler_scheduler(self.p, False),
         'model_hash': lambda self: getattr(self.p, "sd_model_hash", shared.sd_model.sd_model_hash),
         'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.name_for_extra, replace_spaces=False),
         'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
@@ -566,6 +599,16 @@ def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_p
             })
 
             piexif.insert(exif_bytes, filename)
+    elif extension.lower() == '.avif':
+        if opts.enable_pnginfo and geninfo is not None:
+            exif_bytes = piexif.dump({
+                "Exif": {
+                    piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(geninfo or "", encoding="unicode")
+                },
+            })
+
+
+        image.save(filename,format=image_format, exif=exif_bytes)
     elif extension.lower() == ".gif":
         image.save(filename, format=image_format, comment=geninfo)
     else:
@@ -744,7 +787,6 @@ def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
             exif_comment = exif_comment.decode('utf8', errors="ignore")
 
         if exif_comment:
-            items['exif comment'] = exif_comment
             geninfo = exif_comment
     elif "comment" in items: # for gif
         geninfo = items["comment"].decode('utf8', errors="ignore")
@@ -770,7 +812,7 @@ def image_data(data):
     import gradio as gr
 
     try:
-        image = Image.open(io.BytesIO(data))
+        image = read(io.BytesIO(data))
         textinfo, _ = read_info_from_image(image)
         return textinfo, None
     except Exception:
@@ -797,3 +839,30 @@ def flatten(img, bgcolor):
 
     return img.convert('RGB')
 
+
+def read(fp, **kwargs):
+    image = Image.open(fp, **kwargs)
+    image = fix_image(image)
+
+    return image
+
+
+def fix_image(image: Image.Image):
+    if image is None:
+        return None
+
+    try:
+        image = ImageOps.exif_transpose(image)
+        image = fix_png_transparency(image)
+    except Exception:
+        pass
+
+    return image
+
+
+def fix_png_transparency(image: Image.Image):
+    if image.mode not in ("RGB", "P") or not isinstance(image.info.get("transparency"), bytes):
+        return image
+
+    image = image.convert("RGBA")
+    return image

modules/img2img.py

@@ -6,7 +6,7 @@ import numpy as np
 from PIL import Image, ImageOps, ImageFilter, ImageEnhance, UnidentifiedImageError
 import gradio as gr
 
-from modules import images as imgutil
+from modules import images
 from modules.infotext_utils import create_override_settings_dict, parse_generation_parameters
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
@@ -21,7 +21,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     output_dir = output_dir.strip()
     processing.fix_seed(p)
 
-    images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
+    batch_images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
 
     is_inpaint_batch = False
     if inpaint_mask_dir:
@@ -31,9 +31,9 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
         if is_inpaint_batch:
             print(f"\nInpaint batch is enabled. {len(inpaint_masks)} masks found.")
 
-    print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")
+    print(f"Will process {len(batch_images)} images, creating {p.n_iter * p.batch_size} new images for each.")
 
-    state.job_count = len(images) * p.n_iter
+    state.job_count = len(batch_images) * p.n_iter
 
     # extract "default" params to use in case getting png info fails
     prompt = p.prompt
@@ -46,8 +46,8 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     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)}"
+    for i, image in enumerate(batch_images):
+        state.job = f"{i+1} out of {len(batch_images)}"
         if state.skipped:
             state.skipped = False
 
@@ -55,7 +55,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
             break
 
         try:
-            img = Image.open(image)
+            img = images.read(image)
         except UnidentifiedImageError as e:
             print(e)
             continue
@@ -86,7 +86,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
                 # otherwise user has many masks with the same name but different extensions
                 mask_image_path = masks_found[0]
 
-            mask_image = Image.open(mask_image_path)
+            mask_image = images.read(mask_image_path)
             p.image_mask = mask_image
 
         if use_png_info:
@@ -94,8 +94,8 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
                 info_img = img
                 if png_info_dir:
                     info_img_path = os.path.join(png_info_dir, os.path.basename(image))
-                    info_img = Image.open(info_img_path)
-                geninfo, _ = imgutil.read_info_from_image(info_img)
+                    info_img = images.read(info_img_path)
+                geninfo, _ = images.read_info_from_image(info_img)
                 parsed_parameters = parse_generation_parameters(geninfo)
                 parsed_parameters = {k: v for k, v in parsed_parameters.items() if k in (png_info_props or {})}
             except Exception:
@@ -146,7 +146,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     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_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):
+def img2img(id_task: str, request: gr.Request, 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, 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, *args):
     override_settings = create_override_settings_dict(override_settings_texts)
 
     is_batch = mode == 5
@@ -175,9 +175,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         image = None
         mask = None
 
-    # Use the EXIF orientation of photos taken by smartphones.
-    if image is not None:
-        image = ImageOps.exif_transpose(image)
+    image = images.fix_image(image)
+    mask = images.fix_image(mask)
 
     if selected_scale_tab == 1 and not is_batch:
         assert image, "Can't scale by because no image is selected"
@@ -194,10 +193,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         prompt=prompt,
         negative_prompt=negative_prompt,
         styles=prompt_styles,
-        sampler_name=sampler_name,
         batch_size=batch_size,
         n_iter=n_iter,
-        steps=steps,
         cfg_scale=cfg_scale,
         width=width,
         height=height,

modules/infotext_utils.py

@@ -8,7 +8,7 @@ import sys
 
 import gradio as gr
 from modules.paths import data_path
-from modules import shared, ui_tempdir, script_callbacks, processing, infotext_versions
+from modules import shared, ui_tempdir, script_callbacks, processing, infotext_versions, images, prompt_parser, errors
 from PIL import Image
 
 sys.modules['modules.generation_parameters_copypaste'] = sys.modules[__name__]  # alias for old name
@@ -83,7 +83,7 @@ def image_from_url_text(filedata):
         assert is_in_right_dir, 'trying to open image file outside of allowed directories'
 
         filename = filename.rsplit('?', 1)[0]
-        return Image.open(filename)
+        return images.read(filename)
 
     if type(filedata) == list:
         if len(filedata) == 0:
@@ -95,7 +95,7 @@ def image_from_url_text(filedata):
         filedata = filedata[len("data:image/png;base64,"):]
 
     filedata = base64.decodebytes(filedata.encode('utf-8'))
-    image = Image.open(io.BytesIO(filedata))
+    image = images.read(io.BytesIO(filedata))
     return image
 
 
@@ -265,17 +265,6 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         else:
             prompt += ("" if prompt == "" else "\n") + line
 
-    if shared.opts.infotext_styles != "Ignore":
-        found_styles, prompt, negative_prompt = shared.prompt_styles.extract_styles_from_prompt(prompt, negative_prompt)
-
-        if shared.opts.infotext_styles == "Apply":
-            res["Styles array"] = found_styles
-        elif shared.opts.infotext_styles == "Apply if any" and found_styles:
-            res["Styles array"] = found_styles
-
-    res["Prompt"] = prompt
-    res["Negative prompt"] = negative_prompt
-
     for k, v in re_param.findall(lastline):
         try:
             if v[0] == '"' and v[-1] == '"':
@@ -290,6 +279,26 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         except Exception:
             print(f"Error parsing \"{k}: {v}\"")
 
+    # Extract styles from prompt
+    if shared.opts.infotext_styles != "Ignore":
+        found_styles, prompt_no_styles, negative_prompt_no_styles = shared.prompt_styles.extract_styles_from_prompt(prompt, negative_prompt)
+
+        same_hr_styles = True
+        if ("Hires prompt" in res or "Hires negative prompt" in res) and (infotext_ver > infotext_versions.v180_hr_styles if (infotext_ver := infotext_versions.parse_version(res.get("Version"))) else True):
+            hr_prompt, hr_negative_prompt = res.get("Hires prompt", prompt), res.get("Hires negative prompt", negative_prompt)
+            hr_found_styles, hr_prompt_no_styles, hr_negative_prompt_no_styles = shared.prompt_styles.extract_styles_from_prompt(hr_prompt, hr_negative_prompt)
+            if same_hr_styles := found_styles == hr_found_styles:
+                res["Hires prompt"] = '' if hr_prompt_no_styles == prompt_no_styles else hr_prompt_no_styles
+                res['Hires negative prompt'] = '' if hr_negative_prompt_no_styles == negative_prompt_no_styles else hr_negative_prompt_no_styles
+
+        if same_hr_styles:
+            prompt, negative_prompt = prompt_no_styles, negative_prompt_no_styles
+            if (shared.opts.infotext_styles == "Apply if any" and found_styles) or shared.opts.infotext_styles == "Apply":
+                res['Styles array'] = found_styles
+
+    res["Prompt"] = prompt
+    res["Negative prompt"] = negative_prompt
+
     # Missing CLIP skip means it was set to 1 (the default)
     if "Clip skip" not in res:
         res["Clip skip"] = "1"
@@ -305,6 +314,9 @@ 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 schedule type" not in res:
+        res["Hires schedule type"] = "Use same scheduler"
+
     if "Hires checkpoint" not in res:
         res["Hires checkpoint"] = "Use same checkpoint"
 
@@ -356,6 +368,15 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "Cache FP16 weight for LoRA" not in res and res["FP8 weight"] != "Disable":
         res["Cache FP16 weight for LoRA"] = False
 
+    prompt_attention = prompt_parser.parse_prompt_attention(prompt)
+    prompt_attention += prompt_parser.parse_prompt_attention(negative_prompt)
+    prompt_uses_emphasis = len(prompt_attention) != len([p for p in prompt_attention if p[1] == 1.0 or p[0] == 'BREAK'])
+    if "Emphasis" not in res and prompt_uses_emphasis:
+        res["Emphasis"] = "Original"
+
+    if "Refiner switch by sampling steps" not in res:
+        res["Refiner switch by sampling steps"] = False
+
     infotext_versions.backcompat(res)
 
     for key in skip_fields:
@@ -453,7 +474,7 @@ def get_override_settings(params, *, skip_fields=None):
 
 def connect_paste(button, paste_fields, input_comp, override_settings_component, tabname):
     def paste_func(prompt):
-        if not prompt and not shared.cmd_opts.hide_ui_dir_config:
+        if not prompt and not shared.cmd_opts.hide_ui_dir_config and not shared.cmd_opts.no_prompt_history:
             filename = os.path.join(data_path, "params.txt")
             try:
                 with open(filename, "r", encoding="utf8") as file:
@@ -467,7 +488,11 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
 
         for output, key in paste_fields:
             if callable(key):
-                v = key(params)
+                try:
+                    v = key(params)
+                except Exception:
+                    errors.report(f"Error executing {key}", exc_info=True)
+                    v = None
             else:
                 v = params.get(key, None)
 

modules/infotext_versions.py

@@ -5,6 +5,8 @@ import re
 
 v160 = version.parse("1.6.0")
 v170_tsnr = version.parse("v1.7.0-225")
+v180 = version.parse("1.8.0")
+v180_hr_styles = version.parse("1.8.0-139")
 
 
 def parse_version(text):
@@ -31,9 +33,14 @@ def backcompat(d):
     if ver is None:
         return
 
-    if ver < v160:
+    if ver < v160 and '[' in d.get('Prompt', ''):
         d["Old prompt editing timelines"] = True
 
+    if ver < v160 and d.get('Sampler', '') in ('DDIM', 'PLMS'):
+        d["Pad conds v0"] = True
+
     if ver < v170_tsnr:
         d["Downcast alphas_cumprod"] = True
 
+    if ver < v180 and d.get('Refiner'):
+        d["Refiner switch by sampling steps"] = True

modules/initialize.py

@@ -51,6 +51,7 @@ def check_versions():
 def initialize():
     from modules import initialize_util
     initialize_util.fix_torch_version()
+    initialize_util.fix_pytorch_lightning()
     initialize_util.fix_asyncio_event_loop_policy()
     initialize_util.validate_tls_options()
     initialize_util.configure_sigint_handler()
@@ -109,7 +110,7 @@ def initialize_rest(*, reload_script_modules=False):
     with startup_timer.subcategory("load scripts"):
         scripts.load_scripts()
 
-    if reload_script_modules:
+    if reload_script_modules and shared.opts.enable_reloading_ui_scripts:
         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")
@@ -139,16 +140,17 @@ def initialize_rest(*, reload_script_modules=False):
         """
         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
+        its optimization may be None because the list of optimizers has not been filled
         by that time, so we apply optimization again.
         """
+        from modules import devices
+        devices.torch_npu_set_device()
 
         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()

modules/initialize_util.py

@@ -24,6 +24,13 @@ def fix_torch_version():
         torch.__long_version__ = torch.__version__
         torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0)
 
+def fix_pytorch_lightning():
+    # Checks if pytorch_lightning.utilities.distributed already exists in the sys.modules cache
+    if 'pytorch_lightning.utilities.distributed' not in sys.modules:
+        import pytorch_lightning
+        # Lets the user know that the library was not found and then will set it to pytorch_lightning.utilities.rank_zero
+        print("Pytorch_lightning.distributed not found, attempting pytorch_lightning.rank_zero")
+        sys.modules["pytorch_lightning.utilities.distributed"] = pytorch_lightning.utilities.rank_zero
 
 def fix_asyncio_event_loop_policy():
     """

modules/interrogate.py

@@ -17,7 +17,7 @@ clip_model_name = 'ViT-L/14'
 
 Category = namedtuple("Category", ["name", "topn", "items"])
 
-re_topn = re.compile(r"\.top(\d+)\.")
+re_topn = re.compile(r"\.top(\d+)$")
 
 def category_types():
     return [f.stem for f in Path(shared.interrogator.content_dir).glob('*.txt')]

modules/launch_utils.py

@@ -55,7 +55,7 @@ and delete current Python and "venv" folder in WebUI's directory.
 
 You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
 
-{"Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases" if is_windows else ""}
+{"Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre" if is_windows else ""}
 
 Use --skip-python-version-check to suppress this warning.
 """)
@@ -188,7 +188,7 @@ def git_clone(url, dir, name, commithash=None):
         return
 
     try:
-        run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
+        run(f'"{git}" clone --config core.filemode=false "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
     except RuntimeError:
         shutil.rmtree(dir, ignore_errors=True)
         raise
@@ -251,7 +251,6 @@ def list_extensions(settings_file):
     except Exception:
         errors.report(f'\nCould not load settings\nThe config file "{settings_file}" is likely corrupted\nIt has been moved to the "tmp/config.json"\nReverting config to default\n\n''', exc_info=True)
         os.replace(settings_file, os.path.join(script_path, "tmp", "config.json"))
-        settings = {}
 
     disabled_extensions = set(settings.get('disabled_extensions', []))
     disable_all_extensions = settings.get('disable_all_extensions', 'none')
@@ -339,6 +338,7 @@ def prepare_environment():
             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")
+    requirements_file_for_npu = os.environ.get('REQS_FILE_FOR_NPU', "requirements_npu.txt")
 
     xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.23.post1')
     clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip")
@@ -422,6 +422,13 @@ def prepare_environment():
         run_pip(f"install -r \"{requirements_file}\"", "requirements")
         startup_timer.record("install requirements")
 
+    if not os.path.isfile(requirements_file_for_npu):
+        requirements_file_for_npu = os.path.join(script_path, requirements_file_for_npu)
+
+    if "torch_npu" in torch_command and not requirements_met(requirements_file_for_npu):
+        run_pip(f"install -r \"{requirements_file_for_npu}\"", "requirements_for_npu")
+        startup_timer.record("install requirements_for_npu")
+
     if not args.skip_install:
         run_extensions_installers(settings_file=args.ui_settings_file)
 

modules/mac_specific.py

@@ -12,7 +12,7 @@ log = logging.getLogger(__name__)
 
 # before torch version 1.13, has_mps is only available in nightly pytorch and macOS 12.3+,
 # use check `getattr` and try it for compatibility.
-# in torch version 1.13, backends.mps.is_available() and backends.mps.is_built() are introduced in to check mps availabilty,
+# in torch version 1.13, backends.mps.is_available() and backends.mps.is_built() are introduced in to check mps availability,
 # since torch 2.0.1+ nightly build, getattr(torch, 'has_mps', False) was deprecated, see https://github.com/pytorch/pytorch/pull/103279
 def check_for_mps() -> bool:
     if version.parse(torch.__version__) <= version.parse("2.0.1"):

modules/masking.py

@@ -1,17 +1,39 @@
 from PIL import Image, ImageFilter, ImageOps
 
 
-def get_crop_region(mask, pad=0):
-    """finds a rectangular region that contains all masked ares in an image. Returns (x1, y1, x2, y2) coordinates of the rectangle.
-    For example, if a user has painted the top-right part of a 512x512 image, the result may be (256, 0, 512, 256)"""
-    mask_img = mask if isinstance(mask, Image.Image) else Image.fromarray(mask)
-    box = mask_img.getbbox()
-    if box:
+def get_crop_region_v2(mask, pad=0):
+    """
+    Finds a rectangular region that contains all masked ares in a mask.
+    Returns None if mask is completely black mask (all 0)
+
+    Parameters:
+    mask: PIL.Image.Image L mode or numpy 1d array
+    pad: int number of pixels that the region will be extended on all sides
+    Returns: (x1, y1, x2, y2) | None
+
+    Introduced post 1.9.0
+    """
+    mask = mask if isinstance(mask, Image.Image) else Image.fromarray(mask)
+    if box := mask.getbbox():
         x1, y1, x2, y2 = box
-    else:  # when no box is found
-        x1, y1 = mask_img.size
-        x2 = y2 = 0
-    return max(x1 - pad, 0), max(y1 - pad, 0), min(x2 + pad, mask_img.size[0]), min(y2 + pad, mask_img.size[1])
+        return (max(x1 - pad, 0), max(y1 - pad, 0), min(x2 + pad, mask.size[0]), min(y2 + pad, mask.size[1])) if pad else box
+
+
+def get_crop_region(mask, pad=0):
+    """
+    Same function as get_crop_region_v2 but handles completely black mask (all 0) differently
+    when mask all black still return coordinates but the coordinates may be invalid ie x2>x1 or y2>y1
+    Notes: it is possible for the coordinates to be "valid" again if pad size is sufficiently large
+    (mask_size.x-pad, mask_size.y-pad, pad, pad)
+
+    Extension developer should use get_crop_region_v2 instead unless for compatibility considerations.
+    """
+    mask = mask if isinstance(mask, Image.Image) else Image.fromarray(mask)
+    if box := get_crop_region_v2(mask, pad):
+        return box
+    x1, y1 = mask.size
+    x2 = y2 = 0
+    return max(x1 - pad, 0), max(y1 - pad, 0), min(x2 + pad, mask.size[0]), min(y2 + pad, mask.size[1])
 
 
 def expand_crop_region(crop_region, processing_width, processing_height, image_width, image_height):

modules/modelloader.py

@@ -110,7 +110,7 @@ def load_upscalers():
             except Exception:
                 pass
 
-    datas = []
+    data = []
     commandline_options = vars(shared.cmd_opts)
 
     # some of upscaler classes will not go away after reloading their modules, and we'll end
@@ -129,10 +129,10 @@ def load_upscalers():
         scaler = cls(commandline_model_path)
         scaler.user_path = commandline_model_path
         scaler.model_download_path = commandline_model_path or scaler.model_path
-        datas += scaler.scalers
+        data += scaler.scalers
 
     shared.sd_upscalers = sorted(
-        datas,
+        data,
         # Special case for UpscalerNone keeps it at the beginning of the list.
         key=lambda x: x.name.lower() if not isinstance(x.scaler, (UpscalerNone, UpscalerLanczos, UpscalerNearest)) else ""
     )

modules/models/diffusion/ddpm_edit.py

@@ -341,7 +341,7 @@ class DDPM(pl.LightningModule):
         elif self.parameterization == "x0":
             target = x_start
         else:
-            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+            raise NotImplementedError(f"Parameterization {self.parameterization} not yet supported")
 
         loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
 
@@ -901,7 +901,7 @@ class LatentDiffusion(DDPM):
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
-            # hybrid case, cond is exptected to be a dict
+            # hybrid case, cond is expected to be a dict
             pass
         else:
             if not isinstance(cond, list):
@@ -937,7 +937,7 @@ class LatentDiffusion(DDPM):
                 cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
 
             elif self.cond_stage_key == 'coordinates_bbox':
-                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+                assert 'original_image_size' in self.split_input_params, 'BoundingBoxRescaling is missing original_image_size'
 
                 # assuming padding of unfold is always 0 and its dilation is always 1
                 n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
@@ -947,7 +947,7 @@ class LatentDiffusion(DDPM):
                 num_downs = self.first_stage_model.encoder.num_resolutions - 1
                 rescale_latent = 2 ** (num_downs)
 
-                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # get top left positions of patches as conforming for the bbbox tokenizer, therefore we
                 # need to rescale the tl patch coordinates to be in between (0,1)
                 tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
                                          rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)

modules/npu_specific.py

@@ -0,0 +1,31 @@
+import importlib
+import torch
+
+from modules import shared
+
+
+def check_for_npu():
+    if importlib.util.find_spec("torch_npu") is None:
+        return False
+    import torch_npu
+
+    try:
+        # Will raise a RuntimeError if no NPU is found
+        _ = torch_npu.npu.device_count()
+        return torch.npu.is_available()
+    except RuntimeError:
+        return False
+
+
+def get_npu_device_string():
+    if shared.cmd_opts.device_id is not None:
+        return f"npu:{shared.cmd_opts.device_id}"
+    return "npu:0"
+
+
+def torch_npu_gc():
+    with torch.npu.device(get_npu_device_string()):
+        torch.npu.empty_cache()
+
+
+has_npu = check_for_npu()

modules/options.py

@@ -198,6 +198,8 @@ class Options:
         try:
             with open(filename, "r", encoding="utf8") as file:
                 self.data = json.load(file)
+        except FileNotFoundError:
+            self.data = {}
         except Exception:
             errors.report(f'\nCould not load settings\nThe config file "{filename}" is likely corrupted\nIt has been moved to the "tmp/config.json"\nReverting config to default\n\n''', exc_info=True)
             os.replace(filename, os.path.join(script_path, "tmp", "config.json"))
@@ -238,6 +240,9 @@ class Options:
 
         item_categories = {}
         for item in self.data_labels.values():
+            if item.section[0] is None:
+                continue
+
             category = categories.mapping.get(item.category_id)
             category = "Uncategorized" if category is None else category.label
             if category not in item_categories:

modules/paths_internal.py

@@ -4,6 +4,10 @@ import argparse
 import os
 import sys
 import shlex
+from pathlib import Path
+
+
+normalized_filepath = lambda filepath: str(Path(filepath).absolute())
 
 commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
 sys.argv += shlex.split(commandline_args)
@@ -28,6 +32,6 @@ models_path = os.path.join(data_path, "models")
 extensions_dir = os.path.join(data_path, "extensions")
 extensions_builtin_dir = os.path.join(script_path, "extensions-builtin")
 config_states_dir = os.path.join(script_path, "config_states")
-default_output_dir = os.path.join(data_path, "output")
+default_output_dir = os.path.join(data_path, "outputs")
 
 roboto_ttf_file = os.path.join(modules_path, 'Roboto-Regular.ttf')

modules/postprocessing.py

@@ -2,7 +2,7 @@ import os
 
 from PIL import Image
 
-from modules import shared, images, devices, scripts, scripts_postprocessing, ui_common, infotext_utils
+from modules import shared, images, devices, scripts, scripts_postprocessing, ui_common, infotext_utils, util
 from modules.shared import opts
 
 
@@ -17,10 +17,10 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
         if extras_mode == 1:
             for img in image_folder:
                 if isinstance(img, Image.Image):
-                    image = img
+                    image = images.fix_image(img)
                     fn = ''
                 else:
-                    image = Image.open(os.path.abspath(img.name))
+                    image = images.read(os.path.abspath(img.name))
                     fn = os.path.splitext(img.orig_name)[0]
                 yield image, fn
         elif extras_mode == 2:
@@ -31,6 +31,8 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
             for filename in image_list:
                 yield filename, filename
         else:
+            if isinstance(image, str):
+                image = util.decode_base64_to_image(image)
             assert image, 'image not selected'
             yield image, None
 
@@ -56,17 +58,19 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
 
         if isinstance(image_placeholder, str):
             try:
-                image_data = Image.open(image_placeholder)
+                image_data = images.read(image_placeholder)
             except Exception:
                 continue
         else:
             image_data = image_placeholder
 
+        image_data = image_data if image_data.mode in ("RGBA", "RGB") else image_data.convert("RGB")
+
         parameters, existing_pnginfo = images.read_info_from_image(image_data)
         if parameters:
             existing_pnginfo["parameters"] = parameters
 
-        initial_pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB"))
+        initial_pp = scripts_postprocessing.PostprocessedImage(image_data)
 
         scripts.scripts_postproc.run(initial_pp, args)
 
@@ -122,8 +126,6 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
             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), ''
@@ -133,13 +135,15 @@ def run_postprocessing_webui(id_task, *args, **kwargs):
     return run_postprocessing(*args, **kwargs)
 
 
-def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True):
+def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True, max_side_length: int = 0):
     """old handler for API"""
 
     args = scripts.scripts_postproc.create_args_for_run({
         "Upscale": {
+            "upscale_enabled": True,
             "upscale_mode": resize_mode,
             "upscale_by": upscaling_resize,
+            "max_side_length": max_side_length,
             "upscale_to_width": upscaling_resize_w,
             "upscale_to_height": upscaling_resize_h,
             "upscale_crop": upscaling_crop,

modules/processing.py

@@ -74,16 +74,18 @@ def uncrop(image, dest_size, paste_loc):
 
 def apply_overlay(image, paste_loc, overlay):
     if overlay is None:
-        return image
+        return image, image.copy()
 
     if paste_loc is not None:
         image = uncrop(image, (overlay.width, overlay.height), paste_loc)
 
+    original_denoised_image = image.copy()
+
     image = image.convert('RGBA')
     image.alpha_composite(overlay)
     image = image.convert('RGB')
 
-    return image
+    return image, original_denoised_image
 
 def create_binary_mask(image, round=True):
     if image.mode == 'RGBA' and image.getextrema()[-1] != (255, 255):
@@ -150,6 +152,7 @@ class StableDiffusionProcessing:
     seed_resize_from_w: int = -1
     seed_enable_extras: bool = True
     sampler_name: str = None
+    scheduler: str = None
     batch_size: int = 1
     n_iter: int = 1
     steps: int = 50
@@ -455,6 +458,7 @@ class StableDiffusionProcessing:
             self.height,
             opts.fp8_storage,
             opts.cache_fp16_weight,
+            opts.emphasis,
         )
 
     def get_conds_with_caching(self, function, required_prompts, steps, caches, extra_network_data, hires_steps=None):
@@ -604,7 +608,7 @@ class Processed:
             "version": self.version,
         }
 
-        return json.dumps(obj)
+        return json.dumps(obj, default=lambda o: None)
 
     def infotext(self, p: StableDiffusionProcessing, index):
         return create_infotext(p, self.all_prompts, self.all_seeds, self.all_subseeds, comments=[], position_in_batch=index % self.batch_size, iteration=index // self.batch_size)
@@ -700,7 +704,53 @@ def program_version():
 
 
 def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0, use_main_prompt=False, index=None, all_negative_prompts=None):
-    if index is None:
+    """
+    this function is used to generate the infotext that is stored in the generated images, it's contains the parameters that are required to generate the imagee
+    Args:
+        p: StableDiffusionProcessing
+        all_prompts: list[str]
+        all_seeds: list[int]
+        all_subseeds: list[int]
+        comments: list[str]
+        iteration: int
+        position_in_batch: int
+        use_main_prompt: bool
+        index: int
+        all_negative_prompts: list[str]
+
+    Returns: str
+
+    Extra generation params
+    p.extra_generation_params dictionary allows for additional parameters to be added to the infotext
+    this can be use by the base webui or extensions.
+    To add a new entry, add a new key value pair, the dictionary key will be used as the key of the parameter in the infotext
+    the value generation_params can be defined as:
+        - str | None
+        - List[str|None]
+        - callable func(**kwargs) -> str | None
+
+    When defined as a string, it will be used as without extra processing; this is this most common use case.
+
+    Defining as a list allows for parameter that changes across images in the job, for example, the 'Seed' parameter.
+    The list should have the same length as the total number of images in the entire job.
+
+    Defining as a callable function allows parameter cannot be generated earlier or when extra logic is required.
+    For example 'Hires prompt', due to reasons the hr_prompt might be changed by process in the pipeline or extensions
+    and may vary across different images, defining as a static string or list would not work.
+
+    The function takes locals() as **kwargs, as such will have access to variables like 'p' and 'index'.
+    the base signature of the function should be:
+        func(**kwargs) -> str | None
+    optionally it can have additional arguments that will be used in the function:
+        func(p, index, **kwargs) -> str | None
+    note: for better future compatibility even though this function will have access to all variables in the locals(),
+        it is recommended to only use the arguments present in the function signature of create_infotext.
+    For actual implementation examples, see StableDiffusionProcessingTxt2Img.init > get_hr_prompt.
+    """
+
+    if use_main_prompt:
+        index = 0
+    elif index is None:
         index = position_in_batch + iteration * p.batch_size
 
     if all_negative_prompts is None:
@@ -711,6 +761,9 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
     token_merging_ratio = p.get_token_merging_ratio()
     token_merging_ratio_hr = p.get_token_merging_ratio(for_hr=True)
 
+    prompt_text = p.main_prompt if use_main_prompt else all_prompts[index]
+    negative_prompt = p.main_negative_prompt if use_main_prompt else all_negative_prompts[index]
+
     uses_ensd = opts.eta_noise_seed_delta != 0
     if uses_ensd:
         uses_ensd = sd_samplers_common.is_sampler_using_eta_noise_seed_delta(p)
@@ -718,6 +771,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
     generation_params = {
         "Steps": p.steps,
         "Sampler": p.sampler_name,
+        "Schedule type": p.scheduler,
         "CFG scale": p.cfg_scale,
         "Image CFG scale": getattr(p, 'image_cfg_scale', None),
         "Seed": p.all_seeds[0] if use_main_prompt else all_seeds[index],
@@ -747,10 +801,19 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "User": p.user if opts.add_user_name_to_info else None,
     }
 
+    for key, value in generation_params.items():
+        try:
+            if isinstance(value, list):
+                generation_params[key] = value[index]
+            elif callable(value):
+                generation_params[key] = value(**locals())
+        except Exception:
+            errors.report(f'Error creating infotext for key "{key}"', exc_info=True)
+            generation_params[key] = None
+
     generation_params_text = ", ".join([k if k == v else f'{k}: {infotext_utils.quote(v)}' for k, v in generation_params.items() if v is not None])
 
-    prompt_text = p.main_prompt if use_main_prompt else all_prompts[index]
-    negative_prompt_text = f"\nNegative prompt: {p.main_negative_prompt if use_main_prompt else all_negative_prompts[index]}" if all_negative_prompts[index] else ""
+    negative_prompt_text = f"\nNegative prompt: {negative_prompt}" if negative_prompt else ""
 
     return f"{prompt_text}{negative_prompt_text}\n{generation_params_text}".strip()
 
@@ -893,52 +956,26 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             if p.scripts is not None:
                 p.scripts.process_batch(p, batch_number=n, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds)
 
+            p.setup_conds()
+
+            p.extra_generation_params.update(model_hijack.extra_generation_params)
+
             # params.txt should be saved after scripts.process_batch, since the
             # infotext could be modified by that callback
             # Example: a wildcard processed by process_batch sets an extra model
             # strength, which is saved as "Model Strength: 1.0" in the infotext
-            if n == 0:
+            if n == 0 and not cmd_opts.no_prompt_history:
                 with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file:
                     processed = Processed(p, [])
                     file.write(processed.infotext(p, 0))
 
-            p.setup_conds()
-
             for comment in model_hijack.comments:
                 p.comment(comment)
 
-            p.extra_generation_params.update(model_hijack.extra_generation_params)
-
             if p.n_iter > 1:
                 shared.state.job = f"Batch {n+1} out of {p.n_iter}"
 
-            def rescale_zero_terminal_snr_abar(alphas_cumprod):
-                alphas_bar_sqrt = alphas_cumprod.sqrt()
-
-                # Store old values.
-                alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone()
-                alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone()
-
-                # Shift so the last timestep is zero.
-                alphas_bar_sqrt -= (alphas_bar_sqrt_T)
-
-                # Scale so the first timestep is back to the old value.
-                alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T)
-
-                # Convert alphas_bar_sqrt to betas
-                alphas_bar = alphas_bar_sqrt**2  # Revert sqrt
-                alphas_bar[-1] = 4.8973451890853435e-08
-                return alphas_bar
-
-            if hasattr(p.sd_model, 'alphas_cumprod') and hasattr(p.sd_model, 'alphas_cumprod_original'):
-                p.sd_model.alphas_cumprod = p.sd_model.alphas_cumprod_original.to(shared.device)
-
-                if opts.use_downcasted_alpha_bar:
-                    p.extra_generation_params['Downcast alphas_cumprod'] = opts.use_downcasted_alpha_bar
-                    p.sd_model.alphas_cumprod = p.sd_model.alphas_cumprod.half().to(shared.device)
-                if opts.sd_noise_schedule == "Zero Terminal SNR":
-                    p.extra_generation_params['Noise Schedule'] = opts.sd_noise_schedule
-                    p.sd_model.alphas_cumprod = rescale_zero_terminal_snr_abar(p.sd_model.alphas_cumprod).to(shared.device)
+            sd_models.apply_alpha_schedule_override(p.sd_model, p)
 
             with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
                 samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
@@ -1005,7 +1042,13 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     image = pp.image
 
                 mask_for_overlay = getattr(p, "mask_for_overlay", None)
-                overlay_image = p.overlay_images[i] if getattr(p, "overlay_images", None) is not None and i < len(p.overlay_images) else None
+
+                if not shared.opts.overlay_inpaint:
+                    overlay_image = None
+                elif getattr(p, "overlay_images", None) is not None and i < len(p.overlay_images):
+                    overlay_image = p.overlay_images[i]
+                else:
+                    overlay_image = None
 
                 if p.scripts is not None:
                     ppmo = scripts.PostProcessMaskOverlayArgs(i, mask_for_overlay, overlay_image)
@@ -1014,7 +1057,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
                 if p.color_corrections is not None and i < len(p.color_corrections):
                     if save_samples and opts.save_images_before_color_correction:
-                        image_without_cc = apply_overlay(image, p.paste_to, overlay_image)
+                        image_without_cc, _ = apply_overlay(image, p.paste_to, overlay_image)
                         images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-color-correction")
                     image = apply_color_correction(p.color_corrections[i], image)
 
@@ -1022,12 +1065,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 # that is being composited over the original image,
                 # we need to keep the original image around
                 # and use it in the composite step.
-                original_denoised_image = image.copy()
-
-                if p.paste_to is not None:
-                    original_denoised_image = uncrop(original_denoised_image, (overlay_image.width, overlay_image.height), p.paste_to)
-
-                image = apply_overlay(image, p.paste_to, overlay_image)
+                image, original_denoised_image = apply_overlay(image, p.paste_to, overlay_image)
 
                 if p.scripts is not None:
                     pp = scripts.PostprocessImageArgs(image)
@@ -1128,6 +1166,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     hr_resize_y: int = 0
     hr_checkpoint_name: str = None
     hr_sampler_name: str = None
+    hr_scheduler: str = None
     hr_prompt: str = ''
     hr_negative_prompt: str = ''
     force_task_id: str = None
@@ -1216,11 +1255,21 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             if self.hr_sampler_name is not None and self.hr_sampler_name != self.sampler_name:
                 self.extra_generation_params["Hires sampler"] = self.hr_sampler_name
 
-            if tuple(self.hr_prompt) != tuple(self.prompt):
-                self.extra_generation_params["Hires prompt"] = self.hr_prompt
+            def get_hr_prompt(p, index, prompt_text, **kwargs):
+                hr_prompt = p.all_hr_prompts[index]
+                return hr_prompt if hr_prompt != prompt_text else None
 
-            if tuple(self.hr_negative_prompt) != tuple(self.negative_prompt):
-                self.extra_generation_params["Hires negative prompt"] = self.hr_negative_prompt
+            def get_hr_negative_prompt(p, index, negative_prompt, **kwargs):
+                hr_negative_prompt = p.all_hr_negative_prompts[index]
+                return hr_negative_prompt if hr_negative_prompt != negative_prompt else None
+
+            self.extra_generation_params["Hires prompt"] = get_hr_prompt
+            self.extra_generation_params["Hires negative prompt"] = get_hr_negative_prompt
+
+            self.extra_generation_params["Hires schedule type"] = None  # to be set in sd_samplers_kdiffusion.py
+
+            if self.hr_scheduler is None:
+                self.hr_scheduler = self.scheduler
 
             self.latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest")
             if self.enable_hr and self.latent_scale_mode is None:
@@ -1562,16 +1611,23 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             if self.inpaint_full_res:
                 self.mask_for_overlay = image_mask
                 mask = image_mask.convert('L')
-                crop_region = masking.get_crop_region(mask, self.inpaint_full_res_padding)
-                crop_region = masking.expand_crop_region(crop_region, self.width, self.height, mask.width, mask.height)
-                x1, y1, x2, y2 = crop_region
-
-                mask = mask.crop(crop_region)
-                image_mask = images.resize_image(2, mask, self.width, self.height)
-                self.paste_to = (x1, y1, x2-x1, y2-y1)
-
-                self.extra_generation_params["Inpaint area"] = "Only masked"
-                self.extra_generation_params["Masked area padding"] = self.inpaint_full_res_padding
+                crop_region = masking.get_crop_region_v2(mask, self.inpaint_full_res_padding)
+                if crop_region:
+                    crop_region = masking.expand_crop_region(crop_region, self.width, self.height, mask.width, mask.height)
+                    x1, y1, x2, y2 = crop_region
+                    mask = mask.crop(crop_region)
+                    image_mask = images.resize_image(2, mask, self.width, self.height)
+                    self.paste_to = (x1, y1, x2-x1, y2-y1)
+                    self.extra_generation_params["Inpaint area"] = "Only masked"
+                    self.extra_generation_params["Masked area padding"] = self.inpaint_full_res_padding
+                else:
+                    crop_region = None
+                    image_mask = None
+                    self.mask_for_overlay = None
+                    self.inpaint_full_res = False
+                    massage = 'Unable to perform "Inpaint Only mask" because mask is blank, switch to img2img mode.'
+                    model_hijack.comments.append(massage)
+                    logging.info(massage)
             else:
                 image_mask = images.resize_image(self.resize_mode, image_mask, self.width, self.height)
                 np_mask = np.array(image_mask)
@@ -1599,6 +1655,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
                 image = images.resize_image(self.resize_mode, image, self.width, self.height)
 
             if image_mask is not None:
+                if self.mask_for_overlay.size != (image.width, image.height):
+                    self.mask_for_overlay = images.resize_image(self.resize_mode, self.mask_for_overlay, image.width, image.height)
                 image_masked = Image.new('RGBa', (image.width, image.height))
                 image_masked.paste(image.convert("RGBA").convert("RGBa"), mask=ImageOps.invert(self.mask_for_overlay.convert('L')))
 

modules/processing_scripts/comments.py

@@ -0,0 +1,49 @@
+from modules import scripts, shared, script_callbacks
+import re
+
+
+def strip_comments(text):
+    text = re.sub('(^|\n)#[^\n]*(\n|$)', '\n', text)  # while line comment
+    text = re.sub('#[^\n]*(\n|$)', '\n', text)  # in the middle of the line comment
+
+    return text
+
+
+class ScriptStripComments(scripts.Script):
+    def title(self):
+        return "Comments"
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def process(self, p, *args):
+        if not shared.opts.enable_prompt_comments:
+            return
+
+        p.all_prompts = [strip_comments(x) for x in p.all_prompts]
+        p.all_negative_prompts = [strip_comments(x) for x in p.all_negative_prompts]
+
+        p.main_prompt = strip_comments(p.main_prompt)
+        p.main_negative_prompt = strip_comments(p.main_negative_prompt)
+
+        if getattr(p, 'enable_hr', False):
+            p.all_hr_prompts = [strip_comments(x) for x in p.all_hr_prompts]
+            p.all_hr_negative_prompts = [strip_comments(x) for x in p.all_hr_negative_prompts]
+
+            p.hr_prompt = strip_comments(p.hr_prompt)
+            p.hr_negative_prompt = strip_comments(p.hr_negative_prompt)
+
+
+def before_token_counter(params: script_callbacks.BeforeTokenCounterParams):
+    if not shared.opts.enable_prompt_comments:
+        return
+
+    params.prompt = strip_comments(params.prompt)
+
+
+script_callbacks.on_before_token_counter(before_token_counter)
+
+
+shared.options_templates.update(shared.options_section(('sd', "Stable Diffusion", "sd"), {
+    "enable_prompt_comments": shared.OptionInfo(True, "Enable comments").info("Use # anywhere in the prompt to hide the text between # and the end of the line from the generation."),
+}))

modules/processing_scripts/sampler.py

@@ -0,0 +1,45 @@
+import gradio as gr
+
+from modules import scripts, sd_samplers, sd_schedulers, shared
+from modules.infotext_utils import PasteField
+from modules.ui_components import FormRow, FormGroup
+
+
+class ScriptSampler(scripts.ScriptBuiltinUI):
+    section = "sampler"
+
+    def __init__(self):
+        self.steps = None
+        self.sampler_name = None
+        self.scheduler = None
+
+    def title(self):
+        return "Sampler"
+
+    def ui(self, is_img2img):
+        sampler_names = [x.name for x in sd_samplers.visible_samplers()]
+        scheduler_names = [x.label for x in sd_schedulers.schedulers]
+
+        if shared.opts.samplers_in_dropdown:
+            with FormRow(elem_id=f"sampler_selection_{self.tabname}"):
+                self.sampler_name = gr.Dropdown(label='Sampling method', elem_id=f"{self.tabname}_sampling", choices=sampler_names, value=sampler_names[0])
+                self.scheduler = gr.Dropdown(label='Schedule type', elem_id=f"{self.tabname}_scheduler", choices=scheduler_names, value=scheduler_names[0])
+                self.steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{self.tabname}_steps", label="Sampling steps", value=20)
+        else:
+            with FormGroup(elem_id=f"sampler_selection_{self.tabname}"):
+                self.steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{self.tabname}_steps", label="Sampling steps", value=20)
+                self.sampler_name = gr.Radio(label='Sampling method', elem_id=f"{self.tabname}_sampling", choices=sampler_names, value=sampler_names[0])
+                self.scheduler = gr.Dropdown(label='Schedule type', elem_id=f"{self.tabname}_scheduler", choices=scheduler_names, value=scheduler_names[0])
+
+        self.infotext_fields = [
+            PasteField(self.steps, "Steps", api="steps"),
+            PasteField(self.sampler_name, sd_samplers.get_sampler_from_infotext, api="sampler_name"),
+            PasteField(self.scheduler, sd_samplers.get_scheduler_from_infotext, api="scheduler"),
+        ]
+
+        return self.steps, self.sampler_name, self.scheduler
+
+    def setup(self, p, steps, sampler_name, scheduler):
+        p.steps = steps
+        p.sampler_name = sampler_name
+        p.scheduler = scheduler

modules/rng.py

@@ -34,7 +34,7 @@ def randn_local(seed, shape):
 
 
 def randn_like(x):
-    """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator.
+    """Generate a tensor with random numbers from a normal distribution using the previously initialized generator.
 
     Use either randn() or manual_seed() to initialize the generator."""
 
@@ -48,7 +48,7 @@ def 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.
+    """Generate a tensor with random numbers from a normal distribution using the previously initialized generator.
 
     Use either randn() or manual_seed() to initialize the generator."""
 

modules/script_callbacks.py

@@ -1,12 +1,14 @@
+from __future__ import annotations
+
+import dataclasses
 import inspect
 import os
-from collections import namedtuple
 from typing import Optional, Any
 
 from fastapi import FastAPI
 from gradio import Blocks
 
-from modules import errors, timer
+from modules import errors, timer, extensions, shared, util
 
 
 def report_exception(c, job):
@@ -106,7 +108,114 @@ class ImageGridLoopParams:
         self.rows = rows
 
 
-ScriptCallback = namedtuple("ScriptCallback", ["script", "callback"])
+@dataclasses.dataclass
+class BeforeTokenCounterParams:
+    prompt: str
+    steps: int
+    styles: list
+
+    is_positive: bool = True
+
+
+@dataclasses.dataclass
+class ScriptCallback:
+    script: str
+    callback: any
+    name: str = "unnamed"
+
+
+def add_callback(callbacks, fun, *, name=None, category='unknown', filename=None):
+    if filename is None:
+        stack = [x for x in inspect.stack() if x.filename != __file__]
+        filename = stack[0].filename if stack else 'unknown file'
+
+    extension = extensions.find_extension(filename)
+    extension_name = extension.canonical_name if extension else 'base'
+
+    callback_name = f"{extension_name}/{os.path.basename(filename)}/{category}"
+    if name is not None:
+        callback_name += f'/{name}'
+
+    unique_callback_name = callback_name
+    for index in range(1000):
+        existing = any(x.name == unique_callback_name for x in callbacks)
+        if not existing:
+            break
+
+        unique_callback_name = f'{callback_name}-{index+1}'
+
+    callbacks.append(ScriptCallback(filename, fun, unique_callback_name))
+
+
+def sort_callbacks(category, unordered_callbacks, *, enable_user_sort=True):
+    callbacks = unordered_callbacks.copy()
+    callback_lookup = {x.name: x for x in callbacks}
+    dependencies = {}
+
+    order_instructions = {}
+    for extension in extensions.extensions:
+        for order_instruction in extension.metadata.list_callback_order_instructions():
+            if order_instruction.name in callback_lookup:
+                if order_instruction.name not in order_instructions:
+                    order_instructions[order_instruction.name] = []
+
+                order_instructions[order_instruction.name].append(order_instruction)
+
+    if order_instructions:
+        for callback in callbacks:
+            dependencies[callback.name] = []
+
+        for callback in callbacks:
+            for order_instruction in order_instructions.get(callback.name, []):
+                for after in order_instruction.after:
+                    if after not in callback_lookup:
+                        continue
+
+                    dependencies[callback.name].append(after)
+
+                for before in order_instruction.before:
+                    if before not in callback_lookup:
+                        continue
+
+                    dependencies[before].append(callback.name)
+
+        sorted_names = util.topological_sort(dependencies)
+        callbacks = [callback_lookup[x] for x in sorted_names]
+
+    if enable_user_sort:
+        for name in reversed(getattr(shared.opts, 'prioritized_callbacks_' + category, [])):
+            index = next((i for i, callback in enumerate(callbacks) if callback.name == name), None)
+            if index is not None:
+                callbacks.insert(0, callbacks.pop(index))
+
+    return callbacks
+
+
+def ordered_callbacks(category, unordered_callbacks=None, *, enable_user_sort=True):
+    if unordered_callbacks is None:
+        unordered_callbacks = callback_map.get('callbacks_' + category, [])
+
+    if not enable_user_sort:
+        return sort_callbacks(category, unordered_callbacks, enable_user_sort=False)
+
+    callbacks = ordered_callbacks_map.get(category)
+    if callbacks is not None and len(callbacks) == len(unordered_callbacks):
+        return callbacks
+
+    callbacks = sort_callbacks(category, unordered_callbacks)
+
+    ordered_callbacks_map[category] = callbacks
+    return callbacks
+
+
+def enumerate_callbacks():
+    for category, callbacks in callback_map.items():
+        if category.startswith('callbacks_'):
+            category = category[10:]
+
+        yield category, callbacks
+
+
 callback_map = dict(
     callbacks_app_started=[],
     callbacks_model_loaded=[],
@@ -128,16 +237,21 @@ callback_map = dict(
     callbacks_on_reload=[],
     callbacks_list_optimizers=[],
     callbacks_list_unets=[],
+    callbacks_before_token_counter=[],
 )
 
+ordered_callbacks_map = {}
+
 
 def clear_callbacks():
     for callback_list in callback_map.values():
         callback_list.clear()
 
+    ordered_callbacks_map.clear()
+
 
 def app_started_callback(demo: Optional[Blocks], app: FastAPI):
-    for c in callback_map['callbacks_app_started']:
+    for c in ordered_callbacks('app_started'):
         try:
             c.callback(demo, app)
             timer.startup_timer.record(os.path.basename(c.script))
@@ -146,7 +260,7 @@ def app_started_callback(demo: Optional[Blocks], app: FastAPI):
 
 
 def app_reload_callback():
-    for c in callback_map['callbacks_on_reload']:
+    for c in ordered_callbacks('on_reload'):
         try:
             c.callback()
         except Exception:
@@ -154,7 +268,7 @@ def app_reload_callback():
 
 
 def model_loaded_callback(sd_model):
-    for c in callback_map['callbacks_model_loaded']:
+    for c in ordered_callbacks('model_loaded'):
         try:
             c.callback(sd_model)
         except Exception:
@@ -164,7 +278,7 @@ def model_loaded_callback(sd_model):
 def ui_tabs_callback():
     res = []
 
-    for c in callback_map['callbacks_ui_tabs']:
+    for c in ordered_callbacks('ui_tabs'):
         try:
             res += c.callback() or []
         except Exception:
@@ -174,7 +288,7 @@ def ui_tabs_callback():
 
 
 def ui_train_tabs_callback(params: UiTrainTabParams):
-    for c in callback_map['callbacks_ui_train_tabs']:
+    for c in ordered_callbacks('ui_train_tabs'):
         try:
             c.callback(params)
         except Exception:
@@ -182,7 +296,7 @@ def ui_train_tabs_callback(params: UiTrainTabParams):
 
 
 def ui_settings_callback():
-    for c in callback_map['callbacks_ui_settings']:
+    for c in ordered_callbacks('ui_settings'):
         try:
             c.callback()
         except Exception:
@@ -190,7 +304,7 @@ def ui_settings_callback():
 
 
 def before_image_saved_callback(params: ImageSaveParams):
-    for c in callback_map['callbacks_before_image_saved']:
+    for c in ordered_callbacks('before_image_saved'):
         try:
             c.callback(params)
         except Exception:
@@ -198,7 +312,7 @@ def before_image_saved_callback(params: ImageSaveParams):
 
 
 def image_saved_callback(params: ImageSaveParams):
-    for c in callback_map['callbacks_image_saved']:
+    for c in ordered_callbacks('image_saved'):
         try:
             c.callback(params)
         except Exception:
@@ -206,7 +320,7 @@ def image_saved_callback(params: ImageSaveParams):
 
 
 def extra_noise_callback(params: ExtraNoiseParams):
-    for c in callback_map['callbacks_extra_noise']:
+    for c in ordered_callbacks('extra_noise'):
         try:
             c.callback(params)
         except Exception:
@@ -214,7 +328,7 @@ def extra_noise_callback(params: ExtraNoiseParams):
 
 
 def cfg_denoiser_callback(params: CFGDenoiserParams):
-    for c in callback_map['callbacks_cfg_denoiser']:
+    for c in ordered_callbacks('cfg_denoiser'):
         try:
             c.callback(params)
         except Exception:
@@ -222,7 +336,7 @@ def cfg_denoiser_callback(params: CFGDenoiserParams):
 
 
 def cfg_denoised_callback(params: CFGDenoisedParams):
-    for c in callback_map['callbacks_cfg_denoised']:
+    for c in ordered_callbacks('cfg_denoised'):
         try:
             c.callback(params)
         except Exception:
@@ -230,7 +344,7 @@ def cfg_denoised_callback(params: CFGDenoisedParams):
 
 
 def cfg_after_cfg_callback(params: AfterCFGCallbackParams):
-    for c in callback_map['callbacks_cfg_after_cfg']:
+    for c in ordered_callbacks('cfg_after_cfg'):
         try:
             c.callback(params)
         except Exception:
@@ -238,7 +352,7 @@ def cfg_after_cfg_callback(params: AfterCFGCallbackParams):
 
 
 def before_component_callback(component, **kwargs):
-    for c in callback_map['callbacks_before_component']:
+    for c in ordered_callbacks('before_component'):
         try:
             c.callback(component, **kwargs)
         except Exception:
@@ -246,7 +360,7 @@ def before_component_callback(component, **kwargs):
 
 
 def after_component_callback(component, **kwargs):
-    for c in callback_map['callbacks_after_component']:
+    for c in ordered_callbacks('after_component'):
         try:
             c.callback(component, **kwargs)
         except Exception:
@@ -254,7 +368,7 @@ def after_component_callback(component, **kwargs):
 
 
 def image_grid_callback(params: ImageGridLoopParams):
-    for c in callback_map['callbacks_image_grid']:
+    for c in ordered_callbacks('image_grid'):
         try:
             c.callback(params)
         except Exception:
@@ -262,7 +376,7 @@ def image_grid_callback(params: ImageGridLoopParams):
 
 
 def infotext_pasted_callback(infotext: str, params: dict[str, Any]):
-    for c in callback_map['callbacks_infotext_pasted']:
+    for c in ordered_callbacks('infotext_pasted'):
         try:
             c.callback(infotext, params)
         except Exception:
@@ -270,7 +384,7 @@ def infotext_pasted_callback(infotext: str, params: dict[str, Any]):
 
 
 def script_unloaded_callback():
-    for c in reversed(callback_map['callbacks_script_unloaded']):
+    for c in reversed(ordered_callbacks('script_unloaded')):
         try:
             c.callback()
         except Exception:
@@ -278,7 +392,7 @@ def script_unloaded_callback():
 
 
 def before_ui_callback():
-    for c in reversed(callback_map['callbacks_before_ui']):
+    for c in reversed(ordered_callbacks('before_ui')):
         try:
             c.callback()
         except Exception:
@@ -288,7 +402,7 @@ def before_ui_callback():
 def list_optimizers_callback():
     res = []
 
