| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Merge pull request #2573 from raefu/ckpt-cache | AUTOMATIC1111 | 2022-10-15 | 2 | -26/+33 |
| |\ | | | | | add --ckpt-cache option for faster model switching | ||||
| | * | Merge branch 'master' into ckpt-cache | AUTOMATIC1111 | 2022-10-15 | 26 | -166/+836 |
| | |\ | |/ |/| | |||||
| * | | Fix prerequisites check in webui.sh | Daniel M | 2022-10-15 | 1 | -2/+2 |
| | | | | | | | | | | | | | - Check the actually used `$python_cmd` and `$GIT` executables instead of the hardcoded ones - Fix typo in comment | ||||
| * | | fix #2588 breaking launch.py (. . .) | AUTOMATIC | 2022-10-15 | 1 | -2/+3 |
| | | | |||||
| * | | Disable compiling deepbooru model | CookieHCl | 2022-10-15 | 1 | -1/+1 |
| | | | | | | | | | | | This is only necessary when you have to train, and compiling model produces warning. | ||||
| * | | Merge pull request #2663 from space-nuko/fix-xyplot-steps | AUTOMATIC1111 | 2022-10-15 | 1 | -1/+4 |
| |\ \ | | | | | | | Fix XY-plot steps if highres fix is enabled | ||||
| | * | | Fix XY-plot steps if highres fix is enabled | space-nuko | 2022-10-14 | 1 | -1/+4 |
| | | | | |||||
| * | | | Merge pull request #2661 from Melanpan/master | AUTOMATIC1111 | 2022-10-15 | 1 | -0/+1 |
| |\ \ \ | | | | | | | | | Raise an assertion error if no training images have been found. | ||||
| | * \ \ | Merge branch 'master' into master | AUTOMATIC1111 | 2022-10-15 | 11 | -139/+219 |
| | |\ \ \ | |/ / / |/| | | | |||||
| * | | | | Set to -1 when seed input is none | githublsx | 2022-10-15 | 1 | -1/+1 |
| | | | | | |||||
| * | | | | Move index_url args into run_pip. | Cassy-Lee | 2022-10-15 | 1 | -8/+8 |
| | | | | | |||||
| * | | | | Update launch.py | Cassy-Lee | 2022-10-15 | 1 | -6/+7 |
| | | | | | | | | | | | | | Allow change set --index-url for pip. | ||||
| * | | | | use "outdir_samples" if specified | ddPn08 | 2022-10-15 | 1 | -1/+3 |
| | | | | | |||||
| * | | | | do not force relative paths in image history | ddPn08 | 2022-10-15 | 1 | -1/+1 |
| | | | | | |||||
| * | | | | Add hint for `ctrl/alt enter` | aoirusann | 2022-10-15 | 3 | -14/+10 |
| | | | | | | | | | | | | | | | | | And duplicate implementations are removed | ||||
| * | | | | remove extra 100ms timeout | ruocaled | 2022-10-15 | 1 | -3/+1 |
| | | | | | |||||
| * | | | | re-attach full screen zoom listeners | ruocaled | 2022-10-15 | 1 | -0/+3 |
| | | | | | |||||
| * | | | | allow re-open for multiple images gallery | ruocaled | 2022-10-15 | 1 | -3/+4 |
| | | | | | |||||
| * | | | | fix observer disconnect logic | ruocaled | 2022-10-15 | 1 | -5/+7 |
| | | | | | |||||
| * | | | | remove console.log | ruocaled | 2022-10-15 | 1 | -1/+0 |
| | | | | | |||||
| * | | | | auto re-open selected image after re-generation | ruocaled | 2022-10-15 | 1 | -0/+32 |
| | | | | | | | | | | | | | | | | | | | | | attach an observer of gallery when generation in progress, if there was a image selected in gallery and gallery has only 1 image, auto re-select/open that image. This matches behavior of prior to Gradio 3.4.1 version bump, is a quality of life feature many people enjoyed. | ||||
| * | | | | add option to use batch size for training | AUTOMATIC | 2022-10-15 | 4 | -30/+54 |
| | | | | | |||||
| * | | | | bring history tab back, make it behave; it's still slow but won't fuck ↵ | AUTOMATIC | 2022-10-14 | 2 | -6/+14 |
| | | | | | | | | | | | | | | | | | anything up until you use it | ||||
| * | | | | reformat lines in images_history.py | AUTOMATIC | 2022-10-14 | 1 | -84/+98 |
| | |/ / |/| | | |||||
| * | | | rename firstpass w/h to discard old user settings | AUTOMATIC | 2022-10-14 | 1 | -2/+2 |
| | | | | |||||
| | * | | Raise an assertion error if no training images have been found. | Melan | 2022-10-14 | 1 | -1/+2 |
| |/ / | |||||
| * | | set firstpass w/h to 0 by default and rever to old behavior when any are 0 | AUTOMATIC | 2022-10-14 | 2 | -21/+32 |
| | | | |||||
| * | | disabling history - i knew it was slow as fuck but i didn't realize it would ↵ | AUTOMATIC | 2022-10-14 | 1 | -2/+3 |
| | | | | | | | | | also show galleries on launch | ||||
| * | | remove duplicate code for log loss, add step, make it read from options ↵ | AUTOMATIC | 2022-10-14 | 4 | -32/+38 |
| | | | | | | | | | rather than gradio input | ||||
| * | | Merge remote-tracking branch 'Melanpan/master' | AUTOMATIC | 2022-10-14 | 3 | -0/+34 |
| |\ \ | |||||
| | * | | Add learn_rate to csv and removed a left-over debug statement | Melan | 2022-10-13 | 2 | -5/+6 |
| | | | | |||||
| | * | | Save a csv containing the loss while training | Melan | 2022-10-12 | 3 | -2/+35 |
| | | | | |||||
| * | | | remove the other Denoising | AUTOMATIC | 2022-10-14 | 1 | -1/+0 |
| | | | | |||||
| * | | | [xy_grid.py] add option denoising_strength | Naeaeaeaeae | 2022-10-14 | 1 | -0/+1 |
| | | | | |||||
| * | | | change checkpoint merger to work in a more obvious way | AUTOMATIC | 2022-10-14 | 3 | -23/+9 |
| | | | | | | | | | | | | | remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier | ||||
| * | | | regression in xy_grid Var. seed fixing | RnDMonkey | 2022-10-14 | 1 | -1/+1 |
| | | | | |||||
| * | | | fix typo | ChucklesTheBeard | 2022-10-14 | 1 | -1/+1 |
| | | | | |||||
| * | | | should fix the issue with missing layers in chechpoint merger | AUTOMATIC | 2022-10-14 | 1 | -1/+6 |
| | | | | |||||
| * | | | restore borders for prompts | AUTOMATIC | 2022-10-14 | 1 | -8/+0 |
| | | | | |||||
| * | | | add option to read generation params for learning previews from txt2img | AUTOMATIC | 2022-10-14 | 3 | -15/+51 |
| | | | | |||||
| * | | | rework the code for lowram a bit | AUTOMATIC | 2022-10-14 | 2 | -11/+4 |
| | | | | |||||
| * | | | load models to VRAM when using `--lowram` param | Ljzd-PRO | 2022-10-14 | 1 | -2/+13 |
| | | | | | | | | | | load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server) | ||||
| * | | | add `--lowram` parameter | Ljzd-PRO | 2022-10-14 | 1 | -0/+1 |
| | | | | | | | | | | load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server) | ||||
| * | | | Add option to prevent empty spots in grid (2/2) | Gugubo | 2022-10-14 | 1 | -1/+4 |
| | | | | |||||
| * | | | Add option to prevent empty spots in grid (1/2) | Gugubo | 2022-10-14 | 1 | -0/+1 |
| | | | | |||||
| * | | | Change grid row count autodetect to prevent empty spots | Gugubo | 2022-10-14 | 1 | -2/+3 |
| | | | | | | | | | | | | | Instead of just rounding (sometimes resulting in grids with "empty" spots), find a divisor. For example: 8 images will now result in a 4x2 grid instead of a 3x3 with one empty spot. | ||||
| * | | | remove user's liners from .gitigbore - those go into .git/info/exclude | AUTOMATIC | 2022-10-14 | 1 | -2/+0 |
| | | | | |||||
| * | | | Merge pull request #2396 from yfszzx/master | AUTOMATIC1111 | 2022-10-14 | 4 | -0/+375 |
| |\ \ \ | | | | | | | | | Add a "History" tab | ||||
| | * \ \ | Merge branch 'AUTOMATIC1111:master' into master | 不会画画的中医不是好程序员 | 2022-10-14 | 3 | -14/+33 |
| | |\ \ \ | |||||
| | * \ \ \ | Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus | yfszzx | 2022-10-14 | 17 | -60/+210 |
| | |\ \ \ \ | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |