| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2023-02-06 | aspect ratio for dim's; sliders adjust by ratio | Gerschel | -0/+14 | |
| Default choices added to settings in user interface section Choices are editable by user User selects from dropdown. When you move one slider, the other adjusts according to the ratio chosen. Vice versa for the other slider. Number fields for changes work as well. For disabling ratio, an unlock pad "🔓" is available as a default. This string can be changed to anything to serve as a disable, as long as there is no colon ":". Ratios are entered in this format, floats or ints with a colon "1:1". The string is split at the colon, parses left and right as floats to perform the math. | ||||
| 2023-02-04 | add --no-hashing | AUTOMATIC | -1/+1 | |
| 2023-01-30 | Adding default true to use_original_name_batch as images should by default ↵ | Joey Sanchez | -1/+1 | |
| hold the same name to help keep sequenced images in their correct order | ||||
| 2023-01-30 | Add --skip-version-check to disable messages asking users to upgrade torch. | AUTOMATIC | -0/+2 | |
| 2023-01-30 | change disable_weights_auto_swap to true by default | AUTOMATIC | -1/+1 | |
| 2023-01-30 | make it so that setting options in pasted infotext (like Clip Skip and ENSD) ↵ | AUTOMATIC | -5/+32 | |
| do not get applied directly and instead are added as temporary overrides | ||||
| 2023-01-28 | add dropdowns in settings for hypernets and loras | AUTOMATIC | -2/+3 | |
| 2023-01-27 | add data-dir flag and set all user data directories based on it | Max Audron | -5/+6 | |
| 2023-01-27 | remove the need to place configs near models | AUTOMATIC | -3/+4 | |
| 2023-01-26 | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | -10/+5 | |
| fix some style inconsistenices | ||||
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | -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. | ||||
| 2023-01-25 | Add option for float32 sampling with float16 UNet | brkirch | -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(). | ||||
| 2023-01-23 | add option to skip interrogate categories | Vladimir Mandic | -1/+1 | |
| 2023-01-23 | Merge branch 'AUTOMATIC1111:master' into interrogate | Vladimir Mandic | -0/+4 | |
| 2023-01-23 | Merge pull request #7032 from gmq/extra-network-styles | AUTOMATIC1111 | -0/+4 | |
| Extra network view style | ||||
| 2023-01-23 | improve interrogate | Vladimir Mandic | -0/+1 | |
| 2023-01-23 | Merge remote-tracking branch 'takuma104/xformers-flash-attention' | AUTOMATIC | -0/+1 | |
| 2023-01-23 | rework extras tab to use script system | AUTOMATIC | -0/+5 | |
| 2023-01-22 | feat(extra-networks): add default view setting | Guillermo Moreno | -0/+4 | |
| 2023-01-22 | add an option to reorder tabs for extra networks | AUTOMATIC | -0/+1 | |
| 2023-01-22 | attention ctrl+up/down enhancements | AUTOMATIC | -3/+5 | |
| 2023-01-22 | add a slider for default value of added extra networks | AUTOMATIC | -2/+3 | |
| 2023-01-21 | add --gradio-queue option to enable gradio queue | AUTOMATIC | -0/+2 | |
| 2023-01-21 | add --xformers-flash-attention option & impl | Takuma Mori | -0/+1 | |
| 2023-01-21 | make CLIP interrogator download original text files if the directory does ↵ | AUTOMATIC | -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 | ||||
| 2023-01-21 | extra networks UI | AUTOMATIC | -5/+16 | |
| rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | ||||
| 2023-01-19 | Update shared.py | vt-idiot | -1/+1 | |
| `Witdth/Height` was driving me insane. -> `Width/Height` | ||||
| 2023-01-19 | allow baking in VAE in checkpoint merger tab | AUTOMATIC | -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 | ||||
| 2023-01-18 | Merge pull request #6851 from ddPn08/master | AUTOMATIC1111 | -0/+1 | |
| Add `--vae-dir` argument | ||||
| 2023-01-18 | add option to show/hide warnings | AUTOMATIC | -0/+1 | |
| removed hiding warnings from LDSR fixed/reworked few places that produced warnings | ||||
| 2023-01-18 | fix typo | ddPn08 | -1/+1 | |
| 2023-01-17 | Add `--vae-dir` argument | ddPn08 | -0/+1 | |
| 2023-01-17 | disable the new NaN check for the CI | AUTOMATIC | -0/+1 | |
| 2023-01-16 | return an option to hide progressbar | AUTOMATIC | -0/+1 | |
| 2023-01-16 | support old configs that say "auto" for ssd_vae | AUTOMATIC | -1/+1 | |
| change sd_vae_as_default to True by default as it's a more sensible setting | ||||
| 2023-01-15 | rename masking to inpaint in UI | AUTOMATIC | -1/+1 | |
| make inpaint go to the right place for users who don't have it in config string | ||||
| 2023-01-15 | Merge pull request #6758 from Poktay/allow_reorder_masking_controls | AUTOMATIC1111 | -0/+1 | |
| allow reordering of inpaint masking controls (like the other sections can be reordered) | ||||
| 2023-01-15 | Merge pull request #6778 from pangbo13/master | AUTOMATIC1111 | -1/+1 | |
| Fix unexpected behavior when show_progress_every_n_steps is set to -1 | ||||
| 2023-01-15 | add setting for progressbar update period | AUTOMATIC | -0/+1 | |
| 2023-01-16 | fix when show_progress_every_n_steps == -1 | pangbo13 | -1/+1 | |
| 2023-01-15 | big rework of progressbar/preview system to allow multiple users to prompts ↵ | AUTOMATIC | -5/+11 | |
| at the same time and do not get previews of each other | ||||
| 2023-01-14 | add inpaint masking controls to orderable section that the settings can order | Josh R | -0/+1 | |
| 2023-01-14 | Merge pull request #6731 from vladmandic/state_server_start | Vladimir Mandic | -0/+2 | |
| Add server start time to state info | ||||
| 2023-01-14 | fix bug with "Ignore selected VAE for..." option completely disabling VAE ↵ | AUTOMATIC | -2/+2 | |
| election rework VAE resolving code to be more simple | ||||
| 2023-01-14 | add server_start to shared.state | Vladimir Mandic | -0/+2 | |
| 2023-01-14 | add an option to choose what you want to see in live preview (Live preview ↵ | AUTOMATIC | -4/+9 | |
| subject) and moves live preview settings to its own tab | ||||
| 2023-01-14 | load hashes from cache for checkpoints that have them | AUTOMATIC | -0/+1 | |
| add checkpoint hash to footer | ||||
| 2023-01-14 | change hypernets to use sha256 hashes | AUTOMATIC | -0/+1 | |
| 2023-01-14 | change hash to sha256 | AUTOMATIC | -1/+1 | |
| 2023-01-13 | Merge branch 'master' into tensorboard | AUTOMATIC1111 | -45/+254 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |