- 25 3月, 2023 35 次提交
-
-
由 AUTOMATIC1111 提交于
Fix img2img-alternative-test script for SD v2.x
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC1111 提交于
Don't bubble when metadata_button is clicked
-
由 AUTOMATIC1111 提交于
-
由 AUTOMATIC1111 提交于
Fix problem of install.py when data-dir is specified
-
由 AUTOMATIC1111 提交于
Unload and re-load checkpoint to VRAM on request (API & Manual)
-
由 AUTOMATIC1111 提交于
Move `load_file_from_url` import
-
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 1 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.
-