-    for c in callback_map['callbacks_list_optimizers']:
+    for c in ordered_callbacks('list_optimizers'):
         try:
             c.callback(res)
         except Exception:
@@ -300,7 +414,7 @@ def list_optimizers_callback():
 def list_unets_callback():
     res = []
 
-    for c in callback_map['callbacks_list_unets']:
+    for c in ordered_callbacks('list_unets'):
         try:
             c.callback(res)
         except Exception:
@@ -309,11 +423,12 @@ def list_unets_callback():
     return res
 
 
-def add_callback(callbacks, fun):
-    stack = [x for x in inspect.stack() if x.filename != __file__]
-    filename = stack[0].filename if stack else 'unknown file'
-
-    callbacks.append(ScriptCallback(filename, fun))
+def before_token_counter_callback(params: BeforeTokenCounterParams):
+    for c in ordered_callbacks('before_token_counter'):
+        try:
+            c.callback(params)
+        except Exception:
+            report_exception(c, 'before_token_counter')
 
 
 def remove_current_script_callbacks():
@@ -324,32 +439,38 @@ def remove_current_script_callbacks():
     for callback_list in callback_map.values():
         for callback_to_remove in [cb for cb in callback_list if cb.script == filename]:
             callback_list.remove(callback_to_remove)
+    for ordered_callbacks_list in ordered_callbacks_map.values():
+        for callback_to_remove in [cb for cb in ordered_callbacks_list if cb.script == filename]:
+            ordered_callbacks_list.remove(callback_to_remove)
 
 
 def remove_callbacks_for_function(callback_func):
     for callback_list in callback_map.values():
         for callback_to_remove in [cb for cb in callback_list if cb.callback == callback_func]:
             callback_list.remove(callback_to_remove)
+    for ordered_callback_list in ordered_callbacks_map.values():
+        for callback_to_remove in [cb for cb in ordered_callback_list if cb.callback == callback_func]:
+            ordered_callback_list.remove(callback_to_remove)
 
 
-def on_app_started(callback):
+def on_app_started(callback, *, name=None):
     """register a function to be called when the webui started, the gradio `Block` component and
     fastapi `FastAPI` object are passed as the arguments"""
-    add_callback(callback_map['callbacks_app_started'], callback)
+    add_callback(callback_map['callbacks_app_started'], callback, name=name, category='app_started')
 
 
-def on_before_reload(callback):
+def on_before_reload(callback, *, name=None):
     """register a function to be called just before the server reloads."""
-    add_callback(callback_map['callbacks_on_reload'], callback)
+    add_callback(callback_map['callbacks_on_reload'], callback, name=name, category='on_reload')
 
 
-def on_model_loaded(callback):
+def on_model_loaded(callback, *, name=None):
     """register a function to be called when the stable diffusion model is created; the model is
     passed as an argument; this function is also called when the script is reloaded. """
-    add_callback(callback_map['callbacks_model_loaded'], callback)
+    add_callback(callback_map['callbacks_model_loaded'], callback, name=name, category='model_loaded')
 
 
-def on_ui_tabs(callback):
+def on_ui_tabs(callback, *, name=None):
     """register a function to be called when the UI is creating new tabs.
     The function must either return a None, which means no new tabs to be added, or a list, where
     each element is a tuple:
@@ -359,71 +480,71 @@ def on_ui_tabs(callback):
     title is tab text displayed to user in the UI
     elem_id is HTML id for the tab
     """
-    add_callback(callback_map['callbacks_ui_tabs'], callback)
+    add_callback(callback_map['callbacks_ui_tabs'], callback, name=name, category='ui_tabs')
 
 
-def on_ui_train_tabs(callback):
+def on_ui_train_tabs(callback, *, name=None):
     """register a function to be called when the UI is creating new tabs for the train tab.
     Create your new tabs with gr.Tab.
     """
-    add_callback(callback_map['callbacks_ui_train_tabs'], callback)
+    add_callback(callback_map['callbacks_ui_train_tabs'], callback, name=name, category='ui_train_tabs')
 
 
-def on_ui_settings(callback):
+def on_ui_settings(callback, *, name=None):
     """register a function to be called before UI settings are populated; add your settings
     by using shared.opts.add_option(shared.OptionInfo(...)) """
-    add_callback(callback_map['callbacks_ui_settings'], callback)
+    add_callback(callback_map['callbacks_ui_settings'], callback, name=name, category='ui_settings')
 
 
-def on_before_image_saved(callback):
+def on_before_image_saved(callback, *, name=None):
     """register a function to be called before an image is saved to a file.
     The callback is called with one argument:
         - params: ImageSaveParams - parameters the image is to be saved with. You can change fields in this object.
     """
-    add_callback(callback_map['callbacks_before_image_saved'], callback)
+    add_callback(callback_map['callbacks_before_image_saved'], callback, name=name, category='before_image_saved')
 
 
-def on_image_saved(callback):
+def on_image_saved(callback, *, name=None):
     """register a function to be called after an image is saved to a file.
     The callback is called with one argument:
         - params: ImageSaveParams - parameters the image was saved with. Changing fields in this object does nothing.
     """
-    add_callback(callback_map['callbacks_image_saved'], callback)
+    add_callback(callback_map['callbacks_image_saved'], callback, name=name, category='image_saved')
 
 
-def on_extra_noise(callback):
+def on_extra_noise(callback, *, name=None):
     """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)
+    add_callback(callback_map['callbacks_extra_noise'], callback, name=name, category='extra_noise')
 
 
-def on_cfg_denoiser(callback):
+def on_cfg_denoiser(callback, *, name=None):
     """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:
         - params: CFGDenoiserParams - parameters to be passed to the inner model and sampling state details.
     """
-    add_callback(callback_map['callbacks_cfg_denoiser'], callback)
+    add_callback(callback_map['callbacks_cfg_denoiser'], callback, name=name, category='cfg_denoiser')
 
 
-def on_cfg_denoised(callback):
+def on_cfg_denoised(callback, *, name=None):
     """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:
         - params: CFGDenoisedParams - parameters to be passed to the inner model and sampling state details.
     """
-    add_callback(callback_map['callbacks_cfg_denoised'], callback)
+    add_callback(callback_map['callbacks_cfg_denoised'], callback, name=name, category='cfg_denoised')
 
 
-def on_cfg_after_cfg(callback):
+def on_cfg_after_cfg(callback, *, name=None):
     """register a function to be called in the kdiffussion cfg_denoiser method after cfg calculations are completed.
     The callback is called with one argument:
         - params: AfterCFGCallbackParams - parameters to be passed to the script for post-processing after cfg calculation.
     """
-    add_callback(callback_map['callbacks_cfg_after_cfg'], callback)
+    add_callback(callback_map['callbacks_cfg_after_cfg'], callback, name=name, category='cfg_after_cfg')
 
 
-def on_before_component(callback):
+def on_before_component(callback, *, name=None):
     """register a function to be called before a component is created.
     The callback is called with arguments:
         - component - gradio component that is about to be created.
@@ -432,54 +553,61 @@ def on_before_component(callback):
     Use elem_id/label fields of kwargs to figure out which component it is.
     This can be useful to inject your own components somewhere in the middle of vanilla UI.
     """
-    add_callback(callback_map['callbacks_before_component'], callback)
+    add_callback(callback_map['callbacks_before_component'], callback, name=name, category='before_component')
 
 
-def on_after_component(callback):
+def on_after_component(callback, *, name=None):
     """register a function to be called after a component is created. See on_before_component for more."""
-    add_callback(callback_map['callbacks_after_component'], callback)
+    add_callback(callback_map['callbacks_after_component'], callback, name=name, category='after_component')
 
 
-def on_image_grid(callback):
+def on_image_grid(callback, *, name=None):
     """register a function to be called before making an image grid.
     The callback is called with one argument:
        - params: ImageGridLoopParams - parameters to be used for grid creation. Can be modified.
     """
-    add_callback(callback_map['callbacks_image_grid'], callback)
+    add_callback(callback_map['callbacks_image_grid'], callback, name=name, category='image_grid')
 
 
-def on_infotext_pasted(callback):
+def on_infotext_pasted(callback, *, name=None):
     """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.
     """
-    add_callback(callback_map['callbacks_infotext_pasted'], callback)
+    add_callback(callback_map['callbacks_infotext_pasted'], callback, name=name, category='infotext_pasted')
 
 
-def on_script_unloaded(callback):
+def on_script_unloaded(callback, *, name=None):
     """register a function to be called before the script is unloaded. Any hooks/hijacks/monkeying about that
     the script did should be reverted here"""
 
-    add_callback(callback_map['callbacks_script_unloaded'], callback)
+    add_callback(callback_map['callbacks_script_unloaded'], callback, name=name, category='script_unloaded')
 
 
-def on_before_ui(callback):
+def on_before_ui(callback, *, name=None):
     """register a function to be called before the UI is created."""
 
-    add_callback(callback_map['callbacks_before_ui'], callback)
+    add_callback(callback_map['callbacks_before_ui'], callback, name=name, category='before_ui')
 
 
-def on_list_optimizers(callback):
+def on_list_optimizers(callback, *, name=None):
     """register a function to be called when UI is making a list of cross attention optimization options.
     The function will be called with one argument, a list, and shall add objects of type modules.sd_hijack_optimizations.SdOptimization
     to it."""
 
-    add_callback(callback_map['callbacks_list_optimizers'], callback)
+    add_callback(callback_map['callbacks_list_optimizers'], callback, name=name, category='list_optimizers')
 
 
-def on_list_unets(callback):
+def on_list_unets(callback, *, name=None):
     """register a function to be called when UI is making a list of alternative options for unet.
     The function will be called with one argument, a list, and shall add objects of type modules.sd_unet.SdUnetOption to it."""
 
-    add_callback(callback_map['callbacks_list_unets'], callback)
+    add_callback(callback_map['callbacks_list_unets'], callback, name=name, category='list_unets')
+
+
+def on_before_token_counter(callback, *, name=None):
+    """register a function to be called when UI is counting tokens for a prompt.
+    The function will be called with one argument of type BeforeTokenCounterParams, and should modify its fields if necessary."""
+
+    add_callback(callback_map['callbacks_before_token_counter'], callback, name=name, category='before_token_counter')

modules/script_loading.py

@@ -4,11 +4,15 @@ import importlib.util
 from modules import errors
 
 
+loaded_scripts = {}
+
+
 def load_module(path):
     module_spec = importlib.util.spec_from_file_location(os.path.basename(path), path)
     module = importlib.util.module_from_spec(module_spec)
     module_spec.loader.exec_module(module)
 
+    loaded_scripts[path] = module
     return module
 
 

modules/scripts.py

@@ -7,7 +7,9 @@ from dataclasses import dataclass
 
 import gradio as gr
 
-from modules import shared, paths, script_callbacks, extensions, script_loading, scripts_postprocessing, errors, timer
+from modules import shared, paths, script_callbacks, extensions, script_loading, scripts_postprocessing, errors, timer, util
+
+topological_sort = util.topological_sort
 
 AlwaysVisible = object()
 
@@ -92,7 +94,7 @@ class Script:
     """If true, the script setup will only be run in Gradio UI, not in API"""
 
     controls = None
-    """A list of controls retured by the ui()."""
+    """A list of controls returned by the ui()."""
 
     def title(self):
         """this function should return the title of the script. This is what will be displayed in the dropdown menu."""
@@ -109,7 +111,7 @@ class Script:
 
     def show(self, is_img2img):
         """
-        is_img2img is True if this function is called for the img2img interface, and Fasle otherwise
+        is_img2img is True if this function is called for the img2img interface, and False otherwise
 
         This function should return:
          - False if the script should not be shown in UI at all
@@ -138,7 +140,6 @@ class Script:
         """
         pass
 
-
     def before_process(self, p, *args):
         """
         This function is called very early during processing begins for AlwaysVisible scripts.
@@ -351,6 +352,9 @@ class ScriptBuiltinUI(Script):
 
         return f'{tabname}{item_id}'
 
+    def show(self, is_img2img):
+        return AlwaysVisible
+
 
 current_basedir = paths.script_path
 
@@ -369,29 +373,6 @@ 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
-    """
-
-    visited = {}
-    result = []
-
-    def inner(name):
-        visited[name] = True
-
-        for dep in dependencies.get(name, []):
-            if dep in dependencies and dep not in visited:
-                inner(dep)
-
-        result.append(name)
-
-    for depname in dependencies:
-        if depname not in visited:
-            inner(depname)
-
-    return result
-
 
 @dataclass
 class ScriptWithDependencies:
@@ -562,6 +543,25 @@ class ScriptRunner:
         self.paste_field_names = []
         self.inputs = [None]
 
+        self.callback_map = {}
+        self.callback_names = [
+            'before_process',
+            'process',
+            'before_process_batch',
+            'after_extra_networks_activate',
+            'process_batch',
+            'postprocess',
+            'postprocess_batch',
+            'postprocess_batch_list',
+            'post_sample',
+            'on_mask_blend',
+            'postprocess_image',
+            'postprocess_maskoverlay',
+            'postprocess_image_after_composite',
+            'before_component',
+            'after_component',
+        ]
+
         self.on_before_component_elem_id = {}
         """dict of callbacks to be called before an element is created; key=elem_id, value=list of callbacks"""
 
@@ -600,6 +600,8 @@ class ScriptRunner:
                 self.scripts.append(script)
                 self.selectable_scripts.append(script)
 
+        self.callback_map.clear()
+
         self.apply_on_before_component_callbacks()
 
     def apply_on_before_component_callbacks(self):
@@ -737,12 +739,17 @@ class ScriptRunner:
         def onload_script_visibility(params):
             title = params.get('Script', None)
             if title:
-                title_index = self.titles.index(title)
-                visibility = title_index == self.script_load_ctr
-                self.script_load_ctr = (self.script_load_ctr + 1) % len(self.titles)
-                return gr.update(visible=visibility)
-            else:
-                return gr.update(visible=False)
+                try:
+                    title_index = self.titles.index(title)
+                    visibility = title_index == self.script_load_ctr
+                    self.script_load_ctr = (self.script_load_ctr + 1) % len(self.titles)
+                    return gr.update(visible=visibility)
+                except ValueError:
+                    params['Script'] = None
+                    massage = f'Cannot find Script: "{title}"'
+                    print(massage)
+                    gr.Warning(massage)
+            return gr.update(visible=False)
 
         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])
@@ -769,8 +776,42 @@ class ScriptRunner:
 
         return processed
 
+    def list_scripts_for_method(self, method_name):
+        if method_name in ('before_component', 'after_component'):
+            return self.scripts
+        else:
+            return self.alwayson_scripts
+
+    def create_ordered_callbacks_list(self,  method_name, *, enable_user_sort=True):
+        script_list = self.list_scripts_for_method(method_name)
+        category = f'script_{method_name}'
+        callbacks = []
+
+        for script in script_list:
+            if getattr(script.__class__, method_name, None) == getattr(Script, method_name, None):
+                continue
+
+            script_callbacks.add_callback(callbacks, script, category=category, name=script.__class__.__name__, filename=script.filename)
+
+        return script_callbacks.sort_callbacks(category, callbacks, enable_user_sort=enable_user_sort)
+
+    def ordered_callbacks(self, method_name, *, enable_user_sort=True):
+        script_list = self.list_scripts_for_method(method_name)
+        category = f'script_{method_name}'
+
+        scrpts_len, callbacks = self.callback_map.get(category, (-1, None))
+
+        if callbacks is None or scrpts_len != len(script_list):
+            callbacks = self.create_ordered_callbacks_list(method_name, enable_user_sort=enable_user_sort)
+            self.callback_map[category] = len(script_list), callbacks
+
+        return callbacks
+
+    def ordered_scripts(self, method_name):
+        return [x.callback for x in self.ordered_callbacks(method_name)]
+
     def before_process(self, p):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('before_process'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.before_process(p, *script_args)
@@ -778,7 +819,7 @@ class ScriptRunner:
                 errors.report(f"Error running before_process: {script.filename}", exc_info=True)
 
     def process(self, p):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('process'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.process(p, *script_args)
@@ -786,7 +827,7 @@ class ScriptRunner:
                 errors.report(f"Error running process: {script.filename}", exc_info=True)
 
     def before_process_batch(self, p, **kwargs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('before_process_batch'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.before_process_batch(p, *script_args, **kwargs)
@@ -794,7 +835,7 @@ class ScriptRunner:
                 errors.report(f"Error running before_process_batch: {script.filename}", exc_info=True)
 
     def after_extra_networks_activate(self, p, **kwargs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('after_extra_networks_activate'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.after_extra_networks_activate(p, *script_args, **kwargs)
@@ -802,7 +843,7 @@ class ScriptRunner:
                 errors.report(f"Error running after_extra_networks_activate: {script.filename}", exc_info=True)
 
     def process_batch(self, p, **kwargs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('process_batch'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.process_batch(p, *script_args, **kwargs)
@@ -810,7 +851,7 @@ class ScriptRunner:
                 errors.report(f"Error running process_batch: {script.filename}", exc_info=True)
 
     def postprocess(self, p, processed):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('postprocess'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.postprocess(p, processed, *script_args)
@@ -818,7 +859,7 @@ class ScriptRunner:
                 errors.report(f"Error running postprocess: {script.filename}", exc_info=True)
 
     def postprocess_batch(self, p, images, **kwargs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('postprocess_batch'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.postprocess_batch(p, *script_args, images=images, **kwargs)
@@ -826,7 +867,7 @@ class ScriptRunner:
                 errors.report(f"Error running postprocess_batch: {script.filename}", exc_info=True)
 
     def postprocess_batch_list(self, p, pp: PostprocessBatchListArgs, **kwargs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('postprocess_batch_list'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.postprocess_batch_list(p, pp, *script_args, **kwargs)
@@ -834,7 +875,7 @@ class ScriptRunner:
                 errors.report(f"Error running postprocess_batch_list: {script.filename}", exc_info=True)
 
     def post_sample(self, p, ps: PostSampleArgs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('post_sample'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.post_sample(p, ps, *script_args)
@@ -842,7 +883,7 @@ class ScriptRunner:
                 errors.report(f"Error running post_sample: {script.filename}", exc_info=True)
 
     def on_mask_blend(self, p, mba: MaskBlendArgs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('on_mask_blend'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.on_mask_blend(p, mba, *script_args)
@@ -850,7 +891,7 @@ class ScriptRunner:
                 errors.report(f"Error running post_sample: {script.filename}", exc_info=True)
 
     def postprocess_image(self, p, pp: PostprocessImageArgs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('postprocess_image'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.postprocess_image(p, pp, *script_args)
@@ -858,7 +899,7 @@ class ScriptRunner:
                 errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
 
     def postprocess_maskoverlay(self, p, ppmo: PostProcessMaskOverlayArgs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('postprocess_maskoverlay'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.postprocess_maskoverlay(p, ppmo, *script_args)
@@ -866,7 +907,7 @@ class ScriptRunner:
                 errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
 
     def postprocess_image_after_composite(self, p, pp: PostprocessImageArgs):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('postprocess_image_after_composite'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.postprocess_image_after_composite(p, pp, *script_args)
@@ -880,7 +921,7 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running on_before_component: {script.filename}", exc_info=True)
 
-        for script in self.scripts:
+        for script in self.ordered_scripts('before_component'):
             try:
                 script.before_component(component, **kwargs)
             except Exception:
@@ -893,7 +934,7 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running on_after_component: {script.filename}", exc_info=True)
 
-        for script in self.scripts:
+        for script in self.ordered_scripts('after_component'):
             try:
                 script.after_component(component, **kwargs)
             except Exception:
@@ -921,7 +962,7 @@ class ScriptRunner:
                     self.scripts[si].args_to = args_to
 
     def before_hr(self, p):
-        for script in self.alwayson_scripts:
+        for script in self.ordered_scripts('before_hr'):
             try:
                 script_args = p.script_args[script.args_from:script.args_to]
                 script.before_hr(p, *script_args)
@@ -929,7 +970,7 @@ class ScriptRunner:
                 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:
+        for script in self.ordered_scripts('setup'):
             if not is_ui and script.setup_for_ui_only:
                 continue
 
@@ -939,22 +980,34 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running setup: {script.filename}", exc_info=True)
 
-    def set_named_arg(self, args, script_type, arg_elem_id, value):
-        script = next((x for x in self.scripts if type(x).__name__ == script_type), None)
+    def set_named_arg(self, args, script_name, arg_elem_id, value, fuzzy=False):
+        """Locate an arg of a specific script in script_args and set its value
+        Args:
+            args: all script args of process p, p.script_args
+            script_name: the name target script name to
+            arg_elem_id: the elem_id of the target arg
+            value: the value to set
+            fuzzy: if True, arg_elem_id can be a substring of the control.elem_id else exact match
+        Returns:
+            Updated script args
+        when script_name in not found or arg_elem_id is not found in script controls, raise RuntimeError
+        """
+        script = next((x for x in self.scripts if x.name == script_name), None)
         if script is None:
-            return
+            raise RuntimeError(f"script {script_name} not found")
 
         for i, control in enumerate(script.controls):
-            if arg_elem_id in control.elem_id:
+            if arg_elem_id in control.elem_id if fuzzy else arg_elem_id == control.elem_id:
                 index = script.args_from + i
 
-                if isinstance(args, list):
+                if isinstance(args, tuple):
+                    return args[:index] + (value,) + args[index + 1:]
+                elif isinstance(args, list):
                     args[index] = value
                     return args
-                elif isinstance(args, tuple):
-                    return args[:index] + (value,) + args[index+1:]
                 else:
-                    return None
+                    raise RuntimeError(f"args is not a list or tuple, but {type(args)}")
+        raise RuntimeError(f"arg_elem_id {arg_elem_id} not found in script {script_name}")
 
 
 scripts_txt2img: ScriptRunner = None

modules/scripts_postprocessing.py

@@ -143,6 +143,7 @@ class ScriptPostprocessingRunner:
             self.initialize_scripts(modules.scripts.postprocessing_scripts_data)
 
         scripts_order = shared.opts.postprocessing_operation_order
+        scripts_filter_out = set(shared.opts.postprocessing_disable_in_extras)
 
         def script_score(name):
             for i, possible_match in enumerate(scripts_order):
@@ -151,9 +152,10 @@ class ScriptPostprocessingRunner:
 
             return len(self.scripts)
 
-        script_scores = {script.name: (script_score(script.name), script.order, script.name, original_index) for original_index, script in enumerate(self.scripts)}
+        filtered_scripts = [script for script in self.scripts if script.name not in scripts_filter_out]
+        script_scores = {script.name: (script_score(script.name), script.order, script.name, original_index) for original_index, script in enumerate(filtered_scripts)}
 
-        return sorted(self.scripts, key=lambda x: script_scores[x.name])
+        return sorted(filtered_scripts, key=lambda x: script_scores[x.name])
 
     def setup_ui(self):
         inputs = []

modules/sd_emphasis.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+import torch
+
+
+class Emphasis:
+    """Emphasis class decides how to death with (emphasized:1.1) text in prompts"""
+
+    name: str = "Base"
+    description: str = ""
+
+    tokens: list[list[int]]
+    """tokens from the chunk of the prompt"""
+
+    multipliers: torch.Tensor
+    """tensor with multipliers, once for each token"""
+
+    z: torch.Tensor
+    """output of cond transformers network (CLIP)"""
+
+    def after_transformers(self):
+        """Called after cond transformers network has processed the chunk of the prompt; this function should modify self.z to apply the emphasis"""
+
+        pass
+
+
+class EmphasisNone(Emphasis):
+    name = "None"
+    description = "disable the mechanism entirely and treat (:.1.1) as literal characters"
+
+
+class EmphasisIgnore(Emphasis):
+    name = "Ignore"
+    description = "treat all empasised words as if they have no emphasis"
+
+
+class EmphasisOriginal(Emphasis):
+    name = "Original"
+    description = "the original emphasis implementation"
+
+    def after_transformers(self):
+        original_mean = self.z.mean()
+        self.z = self.z * self.multipliers.reshape(self.multipliers.shape + (1,)).expand(self.z.shape)
+
+        # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
+        new_mean = self.z.mean()
+        self.z = self.z * (original_mean / new_mean)
+
+
+class EmphasisOriginalNoNorm(EmphasisOriginal):
+    name = "No norm"
+    description = "same as original, but without normalization (seems to work better for SDXL)"
+
+    def after_transformers(self):
+        self.z = self.z * self.multipliers.reshape(self.multipliers.shape + (1,)).expand(self.z.shape)
+
+
+def get_current_option(emphasis_option_name):
+    return next(iter([x for x in options if x.name == emphasis_option_name]), EmphasisOriginal)
+
+
+def get_options_descriptions():
+    return ", ".join(f"{x.name}: {x.description}" for x in options)
+
+
+options = [
+    EmphasisNone,
+    EmphasisIgnore,
+    EmphasisOriginal,
+    EmphasisOriginalNoNorm,
+]

modules/sd_hijack_clip.py

@@ -3,7 +3,7 @@ from collections import namedtuple
 
 import torch
 
-from modules import prompt_parser, devices, sd_hijack
+from modules import prompt_parser, devices, sd_hijack, sd_emphasis
 from modules.shared import opts
 
 
@@ -23,7 +23,7 @@ class PromptChunk:
 
 PromptChunkFix = namedtuple('PromptChunkFix', ['offset', 'embedding'])
 """An object of this type is a marker showing that textual inversion embedding's vectors have to placed at offset in the prompt
-chunk. Thos objects are found in PromptChunk.fixes and, are placed into FrozenCLIPEmbedderWithCustomWordsBase.hijack.fixes, and finally
+chunk. Those objects are found in PromptChunk.fixes and, are placed into FrozenCLIPEmbedderWithCustomWordsBase.hijack.fixes, and finally
 are applied by sd_hijack.EmbeddingsWithFixes's forward function."""
 
 
@@ -66,7 +66,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
 
     def encode_with_transformers(self, tokens):
         """
-        converts a batch of token ids (in python lists) into a single tensor with numeric respresentation of those tokens;
+        converts a batch of token ids (in python lists) into a single tensor with numeric representation of those tokens;
         All python lists with tokens are assumed to have same length, usually 77.
         if input is a list with B elements and each element has T tokens, expected output shape is (B, T, C), where C depends on
         model - can be 768 and 1024.
@@ -88,7 +88,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
         Returns the list and the total number of tokens in the prompt.
         """
 
-        if opts.enable_emphasis:
+        if opts.emphasis != "None":
             parsed = prompt_parser.parse_prompt_attention(line)
         else:
             parsed = [[line, 1.0]]
@@ -136,7 +136,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
                 if token == self.comma_token:
                     last_comma = len(chunk.tokens)
 
-                # this is when we are at the end of alloted 75 tokens for the current chunk, and the current token is not a comma. opts.comma_padding_backtrack
+                # this is when we are at the end of allotted 75 tokens for the current chunk, and the current token is not a comma. opts.comma_padding_backtrack
                 # is a setting that specifies that if there is a comma nearby, the text after the comma should be moved out of this chunk and into the next.
                 elif opts.comma_padding_backtrack != 0 and len(chunk.tokens) == self.chunk_length and last_comma != -1 and len(chunk.tokens) - last_comma <= opts.comma_padding_backtrack:
                     break_location = last_comma + 1
@@ -206,7 +206,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
         be a multiple of 77; and C is dimensionality of each token - for SD1 it's 768, for SD2 it's 1024, and for SDXL it's 1280.
         An example shape returned by this function can be: (2, 77, 768).
         For SDXL, instead of returning one tensor avobe, it returns a tuple with two: the other one with shape (B, 1280) with pooled values.
-        Webui usually sends just one text at a time through this function - the only time when texts is an array with more than one elemenet
+        Webui usually sends just one text at a time through this function - the only time when texts is an array with more than one element
         is when you do prompt editing: "a picture of a [cat:dog:0.4] eating ice cream"
         """
 
@@ -230,7 +230,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
             for fixes in self.hijack.fixes:
                 for _position, embedding in fixes:
                     used_embeddings[embedding.name] = embedding
-
+            devices.torch_npu_set_device()
             z = self.process_tokens(tokens, multipliers)
             zs.append(z)
 
@@ -249,6 +249,9 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
                     hashes.append(self.hijack.extra_generation_params.get("TI hashes"))
                 self.hijack.extra_generation_params["TI hashes"] = ", ".join(hashes)
 
+        if any(x for x in texts if "(" in x or "[" in x) and opts.emphasis != "Original":
+            self.hijack.extra_generation_params["Emphasis"] = opts.emphasis
+
         if getattr(self.wrapped, 'return_pooled', False):
             return torch.hstack(zs), zs[0].pooled
         else:
@@ -274,12 +277,14 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
 
         pooled = getattr(z, 'pooled', None)
 
-        # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
-        batch_multipliers = torch.asarray(batch_multipliers).to(devices.device)
-        original_mean = z.mean()
-        z = z * batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
-        new_mean = z.mean()
-        z = z * (original_mean / new_mean)
+        emphasis = sd_emphasis.get_current_option(opts.emphasis)()
+        emphasis.tokens = remade_batch_tokens
+        emphasis.multipliers = torch.asarray(batch_multipliers).to(devices.device)
+        emphasis.z = z
+
+        emphasis.after_transformers()
+
+        z = emphasis.z
 
         if pooled is not None:
             z.pooled = pooled

modules/sd_hijack_clip_old.py

@@ -32,7 +32,7 @@ def process_text_old(self: sd_hijack_clip.FrozenCLIPEmbedderWithCustomWordsBase,
 
                 embedding, embedding_length_in_tokens = self.hijack.embedding_db.find_embedding_at_position(tokens, i)
 
-                mult_change = self.token_mults.get(token) if shared.opts.enable_emphasis else None
+                mult_change = self.token_mults.get(token) if shared.opts.emphasis != "None" else None
                 if mult_change is not None:
                     mult *= mult_change
                     i += 1

modules/sd_models.py

@@ -1,5 +1,5 @@
 import collections
-import os.path
+import os
 import sys
 import threading
 
@@ -7,7 +7,6 @@ import torch
 import re
 import safetensors.torch
 from omegaconf import OmegaConf, ListConfig
-from os import mkdir
 from urllib import request
 import ldm.modules.midas as midas
 
@@ -15,6 +14,7 @@ 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, cache, extra_networks, processing, lowvram, sd_hijack, patches
 from modules.timer import Timer
+from modules.shared import opts
 import tomesd
 import numpy as np
 
@@ -150,7 +150,7 @@ def list_models():
     if shared.cmd_opts.no_download_sd_model or cmd_ckpt != shared.sd_model_file or os.path.exists(cmd_ckpt):
         model_url = None
     else:
-        model_url = "https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors"
+        model_url = f"{shared.hf_endpoint}/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors"
 
     model_list = modelloader.load_models(model_path=model_path, model_url=model_url, command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt", ".safetensors"], download_name="v1-5-pruned-emaonly.safetensors", ext_blacklist=[".vae.ckpt", ".vae.safetensors"])
 
@@ -427,6 +427,8 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
         devices.dtype_unet = torch.float16
         timer.record("apply half()")
 
+    apply_alpha_schedule_override(model)
+
     for module in model.modules():
         if hasattr(module, 'fp16_weight'):
             del module.fp16_weight
@@ -505,7 +507,7 @@ def enable_midas_autodownload():
         path = midas.api.ISL_PATHS[model_type]
         if not os.path.exists(path):
             if not os.path.exists(midas_path):
-                mkdir(midas_path)
+                os.mkdir(midas_path)
 
             print(f"Downloading midas model weights for {model_type} to {path}")
             request.urlretrieve(midas_urls[model_type], path)
@@ -550,6 +552,48 @@ def repair_config(sd_config):
         sd_config.model.params.noise_aug_config.params.clip_stats_path = sd_config.model.params.noise_aug_config.params.clip_stats_path.replace("checkpoints/karlo_models", karlo_path)
 
 
+def rescale_zero_terminal_snr_abar(alphas_cumprod):
+    alphas_bar_sqrt = alphas_cumprod.sqrt()
+
+    # Store old values.
+    alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone()
+    alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone()
+
+    # Shift so the last timestep is zero.
+    alphas_bar_sqrt -= (alphas_bar_sqrt_T)
+
+    # Scale so the first timestep is back to the old value.
+    alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T)
+
+    # Convert alphas_bar_sqrt to betas
+    alphas_bar = alphas_bar_sqrt ** 2  # Revert sqrt
+    alphas_bar[-1] = 4.8973451890853435e-08
+    return alphas_bar
+
+
+def apply_alpha_schedule_override(sd_model, p=None):
+    """
+    Applies an override to the alpha schedule of the model according to settings.
+    - downcasts the alpha schedule to half precision
+    - rescales the alpha schedule to have zero terminal SNR
+    """
+
+    if not hasattr(sd_model, 'alphas_cumprod') or not hasattr(sd_model, 'alphas_cumprod_original'):
+        return
+
+    sd_model.alphas_cumprod = sd_model.alphas_cumprod_original.to(shared.device)
+
+    if opts.use_downcasted_alpha_bar:
+        if p is not None:
+            p.extra_generation_params['Downcast alphas_cumprod'] = opts.use_downcasted_alpha_bar
+        sd_model.alphas_cumprod = sd_model.alphas_cumprod.half().to(shared.device)
+
+    if opts.sd_noise_schedule == "Zero Terminal SNR":
+        if p is not None:
+            p.extra_generation_params['Noise Schedule'] = opts.sd_noise_schedule
+        sd_model.alphas_cumprod = rescale_zero_terminal_snr_abar(sd_model.alphas_cumprod).to(shared.device)
+
+
 sd1_clip_weight = 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight'
 sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight'
 sdxl_clip_weight = 'conditioner.embedders.1.model.ln_final.weight'
@@ -739,9 +783,16 @@ def reuse_model_from_already_loaded(sd_model, checkpoint_info, timer):
     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).
+    Additionally deletes loaded models that are over the limit set in settings (sd_checkpoints_limit).
     """
 
+    if sd_model is not None and sd_model.sd_checkpoint_info.filename == checkpoint_info.filename:
+        return sd_model
+
+    if shared.opts.sd_checkpoints_keep_in_cpu:
+        send_model_to_cpu(sd_model)
+        timer.record("send model to cpu")
+
     already_loaded = None
     for i in reversed(range(len(model_data.loaded_sd_models))):
         loaded_model = model_data.loaded_sd_models[i]
@@ -751,14 +802,10 @@ def reuse_model_from_already_loaded(sd_model, checkpoint_info, timer):
 
         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()
+            del model_data.loaded_sd_models[i]
             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")

modules/sd_models_xl.py

@@ -13,8 +13,8 @@ def get_learned_conditioning(self: sgm.models.diffusion.DiffusionEngine, batch:
     for embedder in self.conditioner.embedders:
         embedder.ucg_rate = 0.0
 
-    width = getattr(batch, 'width', 1024)
-    height = getattr(batch, 'height', 1024)
+    width = getattr(batch, 'width', 1024) or 1024
+    height = getattr(batch, 'height', 1024) or 1024
     is_negative_prompt = getattr(batch, 'is_negative_prompt', False)
     aesthetic_score = shared.opts.sdxl_refiner_low_aesthetic_score if is_negative_prompt else shared.opts.sdxl_refiner_high_aesthetic_score
 

modules/sd_samplers.py

@@ -1,7 +1,12 @@
-from modules import sd_samplers_kdiffusion, sd_samplers_timesteps, sd_samplers_lcm, shared
+from __future__ import annotations
+
+import functools
+
+from modules import sd_samplers_kdiffusion, sd_samplers_timesteps, sd_samplers_lcm, shared, sd_samplers_common, sd_schedulers
 
 # 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
+samples_to_image_grid = sd_samplers_common.samples_to_image_grid
+sample_to_image = sd_samplers_common.sample_to_image
 
 all_samplers = [
     *sd_samplers_kdiffusion.samplers_data_k_diffusion,
@@ -10,8 +15,8 @@ all_samplers = [
 ]
 all_samplers_map = {x.name: x for x in all_samplers}
 
-samplers = []
-samplers_for_img2img = []
+samplers: list[sd_samplers_common.SamplerData] = []
+samplers_for_img2img: list[sd_samplers_common.SamplerData] = []
 samplers_map = {}
 samplers_hidden = {}
 
@@ -57,4 +62,64 @@ def visible_sampler_names():
     return [x.name for x in samplers if x.name not in samplers_hidden]
 
 
+def visible_samplers():
+    return [x for x in samplers if x.name not in samplers_hidden]
+
+
+def get_sampler_from_infotext(d: dict):
+    return get_sampler_and_scheduler(d.get("Sampler"), d.get("Schedule type"))[0]
+
+
+def get_scheduler_from_infotext(d: dict):
+    return get_sampler_and_scheduler(d.get("Sampler"), d.get("Schedule type"))[1]
+
+
+def get_hr_sampler_and_scheduler(d: dict):
+    hr_sampler = d.get("Hires sampler", "Use same sampler")
+    sampler = d.get("Sampler") if hr_sampler == "Use same sampler" else hr_sampler
+
+    hr_scheduler = d.get("Hires schedule type", "Use same scheduler")
+    scheduler = d.get("Schedule type") if hr_scheduler == "Use same scheduler" else hr_scheduler
+
+    sampler, scheduler = get_sampler_and_scheduler(sampler, scheduler)
+
+    sampler = sampler if sampler != d.get("Sampler") else "Use same sampler"
+    scheduler = scheduler if scheduler != d.get("Schedule type") else "Use same scheduler"
+
+    return sampler, scheduler
+
+
+def get_hr_sampler_from_infotext(d: dict):
+    return get_hr_sampler_and_scheduler(d)[0]
+
+
+def get_hr_scheduler_from_infotext(d: dict):
+    return get_hr_sampler_and_scheduler(d)[1]
+
+
+@functools.cache
+def get_sampler_and_scheduler(sampler_name, scheduler_name):
+    default_sampler = samplers[0]
+    found_scheduler = sd_schedulers.schedulers_map.get(scheduler_name, sd_schedulers.schedulers[0])
+
+    name = sampler_name or default_sampler.name
+
+    for scheduler in sd_schedulers.schedulers:
+        name_options = [scheduler.label, scheduler.name, *(scheduler.aliases or [])]
+
+        for name_option in name_options:
+            if name.endswith(" " + name_option):
+                found_scheduler = scheduler
+                name = name[0:-(len(name_option) + 1)]
+                break
+
+    sampler = all_samplers_map.get(name, default_sampler)
+
+    # revert back to Automatic if it's the default scheduler for the selected sampler
+    if sampler.options.get('scheduler', None) == found_scheduler.name:
+        found_scheduler = sd_schedulers.schedulers[0]
+
+    return sampler.name, found_scheduler.label
+
+
 set_samplers()

modules/sd_samplers_cfg_denoiser.py

@@ -53,6 +53,7 @@ class CFGDenoiser(torch.nn.Module):
         self.step = 0
         self.image_cfg_scale = None
         self.padded_cond_uncond = False
+        self.padded_cond_uncond_v0 = False
         self.sampler = sampler
         self.model_wrap = None
         self.p = None
@@ -91,11 +92,67 @@ class CFGDenoiser(torch.nn.Module):
         self.sampler.sampler_extra_args['cond'] = c
         self.sampler.sampler_extra_args['uncond'] = uc
 
+    def pad_cond_uncond(self, cond, uncond):
+        empty = shared.sd_model.cond_stage_model_empty_prompt
+        num_repeats = (cond.shape[1] - uncond.shape[1]) // empty.shape[1]
+
+        if num_repeats < 0:
+            cond = pad_cond(cond, -num_repeats, empty)
+            self.padded_cond_uncond = True
+        elif num_repeats > 0:
+            uncond = pad_cond(uncond, num_repeats, empty)
+            self.padded_cond_uncond = True
+
+        return cond, uncond
+
+    def pad_cond_uncond_v0(self, cond, uncond):
+        """
+        Pads the 'uncond' tensor to match the shape of the 'cond' tensor.
+
+        If 'uncond' is a dictionary, it is assumed that the 'crossattn' key holds the tensor to be padded.
+        If 'uncond' is a tensor, it is padded directly.
+
+        If the number of columns in 'uncond' is less than the number of columns in 'cond', the last column of 'uncond'
+        is repeated to match the number of columns in 'cond'.
+
+        If the number of columns in 'uncond' is greater than the number of columns in 'cond', 'uncond' is truncated
+        to match the number of columns in 'cond'.
+
+        Args:
+            cond (torch.Tensor or DictWithShape): The condition tensor to match the shape of 'uncond'.
+            uncond (torch.Tensor or DictWithShape): The tensor to be padded, or a dictionary containing the tensor to be padded.
+
+        Returns:
+            tuple: A tuple containing the 'cond' tensor and the padded 'uncond' tensor.
+
+        Note:
+            This is the padding that was always used in DDIM before version 1.6.0
+        """
+
+        is_dict_cond = isinstance(uncond, dict)
+        uncond_vec = uncond['crossattn'] if is_dict_cond else uncond
+
+        if uncond_vec.shape[1] < cond.shape[1]:
+            last_vector = uncond_vec[:, -1:]
+            last_vector_repeated = last_vector.repeat([1, cond.shape[1] - uncond_vec.shape[1], 1])
+            uncond_vec = torch.hstack([uncond_vec, last_vector_repeated])
+            self.padded_cond_uncond_v0 = True
+        elif uncond_vec.shape[1] > cond.shape[1]:
+            uncond_vec = uncond_vec[:, :cond.shape[1]]
+            self.padded_cond_uncond_v0 = True
+
+        if is_dict_cond:
+            uncond['crossattn'] = uncond_vec
+        else:
+            uncond = uncond_vec
+
+        return cond, uncond
+
     def forward(self, x, sigma, uncond, cond, cond_scale, s_min_uncond, image_cond):
         if state.interrupted or state.skipped:
             raise sd_samplers_common.InterruptedException
 
-        if sd_samplers_common.apply_refiner(self):
+        if sd_samplers_common.apply_refiner(self, sigma):
             cond = self.sampler.sampler_extra_args['cond']
             uncond = self.sampler.sampler_extra_args['uncond']
 
@@ -162,16 +219,11 @@ class CFGDenoiser(torch.nn.Module):
             sigma_in = sigma_in[:-batch_size]
 
         self.padded_cond_uncond = False
-        if shared.opts.pad_cond_uncond and tensor.shape[1] != uncond.shape[1]:
-            empty = shared.sd_model.cond_stage_model_empty_prompt
-            num_repeats = (tensor.shape[1] - uncond.shape[1]) // empty.shape[1]
-
-            if num_repeats < 0:
-                tensor = pad_cond(tensor, -num_repeats, empty)
-                self.padded_cond_uncond = True
-            elif num_repeats > 0:
-                uncond = pad_cond(uncond, num_repeats, empty)
-                self.padded_cond_uncond = True
+        self.padded_cond_uncond_v0 = False
+        if shared.opts.pad_cond_uncond_v0 and tensor.shape[1] != uncond.shape[1]:
+            tensor, uncond = self.pad_cond_uncond_v0(tensor, uncond)
+        elif shared.opts.pad_cond_uncond and tensor.shape[1] != uncond.shape[1]:
+            tensor, uncond = self.pad_cond_uncond(tensor, uncond)
 
         if tensor.shape[1] == uncond.shape[1] or skip_uncond:
             if is_edit_model:

modules/sd_samplers_common.py

@@ -155,8 +155,19 @@ def replace_torchsde_browinan():
 replace_torchsde_browinan()
 
 
-def apply_refiner(cfg_denoiser):
-    completed_ratio = cfg_denoiser.step / cfg_denoiser.total_steps
+def apply_refiner(cfg_denoiser, sigma=None):
+    if opts.refiner_switch_by_sample_steps or sigma is None:
+        completed_ratio = cfg_denoiser.step / cfg_denoiser.total_steps
+        cfg_denoiser.p.extra_generation_params["Refiner switch by sampling steps"] = True
+
+    else:
+        # torch.max(sigma) only to handle rare case where we might have different sigmas in the same batch
+        try:
+            timestep = torch.argmin(torch.abs(cfg_denoiser.inner_model.sigmas - torch.max(sigma)))
+        except AttributeError:  # for samplers that don't use sigmas (DDIM) sigma is actually the timestep
+            timestep = torch.max(sigma).to(dtype=int)
+        completed_ratio = (999 - timestep) / 1000
+
     refiner_switch_at = cfg_denoiser.p.refiner_switch_at
     refiner_checkpoint_info = cfg_denoiser.p.refiner_checkpoint_info
 
@@ -335,3 +346,10 @@ class Sampler:
 
     def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
         raise NotImplementedError()
+
+    def add_infotext(self, p):
+        if self.model_wrap_cfg.padded_cond_uncond:
+            p.extra_generation_params["Pad conds"] = True
+
+        if self.model_wrap_cfg.padded_cond_uncond_v0:
+            p.extra_generation_params["Pad conds v0"] = True

modules/sd_samplers_kdiffusion.py

@@ -1,7 +1,7 @@
 import torch
 import inspect
 import k_diffusion.sampling
-from modules import sd_samplers_common, sd_samplers_extra, sd_samplers_cfg_denoiser
+from modules import sd_samplers_common, sd_samplers_extra, sd_samplers_cfg_denoiser, sd_schedulers
 from modules.sd_samplers_cfg_denoiser import CFGDenoiser  # noqa: F401
 from modules.script_callbacks import ExtraNoiseParams, extra_noise_callback
 
@@ -9,32 +9,20 @@ from modules.shared import opts
 import modules.shared as shared
 
 samplers_k_diffusion = [
-    ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
-    ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras', "second_order": True, "brownian_noise": True}),
-    ('DPM++ 2M SDE Exponential', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_exp'], {'scheduler': 'exponential', "brownian_noise": True}),
-    ('DPM++ 2M SDE Karras', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_ka'], {'scheduler': 'karras', "brownian_noise": True}),
+    ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {'scheduler': 'karras'}),
+    ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {'scheduler': 'karras', "second_order": True, "brownian_noise": True}),
+    ('DPM++ 2M SDE', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde'], {'scheduler': 'exponential', "brownian_noise": True}),
+    ('DPM++ 2M SDE Heun', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun'], {'scheduler': 'exponential', "brownian_noise": True, "solver_type": "heun"}),
+    ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {'scheduler': 'karras', "uses_ensd": True, "second_order": True}),
+    ('DPM++ 3M SDE', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde'], {'scheduler': 'exponential', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
     ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {"uses_ensd": True}),
     ('Euler', 'sample_euler', ['k_euler'], {}),
     ('LMS', 'sample_lms', ['k_lms'], {}),
     ('Heun', 'sample_heun', ['k_heun'], {"second_order": True}),
-    ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True, "second_order": True}),
-    ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
-    ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {"uses_ensd": True, "second_order": True}),
-    ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
-    ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {"second_order": True, "brownian_noise": True}),
-    ('DPM++ 2M SDE', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_ka'], {"brownian_noise": True}),
-    ('DPM++ 2M SDE Heun', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun'], {"brownian_noise": True, "solver_type": "heun"}),
-    ('DPM++ 2M SDE Heun Karras', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun_ka'], {'scheduler': 'karras', "brownian_noise": True, "solver_type": "heun"}),
-    ('DPM++ 2M SDE Heun Exponential', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_heun_exp'], {'scheduler': 'exponential', "brownian_noise": True, "solver_type": "heun"}),
-    ('DPM++ 3M SDE', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde'], {'discard_next_to_last_sigma': True, "brownian_noise": True}),
-    ('DPM++ 3M SDE Karras', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
-    ('DPM++ 3M SDE Exponential', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde_exp'], {'scheduler': 'exponential', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
+    ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "second_order": True}),
+    ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
     ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {"uses_ensd": True}),
     ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {"uses_ensd": True}),
-    ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
-    ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
-    ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}),
-    ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras', "uses_ensd": True, "second_order": True}),
     ('Restart', sd_samplers_extra.restart_sampler, ['restart'], {'scheduler': 'karras', "second_order": True}),
 ]
 
@@ -58,12 +46,7 @@ sampler_extra_params = {
 }
 
 k_diffusion_samplers_map = {x.name: x for x in samplers_data_k_diffusion}
-k_diffusion_scheduler = {
-    'Automatic': None,
-    'karras': k_diffusion.sampling.get_sigmas_karras,
-    'exponential': k_diffusion.sampling.get_sigmas_exponential,
-    'polyexponential': k_diffusion.sampling.get_sigmas_polyexponential
-}
+k_diffusion_scheduler = {x.name: x.function for x in sd_schedulers.schedulers}
 
 
 class CFGDenoiserKDiffusion(sd_samplers_cfg_denoiser.CFGDenoiser):
@@ -96,42 +79,43 @@ class KDiffusionSampler(sd_samplers_common.Sampler):
 
         steps += 1 if discard_next_to_last_sigma else 0
 
+        scheduler_name = (p.hr_scheduler if p.is_hr_pass else p.scheduler) or 'Automatic'
+        if scheduler_name == 'Automatic':
+            scheduler_name = self.config.options.get('scheduler', None)
+
+        scheduler = sd_schedulers.schedulers_map.get(scheduler_name)
+
+        m_sigma_min, m_sigma_max = self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item()
+        sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (m_sigma_min, m_sigma_max)
+
         if p.sampler_noise_scheduler_override:
             sigmas = p.sampler_noise_scheduler_override(steps)
-        elif opts.k_sched_type != "Automatic":
-            m_sigma_min, m_sigma_max = (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
-            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (m_sigma_min, m_sigma_max)
-            sigmas_kwargs = {
-                'sigma_min': sigma_min,
-                'sigma_max': sigma_max,
-            }
+        elif scheduler is None or scheduler.function is None:
+            sigmas = self.model_wrap.get_sigmas(steps)
+        else:
+            sigmas_kwargs = {'sigma_min': sigma_min, 'sigma_max': sigma_max}
 
-            sigmas_func = k_diffusion_scheduler[opts.k_sched_type]
-            p.extra_generation_params["Schedule type"] = opts.k_sched_type
+            if scheduler.label != 'Automatic' and not p.is_hr_pass:
+                p.extra_generation_params["Schedule type"] = scheduler.label
+            elif scheduler.label != p.extra_generation_params.get("Schedule type"):
+                p.extra_generation_params["Hires schedule type"] = scheduler.label
 
