3631adfe96
make dragging to prompt work again
2022-10-15 12:58:53 +03:00
e8729dd051
re-apply height hacks to work with new gradio
2022-10-15 12:54:23 +03:00
4ed99d5996
bump gradio to 3.5
2022-10-15 12:10:52 +03:00
7d6042b908
update for commandline args for btch prompts to parse string properly
2022-10-15 12:00:31 +03:00
58e62312c3
Merge pull request #1446 from shirase-0/master
...
Tag/Option Parsing in Prompts From File
2022-10-15 10:47:50 +03:00
f42e0aae6d
Merge branch 'master' into master
2022-10-15 10:47:26 +03:00
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
af144ebdc7
Merge branch 'master' into ckpt-cache
2022-10-15 10:35:18 +03:00
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
f756bc540a
fix #2588 breaking launch.py (. . .)
2022-10-15 10:28:26 +03:00
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
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
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
ea8aa1701a
Merge branch 'master' into master
2022-10-15 10:13:16 +03:00
a13af34b90
Set to -1 when seed input is none
2022-10-15 10:12:16 +03:00
7855993bef
Move index_url args into run_pip.
2022-10-15 10:10:22 +03:00
77bf3525f8
Update launch.py
...
Allow change set --index-url for pip.
2022-10-15 10:10:22 +03:00
0da6c18099
use "outdir_samples" if specified
2022-10-15 10:07:45 +03:00
cd28465bf8
do not force relative paths in image history
2022-10-15 10:07:45 +03:00
db27b987a9
Add hint for `ctrl/alt enter`
...
And duplicate implementations are removed
2022-10-15 09:59:40 +03:00
661a61985c
remove extra 100ms timeout
2022-10-15 09:32:01 +03:00
c7cd2fda5a
re-attach full screen zoom listeners
2022-10-15 09:32:01 +03:00
b26efff8c4
allow re-open for multiple images gallery
2022-10-15 09:32:01 +03:00
c84eef8195
fix observer disconnect logic
2022-10-15 09:32:01 +03:00
6b5c54c187
remove console.log
2022-10-15 09:32:01 +03:00
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
c7a86f7fe9
add option to use batch size for training
2022-10-15 09:24:59 +03:00
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
a8f7722e4e
Fix XY-plot steps if highres fix is enabled
2022-10-14 14:26:38 -07:00
4bbe5d62e0
reformat lines in images_history.py
2022-10-15 00:25:09 +03:00
4dc4265099
rename firstpass w/h to discard old user settings
2022-10-15 00:21:48 +03:00
4d19f3b7d4
Raise an assertion error if no training images have been found.
2022-10-14 22:45:26 +02:00
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
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
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
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
326fe7d44b
Merge remote-tracking branch 'Melanpan/master'
2022-10-14 22:14:50 +03:00
989a552de3
remove the other Denoising
2022-10-14 22:04:08 +03:00
4cc37e4cdf
[xy_grid.py] add option denoising_strength
2022-10-14 22:03:33 +03:00
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
02382f7ce4
regression in xy_grid Var. seed fixing
2022-10-14 22:02:21 +03:00
9b75ab144f
fix typo
2022-10-14 21:26:54 +03:00
2f0e089c7c
should fix the issue with missing layers in chechpoint merger
2022-10-14 21:20:28 +03:00
6cdf55627c
restore borders for prompts
2022-10-14 21:12:52 +03:00
c344ba3b32
add option to read generation params for learning previews from txt2img
2022-10-14 20:31:49 +03:00
bb295f5478
rework the code for lowram a bit
2022-10-14 20:03:41 +03:00
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
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
5f87dd1ee0
Add option to prevent empty spots in grid (2/2)
2022-10-14 19:54:24 +03:00
43f926aad1
Add option to prevent empty spots in grid (1/2)
2022-10-14 19:54:24 +03:00
AUTOMATIC