| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | | change disable_weights_auto_swap to true by default | AUTOMATIC | 2023-01-29 | 1 | -1/+1 | |
| | | | ||||||
| * | | make it so that setting options in pasted infotext (like Clip Skip and ENSD) ↵ | AUTOMATIC | 2023-01-29 | 1 | -5/+32 | |
| | | | | | | | | | do not get applied directly and instead are added as temporary overrides | |||||
| * | | add dropdowns in settings for hypernets and loras | AUTOMATIC | 2023-01-28 | 1 | -2/+3 | |
| |/ | ||||||
| * | add data-dir flag and set all user data directories based on it | Max Audron | 2023-01-27 | 1 | -5/+6 | |
| | | ||||||
| * | remove the need to place configs near models | AUTOMATIC | 2023-01-27 | 1 | -3/+4 | |
| | | ||||||
| * | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | 2023-01-26 | 1 | -10/+5 | |
| | | | | | fix some style inconsistenices | |||||
| * | Add UI setting for upcasting attention to float32 | brkirch | 2023-01-25 | 1 | -0/+1 | |
| | | | | | | | 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 | 1 | -0/+1 | |
| | | | | | 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(). | |||||
| * | add option to skip interrogate categories | Vladimir Mandic | 2023-01-23 | 1 | -1/+1 | |
| | | ||||||
| * | Merge branch 'AUTOMATIC1111:master' into interrogate | Vladimir Mandic | 2023-01-23 | 1 | -0/+4 | |
| |\ | ||||||
| | * | Merge pull request #7032 from gmq/extra-network-styles | AUTOMATIC1111 | 2023-01-23 | 1 | -0/+4 | |
| | |\ | | | | | | | Extra network view style | |||||
| | | * | feat(extra-networks): add default view setting | Guillermo Moreno | 2023-01-22 | 1 | -0/+4 | |
| | | | | ||||||
| * | | | improve interrogate | Vladimir Mandic | 2023-01-23 | 1 | -0/+1 | |
| |/ / | ||||||
| * | | Merge remote-tracking branch 'takuma104/xformers-flash-attention' | AUTOMATIC | 2023-01-23 | 1 | -0/+1 | |
| |\ \ | ||||||
| | * | | add --xformers-flash-attention option & impl | Takuma Mori | 2023-01-21 | 1 | -0/+1 | |
| | | | | ||||||
| * | | | rework extras tab to use script system | AUTOMATIC | 2023-01-23 | 1 | -0/+5 | |
| | |/ |/| | ||||||
| * | | add an option to reorder tabs for extra networks | AUTOMATIC | 2023-01-22 | 1 | -0/+1 | |
| | | | ||||||
| * | | attention ctrl+up/down enhancements | AUTOMATIC | 2023-01-22 | 1 | -3/+5 | |
| | | | ||||||
| * | | add a slider for default value of added extra networks | AUTOMATIC | 2023-01-21 | 1 | -2/+3 | |
| | | | ||||||
| * | | add --gradio-queue option to enable gradio queue | AUTOMATIC | 2023-01-21 | 1 | -0/+2 | |
| |/ | ||||||
| * | make CLIP interrogator download original text files if the directory does ↵ | AUTOMATIC | 2023-01-21 | 1 | -5/+0 | |
| | | | | | | | | | not exist remove random artist built-in extension (to re-added as a normal extension on demand) remove artists.csv (but what does it mean????????????????????) make interrogate buttons show Loading... when you click them | |||||
| * | extra networks UI | AUTOMATIC | 2023-01-21 | 1 | -5/+16 | |
| | | | | | rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | |||||
| * | Update shared.py | vt-idiot | 2023-01-19 | 1 | -1/+1 | |
| | | | | `Witdth/Height` was driving me insane. -> `Width/Height` | |||||
| * | allow baking in VAE in checkpoint merger tab | AUTOMATIC | 2023-01-19 | 1 | -1/+2 | |
| | | | | | | | | do not save config if it's the default for checkpoint merger tab change file naming scheme for checkpoint merger tab allow just saving A without any merging for checkpoint merger tab some stylistic changes for UI in checkpoint merger tab | |||||
| * | Merge pull request #6851 from ddPn08/master | AUTOMATIC1111 | 2023-01-18 | 1 | -0/+1 | |
| |\ | | | | | Add `--vae-dir` argument | |||||
| | * | fix typo | ddPn08 | 2023-01-17 | 1 | -1/+1 | |
| | | | ||||||
| | * | Add `--vae-dir` argument | ddPn08 | 2023-01-17 | 1 | -0/+1 | |
| | | | ||||||
| * | | add option to show/hide warnings | AUTOMATIC | 2023-01-18 | 1 | -0/+1 | |
| |/ | | | | | removed hiding warnings from LDSR fixed/reworked few places that produced warnings | |||||
| * | disable the new NaN check for the CI | AUTOMATIC | 2023-01-17 | 1 | -0/+1 | |
| | | ||||||
| * | return an option to hide progressbar | AUTOMATIC | 2023-01-16 | 1 | -0/+1 | |
| | | ||||||
| * | support old configs that say "auto" for ssd_vae | AUTOMATIC | 2023-01-15 | 1 | -1/+1 | |
| | | | | | change sd_vae_as_default to True by default as it's a more sensible setting | |||||
| * | rename masking to inpaint in UI | AUTOMATIC | 2023-01-15 | 1 | -1/+1 | |
| | | | | | make inpaint go to the right place for users who don't have it in config string | |||||
| * | Merge pull request #6758 from Poktay/allow_reorder_masking_controls | AUTOMATIC1111 | 2023-01-15 | 1 | -0/+1 | |
| |\ | | | | | allow reordering of inpaint masking controls (like the other sections can be reordered) | |||||
| | * | add inpaint masking controls to orderable section that the settings can order | Josh R | 2023-01-14 | 1 | -0/+1 | |
| | | | ||||||
| * | | Merge pull request #6778 from pangbo13/master | AUTOMATIC1111 | 2023-01-15 | 1 | -1/+1 | |
| |\ \ | | | | | | | Fix unexpected behavior when show_progress_every_n_steps is set to -1 | |||||
| | * | | fix when show_progress_every_n_steps == -1 | pangbo13 | 2023-01-15 | 1 | -1/+1 | |
| | | | | ||||||
| * | | | add setting for progressbar update period | AUTOMATIC | 2023-01-15 | 1 | -0/+1 | |
| |/ / | ||||||
| * / | big rework of progressbar/preview system to allow multiple users to prompts ↵ | AUTOMATIC | 2023-01-15 | 1 | -5/+11 | |
| |/ | | | | at the same time and do not get previews of each other | |||||
| * | Merge pull request #6731 from vladmandic/state_server_start | Vladimir Mandic | 2023-01-14 | 1 | -0/+2 | |
| |\ | | | | | Add server start time to state info | |||||
| | * | add server_start to shared.state | Vladimir Mandic | 2023-01-14 | 1 | -0/+2 | |
| | | | ||||||
| * | | fix bug with "Ignore selected VAE for..." option completely disabling VAE ↵ | AUTOMATIC | 2023-01-14 | 1 | -2/+2 | |
| |/ | | | | | | election rework VAE resolving code to be more simple | |||||
| * | add an option to choose what you want to see in live preview (Live preview ↵ | AUTOMATIC | 2023-01-14 | 1 | -4/+9 | |
| | | | | | subject) and moves live preview settings to its own tab | |||||
| * | load hashes from cache for checkpoints that have them | AUTOMATIC | 2023-01-14 | 1 | -0/+1 | |
| | | | | | add checkpoint hash to footer | |||||
| * | change hypernets to use sha256 hashes | AUTOMATIC | 2023-01-14 | 1 | -0/+1 | |
| | | ||||||
| * | change hash to sha256 | AUTOMATIC | 2023-01-14 | 1 | -1/+1 | |
| | | ||||||
| * | Merge branch 'master' into tensorboard | AUTOMATIC1111 | 2023-01-13 | 1 | -45/+254 | |
| |\ | ||||||
| | * | img2img UI rework: obsolete --gradio-img2img-tool --gradio-inpaint-tool and ↵ | AUTOMATIC | 2023-01-11 | 1 | -2/+2 | |
| | | | | | | | | | always show all tools each in own tab | |||||
| | * | change color selector in settings to be part of form | AUTOMATIC | 2023-01-10 | 1 | -2/+2 | |
| | | | ||||||
| | * | make a dropdown for prompt template selection | AUTOMATIC | 2023-01-09 | 1 | -0/+1 | |
| | | | ||||||
| | * | add an option to use old hiresfix width/height behavior | AUTOMATIC | 2023-01-09 | 1 | -0/+1 | |
| | | | | | | | | | add a visual effect to inactive hires fix elements | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |