| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Merge remote-tracking branch 'origin/api' | AUTOMATIC | 2022-10-19 | 1 | -8/+16 |
| |\ | |||||
| | * | example API working with gradio | arcticfaded | 2022-10-17 | 1 | -7/+15 |
| | | | |||||
| | * | initial prototype by borrowing contracts | arcticfaded | 2022-10-17 | 1 | -1/+1 |
| | | | |||||
| * | | remove dependence on TQDM for sampler progress/interrupt functionality | AUTOMATIC | 2022-10-18 | 1 | -6/+0 |
| |/ | |||||
| * | Only make output dir when creating output | CookieHCl | 2022-10-16 | 1 | -6/+0 |
| | | |||||
| * | do not reload embeddings from disk when doing textual inversion | AUTOMATIC | 2022-10-16 | 1 | -2/+3 |
| | | |||||
| * | add First pass size always regardless of whether it was auto chosen or specified | AUTOMATIC | 2022-10-15 | 1 | -1/+1 |
| | | |||||
| * | bring back scale latent option in settings | AUTOMATIC | 2022-10-15 | 1 | -4/+4 |
| | | |||||
| * | Set to -1 when seed input is none | githublsx | 2022-10-15 | 1 | -1/+1 |
| | | |||||
| * | set firstpass w/h to 0 by default and rever to old behavior when any are 0 | AUTOMATIC | 2022-10-14 | 1 | -19/+30 |
| | | |||||
| * | remove scale latent and no-crop options from hires fix | AUTOMATIC | 2022-10-14 | 1 | -37/+27 |
| | | | | | support copy-pasting new parameters for hires fix | ||||
| * | Fixed Scale ratio problem | Buckzor | 2022-10-14 | 1 | -14/+11 |
| | | |||||
| * | Option between stretch and crop for Highres. fix | Buckzor | 2022-10-14 | 1 | -12/+22 |
| | | |||||
| * | Added first_pass_width and height as adjustable inputs to "High Res Fix" | Buckzor | 2022-10-14 | 1 | -2/+4 |
| | | |||||
| * | Restore last generation params | Trung Ngo | 2022-10-13 | 1 | -0/+4 |
| | | |||||
| * | add eta noise seed delta option | AUTOMATIC | 2022-10-10 | 1 | -1/+5 |
| | | |||||
| * | --no-half-vae pt2 | AUTOMATIC | 2022-10-10 | 1 | -2/+1 |
| | | |||||
| * | --no-half-vae | AUTOMATIC | 2022-10-10 | 1 | -2/+9 |
| | | |||||
| * | do not add clip skip to parameters if it's 1 or 0 | AUTOMATIC | 2022-10-09 | 1 | -1/+1 |
| | | |||||
| * | Fix issues with CLIP ignore option name change | Fampai | 2022-10-09 | 1 | -2/+2 |
| | | |||||
| * | change up #2056 to make it work how i want it to plus make xy plot write ↵ | AUTOMATIC | 2022-10-09 | 1 | -3/+2 |
| | | | | | correct values to images | ||||
| * | Sanitize infotext output (for now) | William Moorehouse | 2022-10-09 | 1 | -3/+3 |
| | | |||||
| * | Fix grabbing the model name for infotext | William Moorehouse | 2022-10-09 | 1 | -1/+1 |
| | | |||||
| * | Added extended model details to infotext | William Moorehouse | 2022-10-09 | 1 | -0/+3 |
| | | |||||
| * | additional changes for saving pnginfo for #1803 | AUTOMATIC | 2022-10-09 | 1 | -2/+4 |
| | | |||||
| * | remove line break | frostydad | 2022-10-09 | 1 | -1/+0 |
| | | |||||
| * | Fix incorrect sampler name in output | frostydad | 2022-10-09 | 1 | -1/+8 |
| | | |||||
| * | support loading .yaml config with same name as model | AUTOMATIC | 2022-10-08 | 1 | -1/+1 |
| | | | | | support EMA weights in processing (????) | ||||
| * | chore: Fix typos | Aidan Holland | 2022-10-08 | 1 | -1/+1 |
| | | |||||
| * | add 'Ignore last layers of CLIP model' option as a parameter to the infotext | AUTOMATIC | 2022-10-08 | 1 | -1/+5 |
| | | |||||
| * | fix bug where when using prompt composition, hijack_comments generated ↵ | MrCheeze | 2022-10-08 | 1 | -0/+1 |
| | | | | | before the final AND will be dropped | ||||
| * | do not let user choose his own prompt token count limit | AUTOMATIC | 2022-10-08 | 1 | -5/+0 |
| | | |||||
| * | check specifically for skipped | Trung Ngo | 2022-10-08 | 1 | -2/+1 |
| | | |||||
| * | Add button to skip the current iteration | Trung Ngo | 2022-10-08 | 1 | -0/+4 |
| | | |||||
| * | let user choose his own prompt token count limit | AUTOMATIC | 2022-10-08 | 1 | -0/+6 |
| | | |||||
| * | Added job_timestamp to Processed | Milly | 2022-10-06 | 1 | -0/+2 |
| | | | | | So `[job_timestamp]` pattern can use in saving image UI. | ||||
| * | Added styles to Processed | Milly | 2022-10-06 | 1 | -0/+2 |
| | | | | | So `[styles]` pattern can use in saving image UI. | ||||
| * | add generation parameters to images shown in web ui | AUTOMATIC | 2022-10-06 | 1 | -2/+6 |
| | | |||||
| * | Merge branch 'master' into fix-vram | Jairo Correa | 2022-10-06 | 1 | -8/+8 |
| |\ | |||||
| | * | integrate the new samplers PR | AUTOMATIC | 2022-10-06 | 1 | -3/+4 |
| | | | |||||
| | * | option to let users select which samplers they want to hide | AUTOMATIC | 2022-10-06 | 1 | -7/+6 |
| | | | |||||
| | * | added support for AND from ↵ | AUTOMATIC | 2022-10-05 | 1 | -1/+1 |
| | | | | | | | | | https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/ | ||||
| * | | Removing parts no longer needed to fix vram | Jairo Correa | 2022-10-05 | 1 | -13/+8 |
| | | | |||||
| * | | Merge branch 'master' into fix-vram | Jairo Correa | 2022-10-04 | 1 | -20/+33 |
| |\| | |||||
| | * | prompt_parser: allow spaces in schedules, add test, log/ignore errors | Rae Fu | 2022-10-04 | 1 | -5/+5 |
| | | | | | | | | | | | | | Only build the parser once (at import time) instead of for each step. doctest is run by simply executing modules/prompt_parser.py | ||||
| | * | do not touch p.seed/p.subseed during processing #1181 | AUTOMATIC | 2022-10-04 | 1 | -9/+17 |
| | | | |||||
| | * | emergency fix for img2img | AUTOMATIC | 2022-10-04 | 1 | -1/+2 |
| | | | |||||
| | * | support interrupting after the previous change | AUTOMATIC | 2022-10-04 | 1 | -1/+3 |
| | | | |||||
| | * | send all three of GFPGAN's and codeformer's models to CPU memory instead of ↵ | AUTOMATIC | 2022-10-04 | 1 | -7/+9 |
| | | | | | | | | | just one for #1283 | ||||
| * | | Merge branch 'master' into stable | Jairo Correa | 2022-10-02 | 1 | -7/+10 |
| |\| | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |