- 25 3月, 2023 28 次提交
-
-
由 AUTOMATIC1111 提交于
Fix scripts load order
-
由 AUTOMATIC1111 提交于
Add ability to display and/or save inpainting mask and masked composite
-
由 AUTOMATIC1111 提交于
disable gradio css transitions
-
由 AUTOMATIC1111 提交于
fix variable typo
-
由 AUTOMATIC1111 提交于
Support git submodule for extension and Fix Windows PermissionError
-
由 AUTOMATIC1111 提交于
Loopback Script Updates
-
由 AUTOMATIC1111 提交于
Fixes xyz extra_generation_params not being saved (previously worked)
-
由 AUTOMATIC1111 提交于
fixed typo in prompt-bracket-checker.js which leads to js error
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC1111 提交于
Fix None type error for TI module
-
由 AUTOMATIC1111 提交于
Add PyTorch 2.0 support for macOS, fix image generation on macOS 13.2.X
-
由 AUTOMATIC1111 提交于
--upcast-sampling support for CUDA
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
fix broken image dragging
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
more stylistic changes
-
由 AUTOMATIC 提交于
more stylistic changes
-
由 AUTOMATIC 提交于
fix dropdown obscured by live preview stylistic changes
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
fix broken image dragging
-
由 FNSpd 提交于
-
由 butaixianran 提交于
When user using model_name.png as a preview image, textural_inversion.py still treat it as an embeding, and didn't handle its error, just let python throw out an None type error like following: ```bash File "D:\Work\Dev\AI\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 155, in load_from_file name = data.get('name', name) AttributeError: 'NoneType' object has no attribute 'get' ``` With just a simple `if data:` checking as following, there will be no error, breaks nothing, and now this module can works fine with user's preview images. Old code: ```python data = extract_image_data_embed(embed_image) name = data.get('name', name) ``` New code: ```python data = extract_image_data_embed(embed_image) if data: name = data.get('name', name) else: # if data is None, means this is not an embeding, just a preview image return ``` Also, since there is no more errors on textual inversion module, from now on, extra network can set "model_name.png" as preview image for embedings.
-
- 24 3月, 2023 4 次提交
-
-
由 FNSpd 提交于
-
由 FNSpd 提交于
-
由 brkirch 提交于
On PyTorch 2.0, with MPS layer_norm only accepts float32 inputs. This was fixed shortly after 2.0 was finalized so the workaround can be applied with an exact version match.
-
由 brkirch 提交于
Credit to danieldk (https://github.com/explosion/curated-transformers/pull/124) for the workaround this is based on.
-
- 23 3月, 2023 4 次提交
-
-
由 James Railton 提交于
The loopback script did not set masked content to original after first loop. So each loop would apply a fill, or latent mask. This would essentially reset progress each loop. The desired behavior is to use the mask for the first loop, then continue to iterate on the results of the previous loop.
-
由 carat-johyun 提交于
-
由 catboxanon 提交于
For inpainting, this exposes the mask and masked composite and gives the user the ability to display these in the web UI, save to disk, or both.
-
由 sumof2primes 提交于
- 1st webui, 2nd extensions-builtin, 3rd extensions - to load scripts independent of --data-dir - change load order key [x.basedir, x.filename, x.path] to [orderby(x.basedir), x.filename, x.path] e.g., scripts/xyz_grid.py dependent extentions should loaded later extensions\sd-webui-controlnet\scripts\xyz_grid_support.py extensions\sd-webui-additional-networks\scripts\xyz_grid_support.py
-
- 22 3月, 2023 3 次提交
-
-
由 sumof2primes 提交于
- 1st webui, 2nd extensions-builtin, 3rd extensions - to load scripts independent of --data-dir - change load order key [x.basedir, x.filename, x.path] to [orderby(x.basedir), x.filename, x.path] e.g., scripts/xyz_grid.py dependent extentions should loaded later extensions\sd-webui-controlnet\scripts\xyz_grid_support.py extensions\sd-webui-additional-networks\scripts\xyz_grid_support.py
-
由 EllangoK 提交于
-
由 James Railton 提交于
- Improved user experience. You can now pick the denoising strength of the final loop and one of three curves. Previously you picked a multiplier such as 0.98 or 1.03 to define the change to the denoising strength for each loop. You had to do a ton of math in your head to visualize what was happening. The new UX makes it very easy to understand what's going on and tweak. - For batch sizes over 1, intermediate images no longer returned. For a batch size of 1, intermediate images from each loop will continue to be returned. When more than 1 image is returned, a grid will also be generated. Previously for larger jobs, you'd get back a mess of many grids and potentially hundreds of images with no organization. To make large jobs usable, only final images are returned. - Added support for skipping current image. Fixed interrupt to cleanly end and return images. Previously these would throw. - Improved tooltip descriptions - Fix some edge cases
-
- 21 3月, 2023 1 次提交
-
-
由 FNSpd 提交于
-