-            if opts.sigma_min != m_sigma_min and opts.sigma_min != 0:
+            if opts.sigma_min != 0 and opts.sigma_min != m_sigma_min:
                 sigmas_kwargs['sigma_min'] = opts.sigma_min
                 p.extra_generation_params["Schedule min sigma"] = opts.sigma_min
-            if opts.sigma_max != m_sigma_max and opts.sigma_max != 0:
+
+            if opts.sigma_max != 0 and opts.sigma_max != m_sigma_max:
                 sigmas_kwargs['sigma_max'] = opts.sigma_max
                 p.extra_generation_params["Schedule max sigma"] = opts.sigma_max
 
-            default_rho = 1. if opts.k_sched_type == "polyexponential" else 7.
-
-            if opts.k_sched_type != 'exponential' and opts.rho != 0 and opts.rho != default_rho:
+            if scheduler.default_rho != -1 and opts.rho != 0 and opts.rho != scheduler.default_rho:
                 sigmas_kwargs['rho'] = opts.rho
                 p.extra_generation_params["Schedule rho"] = opts.rho
 
-            sigmas = sigmas_func(n=steps, **sigmas_kwargs, device=shared.device)
-        elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
-            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
+            if scheduler.need_inner_model:
+                sigmas_kwargs['inner_model'] = self.model_wrap
 
-            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
-        elif self.config is not None and self.config.options.get('scheduler', None) == 'exponential':
-            m_sigma_min, m_sigma_max = (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
-            sigmas = k_diffusion.sampling.get_sigmas_exponential(n=steps, sigma_min=m_sigma_min, sigma_max=m_sigma_max, device=shared.device)
-        else:
-            sigmas = self.model_wrap.get_sigmas(steps)
+            sigmas = scheduler.function(n=steps, **sigmas_kwargs, device=shared.device)
 
         if discard_next_to_last_sigma:
             sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])
@@ -187,8 +171,7 @@ class KDiffusionSampler(sd_samplers_common.Sampler):
 
         samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
 
-        if self.model_wrap_cfg.padded_cond_uncond:
-            p.extra_generation_params["Pad conds"] = True
+        self.add_infotext(p)
 
         return samples
 
@@ -234,8 +217,7 @@ class KDiffusionSampler(sd_samplers_common.Sampler):
 
         samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
 
-        if self.model_wrap_cfg.padded_cond_uncond:
-            p.extra_generation_params["Pad conds"] = True
+        self.add_infotext(p)
 
         return samples
 

modules/sd_samplers_timesteps.py

@@ -133,8 +133,7 @@ class CompVisSampler(sd_samplers_common.Sampler):
 
         samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
 
-        if self.model_wrap_cfg.padded_cond_uncond:
-            p.extra_generation_params["Pad conds"] = True
+        self.add_infotext(p)
 
         return samples
 
@@ -158,8 +157,7 @@ class CompVisSampler(sd_samplers_common.Sampler):
         }
         samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
 
-        if self.model_wrap_cfg.padded_cond_uncond:
-            p.extra_generation_params["Pad conds"] = True
+        self.add_infotext(p)
 
         return samples
 

modules/sd_schedulers.py

@@ -0,0 +1,43 @@
+import dataclasses
+
+import torch
+
+import k_diffusion
+
+
+@dataclasses.dataclass
+class Scheduler:
+    name: str
+    label: str
+    function: any
+
+    default_rho: float = -1
+    need_inner_model: bool = False
+    aliases: list = None
+
+
+def uniform(n, sigma_min, sigma_max, inner_model, device):
+    return inner_model.get_sigmas(n)
+
+
+def sgm_uniform(n, sigma_min, sigma_max, inner_model, device):
+    start = inner_model.sigma_to_t(torch.tensor(sigma_max))
+    end = inner_model.sigma_to_t(torch.tensor(sigma_min))
+    sigs = [
+        inner_model.t_to_sigma(ts)
+        for ts in torch.linspace(start, end, n + 1)[:-1]
+    ]
+    sigs += [0.0]
+    return torch.FloatTensor(sigs).to(device)
+
+
+schedulers = [
+    Scheduler('automatic', 'Automatic', None),
+    Scheduler('uniform', 'Uniform', uniform, need_inner_model=True),
+    Scheduler('karras', 'Karras', k_diffusion.sampling.get_sigmas_karras, default_rho=7.0),
+    Scheduler('exponential', 'Exponential', k_diffusion.sampling.get_sigmas_exponential),
+    Scheduler('polyexponential', 'Polyexponential', k_diffusion.sampling.get_sigmas_polyexponential, default_rho=1.0),
+    Scheduler('sgm_uniform', 'SGM Uniform', sgm_uniform, need_inner_model=True, aliases=["SGMUniform"]),
+]
+
+schedulers_map = {**{x.name: x for x in schedulers}, **{x.label: x for x in schedulers}}

modules/shared.py

@@ -1,3 +1,4 @@
+import os
 import sys
 
 import gradio as gr
@@ -5,21 +6,25 @@ import gradio as gr
 from modules import shared_cmd_options, shared_gradio_themes, options, shared_items, sd_models_types
 from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir  # noqa: F401
 from modules import util
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from modules import shared_state, styles, interrogate, shared_total_tqdm, memmon
 
 cmd_opts = shared_cmd_options.cmd_opts
 parser = shared_cmd_options.parser
 
 batch_cond_uncond = True  # old field, unused now in favor of shared.opts.batch_cond_uncond
 parallel_processing_allowed = True
-styles_filename = cmd_opts.styles_file
+styles_filename = cmd_opts.styles_file = cmd_opts.styles_file if len(cmd_opts.styles_file) > 0 else [os.path.join(data_path, 'styles.csv')]
 config_filename = cmd_opts.ui_settings_file
 hide_dirs = {"visible": not cmd_opts.hide_ui_dir_config}
 
-demo = None
+demo: gr.Blocks = None
 
-device = None
+device: str = None
 
-weight_load_location = None
+weight_load_location: str = None
 
 xformers_available = False
 
@@ -27,22 +32,22 @@ hypernetworks = {}
 
 loaded_hypernetworks = []
 
-state = None
+state: 'shared_state.State' = None
 
-prompt_styles = None
+prompt_styles: 'styles.StyleDatabase' = None
 
-interrogator = None
+interrogator: 'interrogate.InterrogateModels' = None
 
 face_restorers = []
 
-options_templates = None
-opts = None
-restricted_opts = None
+options_templates: dict = None
+opts: options.Options = None
+restricted_opts: set[str] = None
 
 sd_model: sd_models_types.WebuiSdModel = None
 
-settings_components = None
-"""assinged from ui.py, a mapping on setting names to gradio components repsponsible for those settings"""
+settings_components: dict = None
+"""assigned from ui.py, a mapping on setting names to gradio components repsponsible for those settings"""
 
 tab_names = []
 
@@ -64,9 +69,9 @@ progress_print_out = sys.stdout
 
 gradio_theme = gr.themes.Base()
 
-total_tqdm = None
+total_tqdm: 'shared_total_tqdm.TotalTQDM' = None
 
-mem_mon = None
+mem_mon: 'memmon.MemUsageMonitor' = None
 
 options_section = options.options_section
 OptionInfo = options.OptionInfo
@@ -85,3 +90,5 @@ list_checkpoint_tiles = shared_items.list_checkpoint_tiles
 refresh_checkpoints = shared_items.refresh_checkpoints
 list_samplers = shared_items.list_samplers
 reload_hypernetworks = shared_items.reload_hypernetworks
+
+hf_endpoint = os.getenv('HF_ENDPOINT', 'https://huggingface.co')

modules/shared_items.py

@@ -1,5 +1,8 @@
+import html
 import sys
 
+from modules import script_callbacks, scripts, ui_components
+from modules.options import OptionHTML, OptionInfo
 from modules.shared_cmd_options import cmd_opts
 
 
@@ -118,6 +121,45 @@ def ui_reorder_categories():
     yield "scripts"
 
 
+def callbacks_order_settings():
+    options = {
+        "sd_vae_explanation": OptionHTML("""
+    For categories below, callbacks added to dropdowns happen before others, in order listed.
+    """),
+
+    }
+
+    callback_options = {}
+
+    for category, _ in script_callbacks.enumerate_callbacks():
+        callback_options[category] = script_callbacks.ordered_callbacks(category, enable_user_sort=False)
+
+    for method_name in scripts.scripts_txt2img.callback_names:
+        callback_options["script_" + method_name] = scripts.scripts_txt2img.create_ordered_callbacks_list(method_name, enable_user_sort=False)
+
+    for method_name in scripts.scripts_img2img.callback_names:
+        callbacks = callback_options.get("script_" + method_name, [])
+
+        for addition in scripts.scripts_img2img.create_ordered_callbacks_list(method_name, enable_user_sort=False):
+            if any(x.name == addition.name for x in callbacks):
+                continue
+
+            callbacks.append(addition)
+
+        callback_options["script_" + method_name] = callbacks
+
+    for category, callbacks in callback_options.items():
+        if not callbacks:
+            continue
+
+        option_info = OptionInfo([], f"{category} callback priority", ui_components.DropdownMulti, {"choices": [x.name for x in callbacks]})
+        option_info.needs_restart()
+        option_info.html("<div class='info'>Default order: <ol>" + "".join(f"<li>{html.escape(x.name)}</li>\n" for x in callbacks) + "</ol></div>")
+        options['prioritized_callbacks_' + category] = option_info
+
+    return options
+
+
 class Shared(sys.modules[__name__].__class__):
     """
     this class is here to provide sd_model field as a property, so that it can be created and loaded on demand rather than

modules/shared_options.py

@@ -1,7 +1,7 @@
 import os
 import gradio as gr
 
-from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes, util
+from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes, util, sd_emphasis
 from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir, default_output_dir  # noqa: F401
 from modules.shared_cmd_options import cmd_opts
 from modules.options import options_section, OptionInfo, OptionHTML, categories
@@ -19,7 +19,9 @@ restricted_opts = {
     "outdir_grids",
     "outdir_txt2img_grids",
     "outdir_save",
-    "outdir_init_images"
+    "outdir_init_images",
+    "temp_dir",
+    "clean_temp_dir_at_start",
 }
 
 categories.register_category("saving", "Saving images")
@@ -101,6 +103,7 @@ options_templates.update(options_section(('upscaling', "Upscaling", "postprocess
     "DAT_tile": OptionInfo(192, "Tile size for DAT upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}).info("0 = no tiling"),
     "DAT_tile_overlap": OptionInfo(8, "Tile overlap for DAT upscalers.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}).info("Low values = visible seam"),
     "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in shared.sd_upscalers]}),
+    "set_scale_by_when_changing_upscaler": OptionInfo(False, "Automatically set the Scale by factor based on the name of the selected Upscaler."),
 }))
 
 options_templates.update(options_section(('face-restoration', "Face restoration", "postprocessing"), {
@@ -154,7 +157,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion", "sd"), {
     "sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}).info("obsolete; set to 0 and use the two settings above instead"),
     "sd_unet": OptionInfo("Automatic", "SD Unet", gr.Dropdown, lambda: {"choices": shared_items.sd_unet_items()}, refresh=shared_items.refresh_unet_list).info("choose Unet model: Automatic = use one with same filename as checkpoint; None = use Unet from checkpoint"),
     "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds").needs_reload_ui(),
-    "enable_emphasis": OptionInfo(True, "Enable emphasis").info("use (text) to make model pay more attention to text and [text] to make it pay less attention"),
+    "emphasis": OptionInfo("Original", "Emphasis mode", gr.Radio, lambda: {"choices": [x.name for x in sd_emphasis.options]}, infotext="Emphasis").info("makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; " + sd_emphasis.get_options_descriptions()),
     "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
     "comma_padding_backtrack": OptionInfo(20, "Prompt word wrap length limit", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1}).info("in tokens - for texts shorter than specified, if they don't fit into 75 token limit, move them to the next 75 token chunk"),
     "CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}, infotext="Clip skip").link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#clip-skip").info("ignore last layers of CLIP network; 1 ignores none, 2 ignores one layer"),
@@ -201,6 +204,7 @@ options_templates.update(options_section(('img2img', "img2img", "sd"), {
     "return_mask": OptionInfo(False, "For inpainting, include the greyscale mask in results for web"),
     "return_mask_composite": OptionInfo(False, "For inpainting, include masked composite in results for web"),
     "img2img_batch_show_results_limit": OptionInfo(32, "Show the first N batch img2img results in UI", gr.Slider, {"minimum": -1, "maximum": 1000, "step": 1}).info('0: disable, -1: show all images. Too many images can cause lag'),
+    "overlay_inpaint": OptionInfo(True, "Overlay original for inpaint").info("when inpainting, overlay the original image over the areas that weren't inpainted."),
 }))
 
 options_templates.update(options_section(('optimizations', "Optimizations", "sd"), {
@@ -209,9 +213,10 @@ options_templates.update(options_section(('optimizations', "Optimizations", "sd"
     "token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"),
     "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"),
     "token_merging_ratio_hr": OptionInfo(0.0, "Token merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio hr').info("only applies if non-zero and overrides above"),
-    "pad_cond_uncond": OptionInfo(False, "Pad prompt/negative prompt to be same length", infotext='Pad conds').info("improves performance when prompt and negative prompt have different lengths; changes seeds"),
+    "pad_cond_uncond": OptionInfo(False, "Pad prompt/negative prompt", infotext='Pad conds').info("improves performance when prompt and negative prompt have different lengths; changes seeds"),
+    "pad_cond_uncond_v0": OptionInfo(False, "Pad prompt/negative prompt (v0)", infotext='Pad conds v0').info("alternative implementation for the above; used prior to 1.6.0 for DDIM sampler; overrides the above if set; WARNING: truncates negative prompt if it's too long; changes seeds"),
     "persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("do not recalculate conds from prompts if prompts have not changed since previous calculation"),
-    "batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"),
+    "batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond commandline argument"),
     "fp8_storage": OptionInfo("Disable", "FP8 weight", gr.Radio, {"choices": ["Disable", "Enable for SDXL", "Enable"]}).info("Use FP8 to store Linear/Conv layers' weight. Require pytorch>=2.1.0."),
     "cache_fp16_weight": OptionInfo(False, "Cache FP16 weight for LoRA").info("Cache fp16 weight when enabling FP8, will increase the quality of LoRA. Use more system ram."),
 }))
@@ -225,7 +230,8 @@ options_templates.update(options_section(('compatibility', "Compatibility", "sd"
     "dont_fix_second_order_samplers_schedule": OptionInfo(False, "Do not fix prompt schedule for second order samplers."),
     "hires_fix_use_firstpass_conds": OptionInfo(False, "For hires fix, calculate conds of second pass using extra networks of first pass."),
     "use_old_scheduling": OptionInfo(False, "Use old prompt editing timelines.", infotext="Old prompt editing timelines").info("For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps"),
-    "use_downcasted_alpha_bar": OptionInfo(False, "Downcast model alphas_cumprod to fp16 before sampling. For reproducing old seeds.", infotext="Downcast alphas_cumprod")
+    "use_downcasted_alpha_bar": OptionInfo(False, "Downcast model alphas_cumprod to fp16 before sampling. For reproducing old seeds.", infotext="Downcast alphas_cumprod"),
+    "refiner_switch_by_sample_steps": OptionInfo(False, "Switch to refiner by sampling steps instead of model timesteps. Old behavior for refiner.", infotext="Refiner switch by sampling steps")
 }))
 
 options_templates.update(options_section(('interrogate', "Interrogate"), {
@@ -252,8 +258,12 @@ options_templates.update(options_section(('extra_networks', "Extra Networks", "s
     "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks").info("in pixels"),
     "extra_networks_card_text_scale": OptionInfo(1.0, "Card text scale", gr.Slider, {"minimum": 0.0, "maximum": 2.0, "step": 0.01}).info("1 = original size"),
     "extra_networks_card_show_desc": OptionInfo(True, "Show description on card"),
+    "extra_networks_card_description_is_html": OptionInfo(False, "Treat card description as HTML"),
     "extra_networks_card_order_field": OptionInfo("Path", "Default order field for Extra Networks cards", gr.Dropdown, {"choices": ['Path', 'Name', 'Date Created', 'Date Modified']}).needs_reload_ui(),
     "extra_networks_card_order": OptionInfo("Ascending", "Default order for Extra Networks cards", gr.Dropdown, {"choices": ['Ascending', 'Descending']}).needs_reload_ui(),
+    "extra_networks_tree_view_style": OptionInfo("Dirs", "Extra Networks directory view style", gr.Radio, {"choices": ["Tree", "Dirs"]}).needs_reload_ui(),
+    "extra_networks_tree_view_default_enabled": OptionInfo(True, "Show the Extra Networks directory view by default").needs_reload_ui(),
+    "extra_networks_tree_view_default_width": OptionInfo(180, "Default width for the Extra Networks directory tree view", gr.Number).needs_reload_ui(),
     "extra_networks_add_text_separator": OptionInfo(" ", "Extra networks separator").info("extra text to add before <...> when adding extra network to prompt"),
     "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order").needs_reload_ui(),
     "textual_inversion_print_at_load": OptionInfo(False, "Print a list of Textual Inversion embeddings when loading model"),
@@ -267,7 +277,8 @@ options_templates.update(options_section(('ui_prompt_editing', "Prompt editing",
     "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Word delimiters when editing the prompt with Ctrl+up/down"),
     "keyedit_delimiters_whitespace": OptionInfo(["Tab", "Carriage Return", "Line Feed"], "Ctrl+up/down whitespace delimiters", gr.CheckboxGroup, lambda: {"choices": ["Tab", "Carriage Return", "Line Feed"]}),
     "keyedit_move": OptionInfo(True, "Alt+left/right moves prompt elements"),
-    "disable_token_counters": OptionInfo(False, "Disable prompt token counters").needs_reload_ui(),
+    "disable_token_counters": OptionInfo(False, "Disable prompt token counters"),
+    "include_styles_into_token_counters": OptionInfo(True, "Count tokens of enabled styles").info("When calculating how many tokens the prompt has, also consider tokens added by enabled styles."),
 }))
 
 options_templates.update(options_section(('ui_gallery', "Gallery", "ui"), {
@@ -280,6 +291,7 @@ options_templates.update(options_section(('ui_gallery', "Gallery", "ui"), {
     "sd_webui_modal_lightbox_icon_opacity": OptionInfo(1, "Full page image viewer: control icon unfocused opacity", gr.Slider, {"minimum": 0.0, "maximum": 1, "step": 0.01}, onchange=shared.reload_gradio_theme).info('for mouse only').needs_reload_ui(),
     "sd_webui_modal_lightbox_toolbar_opacity": OptionInfo(0.9, "Full page image viewer: tool bar opacity", gr.Slider, {"minimum": 0.0, "maximum": 1, "step": 0.01}, onchange=shared.reload_gradio_theme).info('for mouse only').needs_reload_ui(),
     "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("can be any valid CSS value, for example 768px or 20em").needs_reload_ui(),
+    "open_dir_button_choice": OptionInfo("Subdirectory", "What directory the [📂] button opens", gr.Radio, {"choices": ["Output Root", "Subdirectory", "Subdirectory (even temp dir)"]}),
 }))
 
 options_templates.update(options_section(('ui_alternatives', "UI alternatives", "ui"), {
@@ -305,6 +317,8 @@ options_templates.update(options_section(('ui', "User interface", "ui"), {
     "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
     "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
     "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),
+    "enable_reloading_ui_scripts": OptionInfo(False, "Reload UI scripts when using Reload UI option").info("useful for developing: if you make changes to UI scripts code, it is applied when the UI is reloded."),
+
 }))
 
 
@@ -356,13 +370,12 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
     's_tmin':  OptionInfo(0.0, "sigma tmin",  gr.Slider, {"minimum": 0.0, "maximum": 10.0, "step": 0.01}, infotext='Sigma tmin').info('enable stochasticity; start value of the sigma range; only applies to Euler, Heun, and DPM2'),
     's_tmax':  OptionInfo(0.0, "sigma tmax",  gr.Slider, {"minimum": 0.0, "maximum": 999.0, "step": 0.01}, infotext='Sigma tmax').info("0 = inf; end value of the sigma range; only applies to Euler, Heun, and DPM2"),
     's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.1, "step": 0.001}, infotext='Sigma noise').info('amount of additional noise to counteract loss of detail during sampling'),
-    'k_sched_type':  OptionInfo("Automatic", "Scheduler type", gr.Dropdown, {"choices": ["Automatic", "karras", "exponential", "polyexponential"]}, infotext='Schedule type').info("lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below"),
     'sigma_min': OptionInfo(0.0, "sigma min", gr.Number, infotext='Schedule min sigma').info("0 = default (~0.03); minimum noise strength for k-diffusion noise scheduler"),
     'sigma_max': OptionInfo(0.0, "sigma max", gr.Number, infotext='Schedule max sigma').info("0 = default (~14.6); maximum noise strength for k-diffusion noise scheduler"),
     'rho':  OptionInfo(0.0, "rho", gr.Number, infotext='Schedule rho').info("0 = default (7 for karras, 1 for polyexponential); higher values result in a steeper noise schedule (decreases faster)"),
     'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}, infotext='ENSD').info("ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images"),
     'always_discard_next_to_last_sigma': OptionInfo(False, "Always discard next-to-last sigma", infotext='Discard penultimate sigma').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/6044"),
-    'sgm_noise_multiplier': OptionInfo(False, "SGM noise multiplier", infotext='SGM noise multplier').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818").info("Match initial noise to official SDXL implementation - only useful for reproducing images"),
+    'sgm_noise_multiplier': OptionInfo(False, "SGM noise multiplier", infotext='SGM noise multiplier').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818").info("Match initial noise to official SDXL implementation - only useful for reproducing images"),
     'uni_pc_variant': OptionInfo("bh1", "UniPC variant", gr.Radio, {"choices": ["bh1", "bh2", "vary_coeff"]}, infotext='UniPC variant'),
     'uni_pc_skip_type': OptionInfo("time_uniform", "UniPC skip type", gr.Radio, {"choices": ["time_uniform", "time_quadratic", "logSNR"]}, infotext='UniPC skip type'),
     'uni_pc_order': OptionInfo(3, "UniPC order", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}, infotext='UniPC order').info("must be < sampling steps"),
@@ -372,6 +385,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
 
 options_templates.update(options_section(('postprocessing', "Postprocessing", "postprocessing"), {
     'postprocessing_enable_in_main_ui': OptionInfo([], "Enable postprocessing operations in txt2img and img2img tabs", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
+    'postprocessing_disable_in_extras': OptionInfo([], "Disable postprocessing operations in extras tab", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
     'postprocessing_operation_order': OptionInfo([], "Postprocessing operation order", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
     'upscaling_max_images_in_cache': OptionInfo(5, "Maximum number of images in upscaling cache", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
     'postprocessing_existing_caption_action': OptionInfo("Ignore", "Action for existing captions", gr.Radio, {"choices": ["Ignore", "Keep", "Prepend", "Append"]}).info("when generating captions using postprocessing; Ignore = use generated; Keep = use original; Prepend/Append = combine both"),

modules/shared_state.py

@@ -157,10 +157,12 @@ class State:
             self.current_image_sampling_step = self.sampling_step
 
         except Exception:
-            # when switching models during genration, VAE would be on CPU, so creating an image will fail.
+            # when switching models during generation, VAE would be on CPU, so creating an image will fail.
             # we silently ignore this error
             errors.record_exception()
 
     def assign_current_image(self, image):
+        if shared.opts.live_previews_image_format == 'jpeg' and image.mode == 'RGBA':
+            image = image.convert('RGB')
         self.current_image = image
         self.id_live_preview += 1

modules/styles.py

@@ -1,16 +1,17 @@
+from __future__ import annotations
+from pathlib import Path
+from modules import errors
 import csv
-import fnmatch
 import os
-import os.path
 import typing
 import shutil
 
 
 class PromptStyle(typing.NamedTuple):
     name: str
-    prompt: str
-    negative_prompt: str
-    path: str = None
+    prompt: str | None
+    negative_prompt: str | None
+    path: str | None = None
 
 
 def merge_prompts(style_prompt: str, prompt: str) -> str:
@@ -42,7 +43,7 @@ def extract_style_text_from_prompt(style_text, prompt):
     stripped_style_text = style_text.strip()
 
     if "{prompt}" in stripped_style_text:
-        left, right = stripped_style_text.split("{prompt}", 2)
+        left, _, right = stripped_style_text.partition("{prompt}")
         if stripped_prompt.startswith(left) and stripped_prompt.endswith(right):
             prompt = stripped_prompt[len(left):len(stripped_prompt)-len(right)]
             return True, prompt
@@ -79,14 +80,19 @@ def extract_original_prompts(style: PromptStyle, prompt, negative_prompt):
 
 
 class StyleDatabase:
-    def __init__(self, path: str):
+    def __init__(self, paths: list[str | Path]):
         self.no_style = PromptStyle("None", "", "", None)
         self.styles = {}
-        self.path = path
+        self.paths = paths
+        self.all_styles_files: list[Path] = []
 
-        folder, file = os.path.split(self.path)
-        filename, _, ext = file.partition('*')
-        self.default_path = os.path.join(folder, filename + ext)
+        folder, file = os.path.split(self.paths[0])
+        if '*' in file or '?' in file:
+            # if the first path is a wildcard pattern, find the first match else use "folder/styles.csv" as the default path
+            self.default_path = next(Path(folder).glob(file), Path(os.path.join(folder, 'styles.csv')))
+            self.paths.insert(0, self.default_path)
+        else:
+            self.default_path = Path(self.paths[0])
 
         self.prompt_fields = [field for field in PromptStyle._fields if field != "path"]
 
@@ -99,57 +105,58 @@ class StyleDatabase:
         """
         self.styles.clear()
 
-        path, filename = os.path.split(self.path)
+        # scans for all styles files
+        all_styles_files = []
+        for pattern in self.paths:
+            folder, file = os.path.split(pattern)
+            if '*' in file or '?' in file:
+                found_files = Path(folder).glob(file)
+                [all_styles_files.append(file) for file in found_files]
+            else:
+                # if os.path.exists(pattern):
+                all_styles_files.append(Path(pattern))
 
-        if "*" in filename:
-            fileglob = filename.split("*")[0] + "*.csv"
-            filelist = []
-            for file in os.listdir(path):
-                if fnmatch.fnmatch(file, fileglob):
-                    filelist.append(file)
-                    # Add a visible divider to the style list
-                    half_len = round(len(file) / 2)
-                    divider = f"{'-' * (20 - half_len)} {file.upper()}"
-                    divider = f"{divider} {'-' * (40 - len(divider))}"
-                    self.styles[divider] = PromptStyle(
-                        f"{divider}", None, None, "do_not_save"
+        # Remove any duplicate entries
+        seen = set()
+        self.all_styles_files = [s for s in all_styles_files if not (s in seen or seen.add(s))]
+
+        for styles_file in self.all_styles_files:
+            if len(all_styles_files) > 1:
+                # add divider when more than styles file
+                # '---------------- STYLES ----------------'
+                divider = f' {styles_file.stem.upper()} '.center(40, '-')
+                self.styles[divider] = PromptStyle(f"{divider}", None, None, "do_not_save")
+            if styles_file.is_file():
+                self.load_from_csv(styles_file)
+
+    def load_from_csv(self, path: str | Path):
+        try:
+            with open(path, "r", encoding="utf-8-sig", newline="") as file:
+                reader = csv.DictReader(file, skipinitialspace=True)
+                for row in reader:
+                    # Ignore empty rows or rows starting with a comment
+                    if not row or row["name"].startswith("#"):
+                        continue
+                    # Support loading old CSV format with "name, text"-columns
+                    prompt = row["prompt"] if "prompt" in row else row["text"]
+                    negative_prompt = row.get("negative_prompt", "")
+                    # Add style to database
+                    self.styles[row["name"]] = PromptStyle(
+                        row["name"], prompt, negative_prompt, str(path)
                     )
-                    # Add styles from this CSV file
-                    self.load_from_csv(os.path.join(path, file))
-            if len(filelist) == 0:
-                print(f"No styles found in {path} matching {fileglob}")
-                return
-        elif not os.path.exists(self.path):
-            print(f"Style database not found: {self.path}")
-            return
-        else:
-            self.load_from_csv(self.path)
-
-    def load_from_csv(self, path: str):
-        with open(path, "r", encoding="utf-8-sig", newline="") as file:
-            reader = csv.DictReader(file, skipinitialspace=True)
-            for row in reader:
-                # Ignore empty rows or rows starting with a comment
-                if not row or row["name"].startswith("#"):
-                    continue
-                # Support loading old CSV format with "name, text"-columns
-                prompt = row["prompt"] if "prompt" in row else row["text"]
-                negative_prompt = row.get("negative_prompt", "")
-                # Add style to database
-                self.styles[row["name"]] = PromptStyle(
-                    row["name"], prompt, negative_prompt, path
-                )
+        except Exception:
+            errors.report(f'Error loading styles from {path}: ', exc_info=True)
 
     def get_style_paths(self) -> set:
         """Returns a set of all distinct paths of files that styles are loaded from."""
         # Update any styles without a path to the default path
         for style in list(self.styles.values()):
             if not style.path:
-                self.styles[style.name] = style._replace(path=self.default_path)
+                self.styles[style.name] = style._replace(path=str(self.default_path))
 
         # Create a list of all distinct paths, including the default path
         style_paths = set()
-        style_paths.add(self.default_path)
+        style_paths.add(str(self.default_path))
         for _, style in self.styles.items():
             if style.path:
                 style_paths.add(style.path)
@@ -177,7 +184,6 @@ class StyleDatabase:
 
     def save_styles(self, path: str = None) -> None:
         # The path argument is deprecated, but kept for backwards compatibility
-        _ = path
 
         style_paths = self.get_style_paths()
 

modules/textual_inversion/autocrop.py

@@ -65,7 +65,7 @@ def crop_image(im, settings):
         rect[3] -= 1
         d.rectangle(rect, outline=GREEN)
         results.append(im_debug)
-        if settings.destop_view_image:
+        if settings.desktop_view_image:
             im_debug.show()
 
     return results
@@ -341,5 +341,5 @@ class Settings:
         self.entropy_points_weight = entropy_points_weight
         self.face_points_weight = face_points_weight
         self.annotate_image = annotate_image
-        self.destop_view_image = False
+        self.desktop_view_image = False
         self.dnn_model_path = dnn_model_path

modules/textual_inversion/dataset.py

@@ -2,7 +2,6 @@ import os
 import numpy as np
 import PIL
 import torch
-from PIL import Image
 from torch.utils.data import Dataset, DataLoader, Sampler
 from torchvision import transforms
 from collections import defaultdict
@@ -10,7 +9,7 @@ from random import shuffle, choices
 
 import random
 import tqdm
-from modules import devices, shared
+from modules import devices, shared, images
 import re
 
 from ldm.modules.distributions.distributions import DiagonalGaussianDistribution
@@ -61,7 +60,7 @@ class PersonalizedBase(Dataset):
             if shared.state.interrupted:
                 raise Exception("interrupted")
             try:
-                image = Image.open(path)
+                image = images.read(path)
                 #Currently does not work for single color transparency
                 #We would need to read image.info['transparency'] for that
                 if use_weight and 'A' in image.getbands():

modules/textual_inversion/image_embedding.py

@@ -1,12 +1,16 @@
 import base64
 import json
+import os.path
 import warnings
+import logging
 
 import numpy as np
 import zlib
 from PIL import Image, ImageDraw
 import torch
 
+logger = logging.getLogger(__name__)
+
 
 class EmbeddingEncoder(json.JSONEncoder):
     def default(self, obj):
@@ -43,7 +47,7 @@ def lcg(m=2**32, a=1664525, c=1013904223, seed=0):
 
 def xor_block(block):
     g = lcg()
-    randblock = np.array([next(g) for _ in range(np.product(block.shape))]).astype(np.uint8).reshape(block.shape)
+    randblock = np.array([next(g) for _ in range(np.prod(block.shape))]).astype(np.uint8).reshape(block.shape)
     return np.bitwise_xor(block.astype(np.uint8), randblock & 0x0F)
 
 
@@ -114,7 +118,7 @@ def extract_image_data_embed(image):
     outarr = crop_black(np.array(image.convert('RGB').getdata()).reshape(image.size[1], image.size[0], d).astype(np.uint8)) & 0x0F
     black_cols = np.where(np.sum(outarr, axis=(0, 2)) == 0)
     if black_cols[0].shape[0] < 2:
-        print('No Image data blocks found.')
+        logger.debug(f'{os.path.basename(getattr(image, "filename", "unknown image file"))}: no embedded information found.')
         return None
 
     data_block_lower = outarr[:, :black_cols[0].min(), :].astype(np.uint8)
@@ -193,11 +197,11 @@ if __name__ == '__main__':
 
     embedded_image = insert_image_data_embed(cap_image, test_embed)
 
-    retrived_embed = extract_image_data_embed(embedded_image)
+    retrieved_embed = extract_image_data_embed(embedded_image)
 
-    assert str(retrived_embed) == str(test_embed)
+    assert str(retrieved_embed) == str(test_embed)
 
-    embedded_image2 = insert_image_data_embed(cap_image, retrived_embed)
+    embedded_image2 = insert_image_data_embed(cap_image, retrieved_embed)
 
     assert embedded_image == embedded_image2
 

modules/textual_inversion/textual_inversion.py

@@ -17,7 +17,7 @@ import modules.textual_inversion.dataset
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 
 from modules.textual_inversion.image_embedding import embedding_to_b64, embedding_from_b64, insert_image_data_embed, extract_image_data_embed, caption_image_overlay
-from modules.textual_inversion.logging import save_settings_to_file
+from modules.textual_inversion.saving_settings import save_settings_to_file
 
 
 TextualInversionTemplate = namedtuple("TextualInversionTemplate", ["name", "path"])
@@ -150,6 +150,7 @@ class EmbeddingDatabase:
         return embedding
 
     def get_expected_shape(self):
+        devices.torch_npu_set_device()
         vec = shared.sd_model.cond_stage_model.encode_embedding_init_text(",", 1)
         return vec.shape[1]
 
@@ -171,7 +172,7 @@ class EmbeddingDatabase:
                 if data:
                     name = data.get('name', name)
                 else:
-                    # if data is None, means this is not an embeding, just a preview image
+                    # if data is None, means this is not an embedding, just a preview image
                     return
         elif ext in ['.BIN', '.PT']:
             data = torch.load(path, map_location="cpu")