| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2023-01-27 | create user extensions directory if not exists | Max Audron | |
| 2023-01-27 | clean up unused script_path imports | Max Audron | |
| 2023-01-27 | use python importlib to load and execute extension modules | Max Audron | |
| previously module attributes like __file__ where not set correctly, leading to scripts getting the directory of the stable-diffusion repo location instead of their own script. This causes problem when loading user data from an external location using the --data-dir flag, as extensions would look for their own code in the stable-diffusion repo location instead of the data dir location. Using pythons importlib functions sets the modules specs correctly and executes them. But this will break extensions if they build paths based on the previously incorrect __file__ attribute. | |||
| 2023-01-27 | add data-dir flag and set all user data directories based on it | Max Audron | |
| 2023-01-27 | clarify the option to disable NaN check. | AUTOMATIC | |
| 2023-01-27 | support detecting midas model | AUTOMATIC | |
| fix broken api for checkpoint list | |||
| 2023-01-27 | remove the need to place configs near models | AUTOMATIC | |
| 2023-01-26 | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | |
| fix some style inconsistenices | |||
| 2023-01-26 | Merge pull request #7234 from brkirch/fix-full-previews | AUTOMATIC1111 | |
| Fix full previews and--no-half-vae to work correctly with --upcast-sampling | |||
| 2023-01-26 | Fix full previews, --no-half-vae | brkirch | |
| 2023-01-25 | fix prompt editing break after first batch in img2img | AUTOMATIC | |
| 2023-01-25 | add edit_image_conditioning from my earlier edits in case there's an attempt ↵ | AUTOMATIC | |
| to inegrate pix2pix properly this allows to use pix2pix model in img2img though it won't work well this way | |||
| 2023-01-25 | Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinks | AUTOMATIC1111 | |
| allow symlinks in the textual inversion embeddings folder | |||
| 2023-01-25 | Merge pull request #7201 from brkirch/update-macos-defaults | AUTOMATIC1111 | |
| Update default Mac command line arguments to use --upcast-sampling instead of --no-half | |||
| 2023-01-25 | Update arguments to use --upcast-sampling | brkirch | |
| 2023-01-25 | fix for unet hijack breaking the train tab | AUTOMATIC | |
| 2023-01-25 | make clicking extra networks button one more time close the extra networks UI | AUTOMATIC | |
| 2023-01-25 | allow symlinks in the textual inversion embeddings folder | Alex "mcmonkey" Goodwin | |
| 2023-01-25 | add pix2pix credits | AUTOMATIC | |
| 2023-01-25 | Merge pull request #6510 from brkirch/unet16-upcast-precision | AUTOMATIC1111 | |
| Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half | |||
| 2023-01-25 | Merge pull request #7138 from mykeehu/patch-4 | AUTOMATIC1111 | |
| Fix extra network thumbs label color | |||
| 2023-01-25 | change to code for live preview fix on OSX to be bit more obvious | AUTOMATIC | |
| 2023-01-25 | Merge pull request #7151 from brkirch/fix-approx-nn | AUTOMATIC1111 | |
| Fix Approx NN previews changing first generation result | |||
| 2023-01-25 | Merge pull request #7195 from Klace/instruct-pix2pix_model_load | AUTOMATIC1111 | |
| Add instruct-pix2pix hijack | |||
| 2023-01-25 | Update requirements transformers==4.25.1 | Kyle | |
| Update requirement for transformers to version 4.25.1 to allow instruct-pix2pix demo code to work | |||
| 2023-01-25 | Add instruct-pix2pix hijack | Kyle | |
| Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py Adds ddpm_edit.py necessary for instruct-pix2pix | |||
| 2023-01-25 | Merge pull request #7146 from EllangoK/master | AUTOMATIC1111 | |
| Adds X/Y/Z Grid Script | |||
| 2023-01-25 | add an experimental option to apply loras to outputs rather than inputs | AUTOMATIC | |
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | |
| Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers. In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also. | |||
| 2023-01-25 | Add option for float32 sampling with float16 UNet | brkirch | |
| This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half(). | |||
| 2023-01-25 | remove the pip install stuff because it does not work as i hoped it would | AUTOMATIC | |
| 2023-01-24 | add fastapi to requirements | AUTOMATIC | |
| 2023-01-24 | print progress when installing torch | AUTOMATIC | |
| add PIP_INSTALLER_LOCATION env var to install pip if it's not installed remove accidental call to accelerate when venv is disabled add another env var to skip venv - SKIP_VENV | |||
| 2023-01-24 | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | |
| about it mk2 | |||
| 2023-01-24 | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | |
| about it | |||
| 2023-01-24 | make git commands not fail for extensions when you have spaces in webui ↵ | AUTOMATIC | |
| directory | |||
| 2023-01-24 | swaps xyz axes internally if one costs more | EllangoK | |
| 2023-01-24 | handling sub grids and merging into one | EllangoK | |
| 2023-01-24 | implements most of xyz grid script | EllangoK | |
| 2023-01-24 | renamed xy to xyz grid | EllangoK | |
| this is mostly just so git can detect it properly | |||
| 2023-01-24 | also return the removed field to sdapi/v1/upscalers because someone might ↵ | AUTOMATIC | |
| have relied on it existing | |||
| 2023-01-24 | repair sdapi/v1/upscalers returning bogus results | AUTOMATIC | |
| 2023-01-24 | Merge pull request #7140 from vladmandic/api-decode-image | AUTOMATIC1111 | |
| Add exception handling to API image decode | |||
| 2023-01-24 | Merge pull request #7144 from catboxanon/swinir-interrupt | AUTOMATIC1111 | |
| Make SwinIR upscaler interruptible and skippable | |||
| 2023-01-24 | Merge pull request #7148 from acncagua/improvement_launch.py | AUTOMATIC1111 | |
| Set Linux xformers 0.0.16RC425 | |||
| 2023-01-23 | Fix different first gen with Approx NN previews | brkirch | |
| The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance. | |||
| 2023-01-24 | Set Linux xformers 0.0.16RC425 | acncagua | |
| 2023-01-23 | Also make SwinIR skippable | catboxanon | |
| 2023-01-23 | Make SwinIR interruptible | catboxanon | |
| 2023-01-23 | add image decod exception handling | Vladimir Mandic | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |