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
d717eb079c
Interrogate: add option to include ranks in output
...
Since the UI also allows users to specify ranks, it can be useful to show people what ranks are being returned by interrogate
This can also give much better results when feeding the interrogate results back into either img2img or txt2img, especially when trying to generate a specific character or scene for which you have a similar concept image
Testing Steps:
Launch Webui with command line arg: --deepdanbooru
Navigate to img2img tab, use interrogate DeepBooru, verify tags appears as before. Use "Interrogate CLIP", verify prompt appears as before
Navigate to Settings tab, enable new option, click "apply settings"
Navigate to img2img, Interrogate DeepBooru again, verify that weights appear and are properly formatted. Note that "Interrogate CLIP" prompt is still unchanged
In my testing, this change has no effect to "Interrogate CLIP", as it seems to generate a sentence-structured caption, and not a set of tags.
(reproduce changes from 6ed4faac46
3 years ago
65b973ac4e
Update shared.py
...
Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab.
3 years ago
f53f703aeb
resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled
3 years ago
963d986396
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process
3 years ago
6be32b31d1
reports that training with medvram is possible.
3 years ago
66ec505975
add file based test
3 years ago
7e6a6e00ad
Add files via upload
3 years ago
5f3317376b
spacing
3 years ago
91d7ee0d09
update imports
3 years ago
aa75d5cfe8
correct conflict resolution typo
3 years ago
d6fcc6b87b
apply lr schedule to hypernets
3 years ago
db71290d26
remove old caption method
3 years ago
61788c0538
shift embedding logic out of textual_inversion
3 years ago
419e539fe3
Merge branch 'learning_rate-scheduling' into learnschedule
3 years ago
e5fbf5c755
remove embedding related image functions from images
3 years ago
c080f52cea
move embedding logic to separate file
3 years ago
6a9ea5b41c
prevent extra modules from being saved/loaded with hypernet
3 years ago
d4ea5f4d86
add an option to unload models during hypernetwork training to save VRAM
3 years ago
6d09b8d1df
produce error when training with medvram/lowvram enabled
3 years ago
ff4ef13dd5
removed unneeded print
3 years ago
d682444ecc
add option to select hypernetwork modules when creating
3 years ago
4f96ffd0b5
Merge pull request #2201 from alg-wiki/textual__inversion
...
Textual Inversion: Preprocess and Training will only pick-up image files instead
3 years ago
861db783c7
Use apply_hypernetwork function
3 years ago
574c8e554a
Add InvokeAI and lstein to credits, add back CUDA support
3 years ago
98fd5cde72
Add check for psutil
3 years ago
c0484f1b98
Add cross-attention optimization from InvokeAI
...
* Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS)
* Add command line option for it
* Make it default when CUDA is unavailable
3 years ago
f7e86aa420
Merge pull request #2227 from papuSpartan/master
...
Refresh list of models/ckpts upon hitting restart gradio in the setti…
3 years ago
1eaad95533
Merge branch 'master' into embed-embeddings-in-images
3 years ago
66b7d7584f
become even stricter with pickles
...
no pickle shall pass
thank you again, RyotaK
3 years ago
d01a2d0156
move list refresh to webui.py and add stdout indicating it's doing so
3 years ago
a36dea9596
Merge branch 'master' into master
3 years ago
b0583be088
more renames
3 years ago
873efeed49
rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have
3 years ago
a004d1a855
Added new line at the end of ngrok.py
3 years ago
5992564448
Cleaned ngrok integration
3 years ago
861297cefe
add a space holder
3 years ago
87b77cad5f
Layout fix
3 years ago
87d63bbab5
images history improvement
3 years ago
eacc03b167
Fix typo in comments
3 years ago
1eae307607
Remove debug code for checking that first sigma value is same after code cleanup
3 years ago
92d7a13885
Handle different parameters for DPM fast & adaptive
3 years ago
594ab4ba53
images history improvement
3 years ago
7b1db45e1f
images history improvement
3 years ago
530103b586
fixes related to merge
3 years ago
8bacbca0a1
Removed my local edits to checkpoint image generation
3 years ago
b2368a3bce
Switched to exception handling
3 years ago
5de806184f
Merge branch 'master' into hypernetwork-training
3 years ago
948533950c
replace duplicate code with a function
3 years ago
5e2627a1a6
Comma backtrack padding ( #2192 )
...
Comma backtrack padding
3 years ago
8617396c6d
Added slider for deepbooru score threshold in settings
3 years ago
8b7d3f1bef
Make the ctrl+enter shortcut use the generate button on the current tab
3 years ago
7aa8fcac1e
use simple lcg in xor
3 years ago
1add3cff84
Refresh list of models/ckpts upon hitting restart gradio in the settings pane
3 years ago
bb932dbf9f
added alpha sort and threshold variables to create process method in preprocessing
3 years ago
47f5e216da
Merge branch 'deepdanbooru_pre_process' into master
3 years ago
76ef3d75f6
added deepbooru settings (threshold and sort by alpha or likelyhood)
3 years ago
e0fbe6d27e
colour depth conversion fix
3 years ago
767202a4c3
add dependency
3 years ago
315d5a8ed9
update data dis[play style
3 years ago
b980e7188c
corrected tag return in get_deepbooru_tags
3 years ago
a1a05ad2d1
import time missing, added to deepbooru fixxing error on get_deepbooru_tags
3 years ago
907a88b2d0
Added .webp .bmp
3 years ago
2536ecbb17
Refactored learning rate code
3 years ago
f98338faa8
add an option to not add watermark to created images
3 years ago
f0ab972f85
Merge branch 'master' into textual__inversion
3 years ago
bc3e183b73
Textual Inversion: Preprocess and Training will only pick-up image files
3 years ago
1d64976dbc
Simplify crop logic
3 years ago
727e4d1086
no to different messages plus fix using != to compare to None
3 years ago
b3d3b335cf
Merge pull request #2131 from ssysm/upstream-master
...
Add VAE Path Arguments
3 years ago
39919c40dd
add eta noise seed delta option
3 years ago
af62ad4d25
change vae loading method
3 years ago
ed769977f0
add swinir v2 support
3 years ago
ece27fe989
Add files via upload
3 years ago
3e7a981194
remove functorch
3 years ago
623251ce2b
allow pascal onwards
3 years ago
9d33baba58
Always show previous mask and fix extras_send dest
3 years ago
d5c14365fd
Add back in output hidden states parameter
3 years ago
460bbae587
Pad beginning of textual inversion embedding
3 years ago
b340439586
Unlimited Token Works
...
Unlimited tokens actually work now. Works with textual inversion too. Replaces the previous not-so-much-working implementation.
3 years ago
f347ddfd80
Remove max_batch_count from ui.py
3 years ago
df6d0d9286
convert back to rgb as some hosts add alpha
3 years ago
707a431100
add pixel data footer
3 years ago
ce2d7f7eac
Merge branch 'master' into embed-embeddings-in-images
3 years ago
7a20f914ed
Custom Width and Height
3 years ago
6ad3a53e36
Fixed progress bar output for epoch
3 years ago
ea00c1624b
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
3 years ago
8f1efdc130
--no-half-vae pt2
3 years ago
04c745ea4f
Custom Width and Height
3 years ago
7349088d32
--no-half-vae
3 years ago
1e18a5ffcc
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
23f2989799
images history over
3 years ago
2f94331df2
removed change in last commit, simplified to adding the visible argument to process_caption_deepbooru and it set to False if deepdanbooru argument is not set
3 years ago
4ee7519fc2
Fixed progress bar output for epoch
3 years ago
8ec069e64d
removed duplicate run_preprocess.click by creating run_preprocess_inputs list and appending deepbooru variable to input list if in scope
3 years ago
3110f895b2
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
3 years ago
8a7c07a214
show image history
3 years ago
8acc901ba3
Newer versions of PyTorch use TypedStorage instead
...
Pytorch 1.13 and later will rename _TypedStorage to TypedStorage, so check for TypedStorage and use _TypedStorage if it is not available. Currently this is needed so that nightly builds of PyTorch work correctly.
3 years ago
1f92336be7
refactored the deepbooru module to improve speed on running multiple interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
3 years ago
6fdad291bd
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master
3 years ago
cc92dc1f8d
add vae path args
3 years ago
arcticfaded
yfszzx
DepFA
AUTOMATIC
DenkingOfficial
MrCheeze
MalumaDev
SGKoishi
DancingSnow
CookieHCl
Junpeng Qiu
ddPn08
winterspringsummer
zhengxiaoyao0716
C43H66N12O12S2
AngelBottomless
ruocaled
NO_ob
githublsx
aoirusann
Melan
Rae Fu
Ljzd-PRO
Gugubo
Buckzor
brkirch
Greg Fuller
Trung Ngo
d8ahazard
hentailord85ez
Milly
supersteve3d
JC_Array
JC-Array
papuSpartan
JamnedZ
Ben
Martin Cairns
alg-wiki
Kenneth
Jairo Correa
Fampai
alg-wiki
Justin Maier
ssysm
Vladimir Repin
RW21