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