1465 Commits (eef3bc649069d6caaef1274f132de28e528bfa7d)
 

Author SHA1 Message Date
NO_ob eef3bc6490 typo 3 years ago
AUTOMATIC 73901c3f01 make attention edit only work with ctrl as was initially intended 3 years ago
AUTOMATIC 97f0727489 add First pass size always regardless of whether it was auto chosen or specified 3 years ago
AUTOMATIC 20a1f68c75 fix gadio issue with sending files between tabs 3 years ago
AUTOMATIC d3463bc59a change styling for top right corner UI
made save style button not die when you cancel
3 years ago
AUTOMATIC f7ca63937a bring back scale latent option in settings 3 years ago
AUTOMATIC 5967d07d1a fix new gradio failing to preserve image params 3 years ago
AUTOMATIC 3631adfe96 make dragging to prompt work again 3 years ago
AUTOMATIC e8729dd051 re-apply height hacks to work with new gradio 3 years ago
AUTOMATIC 4ed99d5996 bump gradio to 3.5 3 years ago
AUTOMATIC 7d6042b908 update for commandline args for btch prompts to parse string properly 3 years ago
AUTOMATIC1111 58e62312c3
Merge pull request #1446 from shirase-0/master
Tag/Option Parsing in Prompts From File
3 years ago
AUTOMATIC1111 f42e0aae6d
Merge branch 'master' into master 3 years ago
AUTOMATIC1111 d13ce89e20
Merge pull request #2573 from raefu/ckpt-cache
add --ckpt-cache option for faster model switching
3 years ago
AUTOMATIC1111 af144ebdc7
Merge branch 'master' into ckpt-cache 3 years ago
Daniel M 6a4e846710 Fix prerequisites check in webui.sh
- Check the actually used `$python_cmd` and `$GIT` executables instead
  of the hardcoded ones
- Fix typo in comment
3 years ago
AUTOMATIC f756bc540a fix #2588 breaking launch.py (. . .) 3 years ago
CookieHCl c24df4b486 Disable compiling deepbooru model
This is only necessary when you have to train,
and compiling model produces warning.
3 years ago
AUTOMATIC1111 9563636489
Merge pull request #2663 from space-nuko/fix-xyplot-steps
Fix XY-plot steps if highres fix is enabled
3 years ago
AUTOMATIC1111 5207cba56f
Merge pull request #2661 from Melanpan/master
Raise an assertion error if no training images have been found.
3 years ago
AUTOMATIC1111 ea8aa1701a
Merge branch 'master' into master 3 years ago
githublsx a13af34b90 Set to -1 when seed input is none 3 years ago
Cassy-Lee 7855993bef Move index_url args into run_pip. 3 years ago
Cassy-Lee 77bf3525f8 Update launch.py
Allow change set --index-url for pip.
3 years ago
ddPn08 0da6c18099 use "outdir_samples" if specified 3 years ago
ddPn08 cd28465bf8 do not force relative paths in image history 3 years ago
aoirusann db27b987a9 Add hint for `ctrl/alt enter`
And duplicate implementations are removed
3 years ago
ruocaled 661a61985c remove extra 100ms timeout 3 years ago
ruocaled c7cd2fda5a re-attach full screen zoom listeners 3 years ago
ruocaled b26efff8c4 allow re-open for multiple images gallery 3 years ago
ruocaled c84eef8195 fix observer disconnect logic 3 years ago
ruocaled 6b5c54c187 remove console.log 3 years ago
ruocaled 3bd40bb77f auto re-open selected image after re-generation
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.
3 years ago
AUTOMATIC c7a86f7fe9 add option to use batch size for training 3 years ago
AUTOMATIC acedbe67d2 bring history tab back, make it behave; it's still slow but won't fuck anything up until you use it 3 years ago
space-nuko a8f7722e4e Fix XY-plot steps if highres fix is enabled 3 years ago
AUTOMATIC 4bbe5d62e0 reformat lines in images_history.py 3 years ago
AUTOMATIC 4dc4265099 rename firstpass w/h to discard old user settings 3 years ago
Melan 4d19f3b7d4 Raise an assertion error if no training images have been found. 3 years ago
AUTOMATIC 368f4cc4c7 set firstpass w/h to 0 by default and rever to old behavior when any are 0 3 years ago
AUTOMATIC cd58e44051 disabling history - i knew it was slow as fuck but i didn't realize it would also show galleries on launch 3 years ago
Rae Fu e21f01f645 add checkpoint cache option to UI for faster model switching
switching time reduced from ~1500ms to ~280ms
3 years ago
AUTOMATIC 03d62538ae remove duplicate code for log loss, add step, make it read from options rather than gradio input 3 years ago
AUTOMATIC 326fe7d44b Merge remote-tracking branch 'Melanpan/master' 3 years ago
AUTOMATIC 989a552de3 remove the other Denoising 3 years ago
Naeaeaeaeae 4cc37e4cdf [xy_grid.py] add option denoising_strength 3 years ago
AUTOMATIC c250cb289c change checkpoint merger to work in a more obvious way
remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier
3 years ago
RnDMonkey 02382f7ce4 regression in xy_grid Var. seed fixing 3 years ago
ChucklesTheBeard 9b75ab144f fix typo 3 years ago
AUTOMATIC 2f0e089c7c should fix the issue with missing layers in chechpoint merger 3 years ago