| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | | | | | Merge pull request #7284 from Gazzoo-byte/patch-1 | AUTOMATIC1111 | 2023-01-28 | 1 | -0/+11 | |
| |\ \ \ \ \ | | | | | | | | | | | | | Add button to switch width and height | |||||
| | * | | | | | Add button to switch width and height | Gazzoo-byte | 2023-01-27 | 1 | -0/+11 | |
| | |/ / / / | | | | | | | | | | | Adds a button to switch width and height, allowing quick and easy switching between landscape and portrait. | |||||
| * | | | | | make the detection for -v models less broad | AUTOMATIC | 2023-01-28 | 1 | -1/+1 | |
| | | | | | | ||||||
| * | | | | | Merge pull request #7294 from MrCheeze/model-detection | AUTOMATIC1111 | 2023-01-28 | 1 | -1/+4 | |
| |\ \ \ \ \ | | | | | | | | | | | | | add v2-inpainting model detection, and broaden v-model detection to include anything with 768 in the name | |||||
| | * | | | | | add v2-inpainting model detection, and broaden v-model detection to include ↵ | MrCheeze | 2023-01-28 | 1 | -1/+4 | |
| | | | | | | | | | | | | | | | | | | | | | | | | | anything with 768 in the name | |||||
| * | | | | | | Basic inpainting batch support | Andrii Skaliuk | 2023-01-28 | 2 | -4/+25 | |
| |/ / / / / | | | | | | | | | | | | | | | | Modifies batch UI to add optional inpainting support | |||||
| * / / / / | fix broken calls to find_checkpoint_config | AUTOMATIC | 2023-01-27 | 2 | -4/+4 | |
| |/ / / / | ||||||
| * | | | | clarify the option to disable NaN check. | AUTOMATIC | 2023-01-27 | 1 | -0/+2 | |
| | | | | | ||||||
| * | | | | support detecting midas model | AUTOMATIC | 2023-01-27 | 3 | -8/+11 | |
| | | | | | | | | | | | | | | | | | fix broken api for checkpoint list | |||||
| * | | | | remove the need to place configs near models | AUTOMATIC | 2023-01-27 | 8 | -134/+242 | |
| | | | | | ||||||
| * | | | | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | 2023-01-26 | 7 | -18/+107 | |
| | |/ / |/| | | | | | | | | fix some style inconsistenices | |||||
| * | | | Fix full previews, --no-half-vae | brkirch | 2023-01-26 | 2 | -5/+5 | |
| |/ / | ||||||
| * | | fix prompt editing break after first batch in img2img | AUTOMATIC | 2023-01-25 | 1 | -1/+1 | |
| | | | ||||||
| * | | add edit_image_conditioning from my earlier edits in case there's an attempt ↵ | AUTOMATIC | 2023-01-25 | 1 | -1/+9 | |
| | | | | | | | | | | | | | to inegrate pix2pix properly this allows to use pix2pix model in img2img though it won't work well this way | |||||
| * | | Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinks | AUTOMATIC1111 | 2023-01-25 | 1 | -1/+1 | |
| |\ \ | |/ |/| | allow symlinks in the textual inversion embeddings folder | |||||
| | * | allow symlinks in the textual inversion embeddings folder | Alex "mcmonkey" Goodwin | 2023-01-25 | 1 | -1/+1 | |
| | | | ||||||
| * | | fix for unet hijack breaking the train tab | AUTOMATIC | 2023-01-25 | 1 | -2/+5 | |
| | | | ||||||
| * | | make clicking extra networks button one more time close the extra networks UI | AUTOMATIC | 2023-01-25 | 1 | -2/+7 | |
| |/ | ||||||
| * | Merge pull request #6510 from brkirch/unet16-upcast-precision | AUTOMATIC1111 | 2023-01-25 | 9 | -71/+188 | |
| |\ | | | | | Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half | |||||
| | * | Add UI setting for upcasting attention to float32 | brkirch | 2023-01-25 | 5 | -64/+108 | |
| | | | | | | | | | | | | | 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. | |||||
| | * | Add option for float32 sampling with float16 UNet | brkirch | 2023-01-25 | 7 | -8/+81 | |
| | | | | | | | | | 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(). | |||||
| * | | change to code for live preview fix on OSX to be bit more obvious | AUTOMATIC | 2023-01-25 | 1 | -2/+2 | |
| | | | ||||||
| * | | Merge pull request #7151 from brkirch/fix-approx-nn | AUTOMATIC1111 | 2023-01-25 | 1 | -1/+5 | |
| |\ \ | | | | | | | Fix Approx NN previews changing first generation result | |||||
| | * | | Fix different first gen with Approx NN previews | brkirch | 2023-01-24 | 1 | -1/+5 | |
| | | | | | | | | | | | | | 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. | |||||
| * | | | Add instruct-pix2pix hijack | Kyle | 2023-01-25 | 3 | -1/+1483 | |
| | | | | | | | | | | | | | | | | | | | 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 | |||||
| * | | | Merge pull request #7146 from EllangoK/master | AUTOMATIC1111 | 2023-01-25 | 1 | -1/+1 | |
| |\ \ \ | |_|/ |/| | | Adds X/Y/Z Grid Script | |||||
| | * | | handling sub grids and merging into one | EllangoK | 2023-01-24 | 1 | -1/+1 | |
| | | | | ||||||
| * | | | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | 2023-01-24 | 1 | -1/+1 | |
| | | | | | | | | | | | | | about it mk2 | |||||
| * | | | remove fairscale requirement, add fake fairscale to make BLIP not complain ↵ | AUTOMATIC | 2023-01-24 | 1 | -2/+9 | |
| | | | | | | | | | | | | | about it | |||||
| * | | | also return the removed field to sdapi/v1/upscalers because someone might ↵ | AUTOMATIC | 2023-01-24 | 2 | -0/+2 | |
| | | | | | | | | | | | | | have relied on it existing | |||||
| * | | | repair sdapi/v1/upscalers returning bogus results | AUTOMATIC | 2023-01-24 | 2 | -8/+10 | |
| | | | | ||||||
| * | | | add image decod exception handling | Vladimir Mandic | 2023-01-23 | 1 | -1/+5 | |
| | |/ |/| | ||||||
| * | | fix BLIP failing to import depending on configuration | AUTOMATIC | 2023-01-23 | 2 | -1/+16 | |
| | | | ||||||
| * | | Merge pull request #7113 from vladmandic/interrogate | AUTOMATIC1111 | 2023-01-23 | 2 | -16/+26 | |
| |\ \ | | | | | | | Add selector to interrogate categories | |||||
| | * | | add option to skip interrogate categories | Vladimir Mandic | 2023-01-23 | 2 | -15/+19 | |
| | | | | ||||||
| | * | | Merge branch 'AUTOMATIC1111:master' into interrogate | Vladimir Mandic | 2023-01-23 | 4 | -12/+31 | |
| | |\| | ||||||
| | * | | improve interrogate | Vladimir Mandic | 2023-01-23 | 2 | -12/+18 | |
| | | | | ||||||
| * | | | add support for apostrophe in extra network names | AUTOMATIC | 2023-01-23 | 1 | -2/+4 | |
| | |/ |/| | ||||||
| * | | Merge pull request #7032 from gmq/extra-network-styles | AUTOMATIC1111 | 2023-01-23 | 2 | -1/+6 | |
| |\ \ | | | | | | | Extra network view style | |||||
| | * | | feat(extra-networks): remove view dropdown | Guillermo Moreno | 2023-01-23 | 1 | -11/+9 | |
| | | | | ||||||
| | * | | feat(extra-networks): add default view setting | Guillermo Moreno | 2023-01-22 | 2 | -4/+8 | |
| | | | | ||||||
| | * | | feat(extra-networks): add thumbs view style | Guillermo Moreno | 2023-01-22 | 1 | -9/+12 | |
| | | | | ||||||
| * | | | api-image-format | Vladimir Mandic | 2023-01-23 | 1 | -10/+24 | |
| | | | | ||||||
| * | | | a possible fix for broken image upscaling | AUTOMATIC | 2023-01-23 | 1 | -1/+1 | |
| | |/ |/| | ||||||
| * | | better support for xformers flash attention on older versions of torch | AUTOMATIC | 2023-01-23 | 2 | -24/+30 | |
| | | | ||||||
| * | | Merge remote-tracking branch 'takuma104/xformers-flash-attention' | AUTOMATIC | 2023-01-23 | 2 | -2/+25 | |
| |\ \ | ||||||
| | * | | add --xformers-flash-attention option & impl | Takuma Mori | 2023-01-21 | 2 | -2/+25 | |
| | | | | ||||||
| * | | | fix open directory button failing | AUTOMATIC | 2023-01-23 | 2 | -2/+1 | |
| | | | | ||||||
| * | | | Merge pull request #7031 from EllangoK/master | AUTOMATIC1111 | 2023-01-23 | 1 | -1/+1 | |
| |\ \ \ | | | | | | | | | Fixes various button overflowing UI and compact checkbox | |||||
| | * | | | compact checkbox and fix copy image btn overflow | EllangoK | 2023-01-21 | 1 | -1/+1 | |
| | | | | | | | | | | | | | | | | | also fixes type for #tab_extensions in style.css | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |