Commit graph

1610 commits

Author SHA1 Message Date
AUTOMATIC
f7ca63937a bring back scale latent option in settings 2022-10-15 13:23:12 +03:00
AUTOMATIC
5967d07d1a fix new gradio failing to preserve image params 2022-10-15 13:11:28 +03:00
AUTOMATIC
3631adfe96 make dragging to prompt work again 2022-10-15 12:58:53 +03:00
AUTOMATIC
e8729dd051 re-apply height hacks to work with new gradio 2022-10-15 12:54:23 +03:00
AUTOMATIC
4ed99d5996 bump gradio to 3.5 2022-10-15 12:10:52 +03:00
AUTOMATIC
7d6042b908 update for commandline args for btch prompts to parse string properly 2022-10-15 12:00:31 +03:00
AUTOMATIC1111
58e62312c3
Merge pull request #1446 from shirase-0/master
Tag/Option Parsing in Prompts From File
2022-10-15 10:47:50 +03:00
AUTOMATIC1111
f42e0aae6d
Merge branch 'master' into master 2022-10-15 10:47:26 +03:00
AUTOMATIC1111
d13ce89e20
Merge pull request #2573 from raefu/ckpt-cache
add --ckpt-cache option for faster model switching
2022-10-15 10:35:26 +03:00
AUTOMATIC1111
af144ebdc7
Merge branch 'master' into ckpt-cache 2022-10-15 10:35:18 +03:00
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
2022-10-15 10:29:41 +03:00
AUTOMATIC
f756bc540a fix #2588 breaking launch.py (. . .) 2022-10-15 10:28:26 +03:00
CookieHCl
c24df4b486 Disable compiling deepbooru model
This is only necessary when you have to train,
and compiling model produces warning.
2022-10-15 10:21:22 +03:00
AUTOMATIC1111
9563636489
Merge pull request #2663 from space-nuko/fix-xyplot-steps
Fix XY-plot steps if highres fix is enabled
2022-10-15 10:20:29 +03:00
AUTOMATIC1111
5207cba56f
Merge pull request #2661 from Melanpan/master
Raise an assertion error if no training images have been found.
2022-10-15 10:13:23 +03:00
AUTOMATIC1111
ea8aa1701a
Merge branch 'master' into master 2022-10-15 10:13:16 +03:00
githublsx
a13af34b90 Set to -1 when seed input is none 2022-10-15 10:12:16 +03:00
Cassy-Lee
7855993bef Move index_url args into run_pip. 2022-10-15 10:10:22 +03:00
Cassy-Lee
77bf3525f8 Update launch.py
Allow change set --index-url for pip.
2022-10-15 10:10:22 +03:00
ddPn08
0da6c18099 use "outdir_samples" if specified 2022-10-15 10:07:45 +03:00
ddPn08
cd28465bf8 do not force relative paths in image history 2022-10-15 10:07:45 +03:00
aoirusann
db27b987a9 Add hint for ctrl/alt enter
And duplicate implementations are removed
2022-10-15 09:59:40 +03:00
ruocaled
661a61985c remove extra 100ms timeout 2022-10-15 09:32:01 +03:00
ruocaled
c7cd2fda5a re-attach full screen zoom listeners 2022-10-15 09:32:01 +03:00
ruocaled
b26efff8c4 allow re-open for multiple images gallery 2022-10-15 09:32:01 +03:00
ruocaled
c84eef8195 fix observer disconnect logic 2022-10-15 09:32:01 +03:00
ruocaled
6b5c54c187 remove console.log 2022-10-15 09:32:01 +03:00
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.
2022-10-15 09:32:01 +03:00
AUTOMATIC
c7a86f7fe9 add option to use batch size for training 2022-10-15 09:24:59 +03:00
AUTOMATIC
acedbe67d2 bring history tab back, make it behave; it's still slow but won't fuck anything up until you use it 2022-10-15 00:43:15 +03:00
space-nuko
a8f7722e4e Fix XY-plot steps if highres fix is enabled 2022-10-14 14:26:38 -07:00
AUTOMATIC
4bbe5d62e0 reformat lines in images_history.py 2022-10-15 00:25:09 +03:00
AUTOMATIC
4dc4265099 rename firstpass w/h to discard old user settings 2022-10-15 00:21:48 +03:00
Melan
4d19f3b7d4 Raise an assertion error if no training images have been found. 2022-10-14 22:45:26 +02:00
AUTOMATIC
368f4cc4c7 set firstpass w/h to 0 by default and rever to old behavior when any are 0 2022-10-14 23:19:05 +03:00
AUTOMATIC
cd58e44051 disabling history - i knew it was slow as fuck but i didn't realize it would also show galleries on launch 2022-10-14 23:17:28 +03:00
Rae Fu
e21f01f645 add checkpoint cache option to UI for faster model switching
switching time reduced from ~1500ms to ~280ms
2022-10-14 14:09:23 -06:00
AUTOMATIC
03d62538ae remove duplicate code for log loss, add step, make it read from options rather than gradio input 2022-10-14 22:43:55 +03:00
AUTOMATIC
326fe7d44b Merge remote-tracking branch 'Melanpan/master' 2022-10-14 22:14:50 +03:00
AUTOMATIC
989a552de3 remove the other Denoising 2022-10-14 22:04:08 +03:00
Naeaeaeaeae
4cc37e4cdf [xy_grid.py] add option denoising_strength 2022-10-14 22:03:33 +03:00
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
2022-10-14 22:02:32 +03:00
RnDMonkey
02382f7ce4 regression in xy_grid Var. seed fixing 2022-10-14 22:02:21 +03:00
ChucklesTheBeard
9b75ab144f fix typo 2022-10-14 21:26:54 +03:00
AUTOMATIC
2f0e089c7c should fix the issue with missing layers in chechpoint merger 2022-10-14 21:20:28 +03:00
AUTOMATIC
6cdf55627c restore borders for prompts 2022-10-14 21:12:52 +03:00
AUTOMATIC
c344ba3b32 add option to read generation params for learning previews from txt2img 2022-10-14 20:31:49 +03:00
AUTOMATIC
bb295f5478 rework the code for lowram a bit 2022-10-14 20:03:41 +03:00
Ljzd-PRO
4a216ded43 load models to VRAM when using --lowram param
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
2022-10-14 19:57:23 +03:00
Ljzd-PRO
a8eeb2b7ad add --lowram parameter
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
2022-10-14 19:57:23 +03:00