e7f4808505
provide sampler by name
3 years ago
e40ba281f1
update
3 years ago
7f2095c6c8
update
3 years ago
a5611ea502
update
3 years ago
6021f7a75f
add options to custom hypernetwork layer structure
3 years ago
c2765c9bcd
Merge branch 'master' into test_resolve_conflicts
3 years ago
cbf15edbf9
remove dependence on TQDM for sampler progress/interrupt functionality
3 years ago
b7e78ef692
Image browser improve
3 years ago
ec1924ee57
additional fix for difference model merging
3 years ago
e20b7e30fe
fix for add difference model merging
3 years ago
2f448d97a9
styles.csv encoding utf8 to utf-8-sig
...
utf-8-bom for better compatibility for some programs
3 years ago
433a7525c1
remove shared option for update check (because it is not an argument of webui)
...
have launch.py examine both COMMANDLINE_ARGS as well as argv for its arguments
3 years ago
eb299527b1
Image browser
3 years ago
4c605c5174
add shared option for update check
3 years ago
02622b1919
update scripts.py
3 years ago
3003438088
Add visible for dropdown
3 years ago
de29ec0743
Remove exception handling
3 years ago
97d3ba3941
Add scripts to ui-config,json
3 years ago
d2f459c5cf
clarify the comment for the new option from #2959 and move it to UI section.
3 years ago
8b02662215
Disable auto weights swap with config option
3 years ago
cd9c6e0edf
Merge pull request #2984 from guaneec/D
...
Don't eat colons in booru tags
3 years ago
f6c758d055
Merge branch 'master' into dark-mode
3 years ago
c71008c741
Update sd_hijack_optimizations.py
3 years ago
73b5dbf72a
Update sd_hijack.py
3 years ago
84823275e8
readd xformers attnblock
3 years ago
2043c4a231
delete xformers attnblock
3 years ago
786ed49922
use legacy attnblock
3 years ago
1997ccff13
Merge branch 'master' into test_resolve_conflicts
3 years ago
8d5d863a9d
gradio and FastAPI
3 years ago
7432b6f4d2
Fix typo "celem_id" to "elem_id"
3 years ago
1df3ff25e6
Add --nowebui as a means of disabling the webui and run on the other port
3 years ago
247aeb3aaa
Put API under /sdapi/ so that routing is simpler in the future. This means that one could allow access to /sdapi/ but not the webui.
3 years ago
c3851a853d
Re-use webui fastapi application rather than requiring one or the other, not both.
3 years ago
d3338bdef1
extras extend cache key with new upscale to options
3 years ago
ab3f997c0c
Fix typo in 'choices' when loading upscaler 2 config
3 years ago
f29b16bad1
prevent API from saving
3 years ago
2e28c841f4
Oops
3 years ago
f80e914ac4
example API working with gradio
3 years ago
d62ef76614
Don't eat colons in booru tags
3 years ago
cf47d13c1e
localization support
3 years ago
695377a8b9
make modelmerger work with ui-config.json
3 years ago
665beebc08
Use of a --theme argument for more flexibility
...
Added possibility to set the theme (light or dark)
3 years ago
2b5b62e768
fix two bug
3 years ago
2272cf2f35
fix two bug
3 years ago
c408a0b41c
fix two bug
3 years ago
8c6a981d5d
Added dark mode switch
...
Launch the UI in dark mode with the --dark-mode switch
3 years ago
d42125baf6
add missing requirement for api and fix some typos
3 years ago
71d42bb44b
Update api.py
3 years ago
99013ba68a
Update processing.py
3 years ago
832b490e51
Update processing.py
3 years ago
9e02812afd
pydantic instrumentation
3 years ago
60251c9456
initial prototype by borrowing contracts
3 years ago
9d702b16f0
fix two little bug
3 years ago
2a3e7ed872
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
3 years ago
5b1394bead
speed up images history perfect
3 years ago
62edfae257
print list of embeddings on reload
3 years ago
b99d3cf6dd
make CLIP interrogate ranks output sane values
3 years ago
5c94aaf290
fix bug for latest model merge RAM improvement
3 years ago
58f3ef7733
Fix CLIP Interrogator and disable ranks for it
3 years ago
6f7b7a3dcd
only read files with .py extension from the scripts dir
3 years ago
0fd1307671
improve performance of 3-way merge on machines with not enough ram, by only accessing two of the models at a time
3 years ago
589215df22
Merge branch 'master' into test_resolve_conflicts
3 years ago
c8045c5ad4
The hide_ui_dir_config flag also restrict write attempt to path settings
3 years ago
ae0fdad64a
Merge branch 'master' into test_resolve_conflicts
3 years ago
9324cdaa31
ui fix, re organization of the code
3 years ago
a4de699e3c
Images history speed up
3 years ago
fc220a51cf
fix dir_path in some path like `D:/Pic/outputs`
3 years ago
adc0ea74e1
Better readablity of logs
3 years ago
c9836279f5
Only make output dir when creating output
3 years ago
91235d8008
Fix FileNotFoundError in history tab
...
Now only traverse images when directory exists
3 years ago
f62905fdf9
images history speed up
3 years ago
272d979d1c
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
e4f8b5f00d
ui fix
3 years ago
523140d780
ui fix
3 years ago
36a0ba357a
Added Refresh Button to embedding and hypernetwork names in Train Tab
...
Problem
everytime I modified pt files in embedding_dir or hypernetwork_dir, I
need to restart webui to have the new files shown in the dropdown of
Train Tab
Solution
refactored create_refresh_button out of create_setting_component so we
can use this method to create button next to gr.Dropdowns of embedding
name and hypernetworks
Extra Modification
hypernetwork pt are now sorted in alphabetic order
3 years ago
9258a33e37
Warn when user uses bad ui setting
3 years ago
b65a3101ce
Use default value when dropdown ui setting is bad
...
Default value is the first value of selectables.
Particually, None in styles.
3 years ago
20bf99052a
Make style configurable in ui-config.json
3 years ago
3395ba493f
Allow specifying the region of ngrok.
3 years ago
179e3ca752
honor --hide-ui-dir-config option for #2807
3 years ago
2ce27728f6
added extras batch work from directory
3 years ago
0c5fa9a681
do not reload embeddings from disk when doing textual inversion
3 years ago
5d8c59eee5
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
3 years ago
763b893f31
images history sorting files by date
3 years ago
b694bba39a
Merge remote-tracking branch 'origin/test_resolve_conflicts' into test_resolve_conflicts
3 years ago
9325c85f78
fixed dropbox update
3 years ago
97ceaa23d0
Merge branch 'master' into test_resolve_conflicts
3 years ago
3d21684ee3
Add support to other img format, fixed dropbox update
3 years ago
9a33292ce4
reload javascript files when custom script bodies
3 years ago
529afbf4d7
Update sd_hijack.py
3 years ago
74a9ee7002
fix saving images compatibility with gradio update
3 years ago
3f5c3b981e
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
ad9bc604a8
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
0d4f5db235
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
9b7705e057
Update modules/aesthetic_clip.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
4387e4fe64
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
b6e3b96dab
Change vector size footer label
3 years ago
ddf6899df0
generalise to popular lossless formats
3 years ago
9a1dcd78ed
add webp for embed load
3 years ago
939f16529a
only save 1 image per embedding
3 years ago
9e846083b7
add vector size to embed text
3 years ago
7b7561f6e4
Merge branch 'master' into test_resolve_conflicts
3 years ago
703e6d9e4e
check NaN for hypernetwork tuning
3 years ago
5fd638f14d
fix download section layout
3 years ago
37d7ffb415
fix to tokens lenght, addend embs generator, add new features to edit the embedding before the generation using text
3 years ago
eef3bc6490
typo
3 years ago
97f0727489
add First pass size always regardless of whether it was auto chosen or specified
3 years ago
20a1f68c75
fix gadio issue with sending files between tabs
3 years ago
d3463bc59a
change styling for top right corner UI
...
made save style button not die when you cancel
3 years ago
f7ca63937a
bring back scale latent option in settings
3 years ago
5967d07d1a
fix new gradio failing to preserve image params
3 years ago
e8729dd051
re-apply height hacks to work with new gradio
3 years ago
af144ebdc7
Merge branch 'master' into ckpt-cache
3 years ago
c24df4b486
Disable compiling deepbooru model
...
This is only necessary when you have to train,
and compiling model produces warning.
3 years ago
ea8aa1701a
Merge branch 'master' into master
3 years ago
a13af34b90
Set to -1 when seed input is none
3 years ago
0da6c18099
use "outdir_samples" if specified
3 years ago
cd28465bf8
do not force relative paths in image history
3 years ago
db27b987a9
Add hint for `ctrl/alt enter`
...
And duplicate implementations are removed
3 years ago
c7a86f7fe9
add option to use batch size for training
3 years ago
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
4bbe5d62e0
reformat lines in images_history.py
3 years ago
4dc4265099
rename firstpass w/h to discard old user settings
3 years ago
4d19f3b7d4
Raise an assertion error if no training images have been found.
3 years ago
368f4cc4c7
set firstpass w/h to 0 by default and rever to old behavior when any are 0
3 years ago
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
e21f01f645
add checkpoint cache option to UI for faster model switching
...
switching time reduced from ~1500ms to ~280ms
3 years ago
03d62538ae
remove duplicate code for log loss, add step, make it read from options rather than gradio input
3 years ago
326fe7d44b
Merge remote-tracking branch 'Melanpan/master'
3 years ago
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
2f0e089c7c
should fix the issue with missing layers in chechpoint merger
3 years ago
c344ba3b32
add option to read generation params for learning previews from txt2img
3 years ago
bb295f5478
rework the code for lowram a bit
3 years ago
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)
3 years ago
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)
3 years ago
5f87dd1ee0
Add option to prevent empty spots in grid (2/2)
3 years ago
43f926aad1
Add option to prevent empty spots in grid (1/2)
3 years ago
2fb9891af3
Change grid row count autodetect to prevent empty spots
...
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.
3 years ago
6b77af7a43
Merge pull request #2396 from yfszzx/master
...
Add a "History" tab
3 years ago
67f447ddcc
possibility to load checkpoint, clip skip, and hypernet from infotext
3 years ago
0aec19d783
make pasting into img2img prompt work
...
make image params request not use temp files
3 years ago
a156c097ab
Merge branch 'param-loading'
3 years ago
e644b5a80b
remove scale latent and no-crop options from hires fix
...
support copy-pasting new parameters for hires fix
3 years ago
b382de2d77
Fixed Scale ratio problem
3 years ago
40d1c6e423
Option between stretch and crop for Highres. fix
3 years ago
b2261b53ae
Added first_pass_width and height as adjustable inputs to "High Res Fix"
3 years ago
9e5ca5077f
extra message for unpicking fails
3 years ago
fdef8253a4
Add 'interrogate' and 'all' choices to --use-cpu
...
* Add 'interrogate' and 'all' choices to --use-cpu
* Change type for --use-cpu argument to str.lower, so that choices are case insensitive
3 years ago
bb57f30c2d
init
3 years ago
f7712e28e5
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
fdecb63685
add an ability to merge three checkpoints
3 years ago
d48f3470c8
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
3 years ago
4a37c7eede
fix deep nesting directories problem
3 years ago
7c8903367c
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
a1489f9428
images history fix all known bug
3 years ago
08b3f7aef1
emergency fix for broken send to buttons
3 years ago
354ef0da3b
add hypernetwork multipliers
3 years ago
a10b0e11fc
options to refresh list of models and hypernetworks
3 years ago
bb7baf6b9c
add option to change what's shown in quicksettings bar
3 years ago
8636b50aea
Add learn_rate to csv and removed a left-over debug statement
3 years ago
fed7f0e281
Revert "fix prompt in log.csv"
...
This reverts commit e4b5d1696429ab78dae9779420ce6ec4cd9c5f67.
3 years ago
a3f02e4690
fix prompt in log.csv
3 years ago
8711c2fe01
Fix metadata contents
3 years ago
aeacbac218
Fix save error
3 years ago
fde7fefa2e
update #2336 to prevent reading params.txt when --hide-ui-dir-config option is enabled (for servers, since this will let some users access others' params)
3 years ago
e72adc999b
Restore last generation params
3 years ago
04c0e643f2
Merge branch 'master' of https://github.com/HunterVacui/stable-diffusion-webui
3 years ago
4f73e057a9
Merge pull request #2324 from HunterVacui/interrogate_include_ranks_in_output
...
Interrogate: add option to include ranks in output
3 years ago
78592d404a
remove interrogate option I accidentally deleted
3 years ago
0186db178e
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
716a9e034f
images history delete a number of images consecutively next
3 years ago
54e0051bdd
Add drag/drop param loading.
...
Drop an image or generational text onto the prompt bar, it loads the info for parsing.
3 years ago
1cfc2a1898
Save a csv containing the loss while training
3 years ago
514456101b
[3/?] [wip] fix incorrect variable reference
...
still needs testing
3 years ago
f776254b12
[2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenames
3 years ago
efefa4862c
[1/?] [wip] Reintroduce opts.interrogate_return_ranks
...
looks functionally correct, needs testing
Needs particular testing care around whether the colon usage (:) will break anything in whatever new use cases were introduced by https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2143
3 years ago
fb3cefb348
Merge remote-tracking branch 'upstream/master' into interrogate_include_ranks_in_output
3 years ago
698d303b04
deepbooru: added option to use spaces or underscores
...
deepbooru: added option to quote (\) in tags
deepbooru/BLIP: write caption to file instead of image filename
deepbooru/BLIP: now possible to use both for captions
deepbooru: process is stopped even if an exception occurs
3 years ago
c3c8eef9fd
train: change filename processing to be more simple and configurable
...
train: make it possible to make text files with prompts
train: rework scheduler so that there's less repeating code in textual inversion and hypernets
train: move epochs setting to options
3 years ago
df97947b21
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
3 years ago
324e6ed5d1
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
a2aa2a68bc
images history improvement
3 years ago
a1a94b8b5f
images history improvement
3 years ago
c87c3b9c11
test
3 years ago
cc5803603b
Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-images
...
Add option to store TI embeddings in png chunks, and load from same.
3 years ago
511ca57e37
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
3 years ago
e05573e1ad
images history improvement
3 years ago
10a2de644f
formatting
3 years ago
50be33e953
formatting
3 years ago
429442f4a6
fix iterator bug for #2295
3 years ago
80f3cf2bb2
Account when lines are mismatched
3 years ago
ee015a1af6
change textual inversion tab to train
...
remake train interface to use tabs
3 years ago
2d006ce16c
xy_grid: Find hypernetwork by closest name
3 years ago
dc1432e0dd
Merge branch 'master' into feature/scale_to
3 years ago
57e03cdd24
Ensure the directory exists before saving to it
...
The directory for the images saved with the Save button may still not exist, so it needs to be created prior to opening the log.csv file.
3 years ago
336bd8703c
just add the deepdanbooru settings unconditionally
3 years ago
ee10c41e2a
Merge remote-tracking branch 'origin/steve3d'
3 years ago
2e2d45b281
Merge pull request #2143 from JC-Array/deepdanbooru_pre_process
...
deepbooru tags for textual inversion preproccessing
3 years ago
fec2221eea
Truncate error text to fix service lockup / stall
...
What:
* Update wrap_gradio_call to add a limit to the maximum amount of text output
Why:
* wrap_gradio_call currently prints out a list of the arguments provided to the failing function.
* if that function is save_image, this causes the entire image to be printed to stderr
* If the image is large, this can cause the service to lock up while attempting to print all the text
* It is easy to generate large images using the x/y plot script
* it is easy to encounter image save exceptions, including if the output directory does not exist / cannot be written to, or if the file is too big
* The huge amount of log spam is confusing and not particularly helpful
3 years ago
6ac2ec2b78
create dir for hypernetworks
3 years ago
arcticfaded
discus0434
MalumaDev
AUTOMATIC
yfszzx
w-e-w
DepFA
ふぁ
trufty
C43H66N12O12S2
Mykeehu
Ryan Voots
Jordan Hall
guaneec
Michoko
DenkingOfficial
MrCheeze
SGKoishi
DancingSnow
CookieHCl
Junpeng Qiu
ddPn08
winterspringsummer
zhengxiaoyao0716
AngelBottomless
ruocaled
NO_ob
githublsx
aoirusann
Melan
Rae Fu
Ljzd-PRO
Gugubo
Buckzor
brkirch
Greg Fuller
Trung Ngo
d8ahazard
hentailord85ez
Milly