939f16529a
only save 1 image per embedding
2022-10-15 17:23:39 +03:00
9e846083b7
add vector size to embed text
2022-10-15 17:23:39 +03:00
703e6d9e4e
check NaN for hypernetwork tuning
2022-10-15 17:15:26 +03:00
5fd638f14d
fix download section layout
2022-10-15 17:14:58 +03:00
eef3bc6490
typo
2022-10-15 16:13:13 +03:00
97f0727489
add First pass size always regardless of whether it was auto chosen or specified
2022-10-15 15:47:02 +03:00
20a1f68c75
fix gadio issue with sending files between tabs
2022-10-15 15:44:46 +03:00
d3463bc59a
change styling for top right corner UI
...
made save style button not die when you cancel
2022-10-15 14:22:30 +03:00
f7ca63937a
bring back scale latent option in settings
2022-10-15 13:23:12 +03:00
5967d07d1a
fix new gradio failing to preserve image params
2022-10-15 13:11:28 +03:00
e8729dd051
re-apply height hacks to work with new gradio
2022-10-15 12:54:23 +03:00
af144ebdc7
Merge branch 'master' into ckpt-cache
2022-10-15 10:35:18 +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
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
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
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
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
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
2f0e089c7c
should fix the issue with missing layers in chechpoint merger
2022-10-14 21:20:28 +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
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.
2022-10-14 19:54:24 +03:00
6b77af7a43
Merge pull request #2396 from yfszzx/master
...
Add a "History" tab
2022-10-14 19:32:19 +03:00
67f447ddcc
possibility to load checkpoint, clip skip, and hypernet from infotext
2022-10-14 19:30:28 +03:00
0aec19d783
make pasting into img2img prompt work
...
make image params request not use temp files
2022-10-14 18:15:03 +03:00
a156c097ab
Merge branch 'param-loading'
2022-10-14 17:14:24 +03:00
e644b5a80b
remove scale latent and no-crop options from hires fix
...
support copy-pasting new parameters for hires fix
2022-10-14 17:03:03 +03:00
b382de2d77
Fixed Scale ratio problem
2022-10-14 16:47:16 +03:00
40d1c6e423
Option between stretch and crop for Highres. fix
2022-10-14 16:47:16 +03:00
b2261b53ae
Added first_pass_width and height as adjustable inputs to "High Res Fix"
2022-10-14 16:47:16 +03:00
9e5ca5077f
extra message for unpicking fails
2022-10-14 16:37:36 +03:00
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
2022-10-14 16:31:39 +03:00
f7712e28e5
Merge branch 'AUTOMATIC1111:master' into master
2022-10-14 14:43:44 +08:00
fdecb63685
add an ability to merge three checkpoints
2022-10-14 09:20:24 +03:00
d48f3470c8
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
2022-10-14 11:51:26 +08:00
4a37c7eede
fix deep nesting directories problem
2022-10-14 11:48:28 +08:00
7c8903367c
Merge branch 'AUTOMATIC1111:master' into master
2022-10-14 07:35:07 +08:00
a1489f9428
images history fix all known bug
2022-10-14 07:13:38 +08:00
08b3f7aef1
emergency fix for broken send to buttons
2022-10-13 20:42:27 +03:00
354ef0da3b
add hypernetwork multipliers
2022-10-13 20:12:37 +03:00
a10b0e11fc
options to refresh list of models and hypernetworks
2022-10-13 19:22:49 +03:00
bb7baf6b9c
add option to change what's shown in quicksettings bar
2022-10-13 16:22:25 +03:00
8636b50aea
Add learn_rate to csv and removed a left-over debug statement
2022-10-13 12:37:58 +02:00
fed7f0e281
Revert "fix prompt in log.csv"
...
This reverts commit e4b5d16964
2022-10-13 13:25:29 +03:00
a3f02e4690
fix prompt in log.csv
2022-10-13 13:25:29 +03:00
8711c2fe01
Fix metadata contents
2022-10-13 13:25:29 +03:00
aeacbac218
Fix save error
2022-10-13 13:25:29 +03:00
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)
2022-10-13 12:26:34 +03:00
e72adc999b
Restore last generation params
2022-10-13 12:21:20 +03:00
04c0e643f2
Merge branch 'master' of https://github.com/HunterVacui/stable-diffusion-webui
2022-10-13 08:21:01 +03:00
4f73e057a9
Merge pull request #2324 from HunterVacui/interrogate_include_ranks_in_output
...
Interrogate: add option to include ranks in output
2022-10-13 08:05:41 +03:00
78592d404a
remove interrogate option I accidentally deleted
2022-10-13 07:40:03 +03:00
0186db178e
Merge branch 'AUTOMATIC1111:master' into master
2022-10-13 12:35:39 +08:00
716a9e034f
images history delete a number of images consecutively next
2022-10-13 12:19:50 +08:00
54e0051bdd
Add drag/drop param loading.
...
Drop an image or generational text onto the prompt bar, it loads the info for parsing.
2022-10-12 18:17:26 -05:00
1cfc2a1898
Save a csv containing the loss while training
2022-10-12 23:36:29 +02:00
514456101b
[3/?] [wip] fix incorrect variable reference
...
still needs testing
2022-10-12 13:14:13 -07:00
f776254b12
[2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenames
2022-10-12 13:12:18 -07:00
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
2022-10-12 13:03:00 -07:00
fb3cefb348
Merge remote-tracking branch 'upstream/master' into interrogate_include_ranks_in_output
2022-10-12 12:44:41 -07:00
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
2022-10-12 21:55:43 +03:00
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
2022-10-12 20:49:47 +03:00
df97947b21
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
2022-10-13 00:28:37 +08:00
324e6ed5d1
Merge branch 'AUTOMATIC1111:master' into master
2022-10-13 00:21:57 +08:00
a2aa2a68bc
images history improvement
2022-10-13 00:21:16 +08:00
a1a94b8b5f
images history improvement
2022-10-13 00:19:34 +08:00
c87c3b9c11
test
2022-10-12 21:24:40 +08:00
cc5803603b
Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-images
...
Add option to store TI embeddings in png chunks, and load from same.
2022-10-12 15:59:24 +03:00
511ca57e37
Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plus
2022-10-12 20:48:03 +08:00
e05573e1ad
images history improvement
2022-10-12 20:47:55 +08:00
10a2de644f
formatting
2022-10-12 13:15:35 +01:00
50be33e953
formatting
2022-10-12 13:13:25 +01:00
429442f4a6
fix iterator bug for #2295
2022-10-12 13:38:03 +03:00
80f3cf2bb2
Account when lines are mismatched
2022-10-12 11:38:41 +03:00
ee015a1af6
change textual inversion tab to train
...
remake train interface to use tabs
2022-10-12 11:05:57 +03:00
2d006ce16c
xy_grid: Find hypernetwork by closest name
2022-10-12 10:40:10 +03:00
dc1432e0dd
Merge branch 'master' into feature/scale_to
2022-10-12 10:35:42 +03:00
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.
2022-10-12 09:55:56 +03:00
336bd8703c
just add the deepdanbooru settings unconditionally
2022-10-12 09:00:07 +03:00
ee10c41e2a
Merge remote-tracking branch 'origin/steve3d'
2022-10-12 08:35:52 +03:00
2e2d45b281
Merge pull request #2143 from JC-Array/deepdanbooru_pre_process
...
deepbooru tags for textual inversion preproccessing
2022-10-12 08:35:27 +03:00
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
2022-10-12 08:30:06 +03:00
6ac2ec2b78
create dir for hypernetworks
2022-10-12 07:01:20 +03:00
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
2022-10-11 18:02:41 -07:00
65b973ac4e
Update shared.py
...
Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab.
2022-10-12 08:21:52 +08:00
f53f703aeb
resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled
2022-10-11 18:12:12 -05:00
963d986396
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process
2022-10-11 17:33:15 -05:00
6be32b31d1
reports that training with medvram is possible.
2022-10-11 23:07:09 +03:00
66ec505975
add file based test
2022-10-11 20:21:30 +01:00
7e6a6e00ad
Add files via upload
2022-10-11 20:20:46 +01:00
5f3317376b
spacing
2022-10-11 20:09:49 +01:00
91d7ee0d09
update imports
2022-10-11 20:09:10 +01:00
aa75d5cfe8
correct conflict resolution typo
2022-10-11 20:06:13 +01:00
d6fcc6b87b
apply lr schedule to hypernets
2022-10-11 22:03:05 +03:00
db71290d26
remove old caption method
2022-10-11 19:55:54 +01:00
61788c0538
shift embedding logic out of textual_inversion
2022-10-11 19:50:50 +01:00
419e539fe3
Merge branch 'learning_rate-scheduling' into learnschedule
2022-10-11 21:50:19 +03:00
e5fbf5c755
remove embedding related image functions from images
2022-10-11 19:46:33 +01:00
c080f52cea
move embedding logic to separate file
2022-10-11 19:37:58 +01:00
6a9ea5b41c
prevent extra modules from being saved/loaded with hypernet
2022-10-11 19:22:30 +03:00
d4ea5f4d86
add an option to unload models during hypernetwork training to save VRAM
2022-10-11 19:03:08 +03:00
6d09b8d1df
produce error when training with medvram/lowvram enabled
2022-10-11 18:33:57 +03:00
ff4ef13dd5
removed unneeded print
2022-10-11 10:24:27 -05:00
d682444ecc
add option to select hypernetwork modules when creating
2022-10-11 18:04:47 +03:00
4f96ffd0b5
Merge pull request #2201 from alg-wiki/textual__inversion
...
Textual Inversion: Preprocess and Training will only pick-up image files instead
2022-10-11 17:25:36 +03:00
861db783c7
Use apply_hypernetwork function
2022-10-11 17:24:00 +03:00
574c8e554a
Add InvokeAI and lstein to credits, add back CUDA support
2022-10-11 17:24:00 +03:00
98fd5cde72
Add check for psutil
2022-10-11 17:24:00 +03:00
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
2022-10-11 17:24:00 +03:00
f7e86aa420
Merge pull request #2227 from papuSpartan/master
...
Refresh list of models/ckpts upon hitting restart gradio in the setti…
2022-10-11 17:15:19 +03:00
1eaad95533
Merge branch 'master' into embed-embeddings-in-images
2022-10-11 15:15:09 +01:00
66b7d7584f
become even stricter with pickles
...
no pickle shall pass
thank you again, RyotaK
2022-10-11 17:03:16 +03:00
d01a2d0156
move list refresh to webui.py and add stdout indicating it's doing so
2022-10-11 08:31:28 -05:00
a36dea9596
Merge branch 'master' into master
2022-10-11 21:03:41 +08:00
b0583be088
more renames
2022-10-11 15:54:34 +03:00
873efeed49
rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have
2022-10-11 15:51:30 +03:00
a004d1a855
Added new line at the end of ngrok.py
2022-10-11 15:38:53 +03:00
5992564448
Cleaned ngrok integration
2022-10-11 15:38:53 +03:00
861297cefe
add a space holder
2022-10-11 15:37:04 +03:00
87b77cad5f
Layout fix
2022-10-11 15:37:04 +03:00
87d63bbab5
images history improvement
2022-10-11 20:37:03 +08:00
eacc03b167
Fix typo in comments
2022-10-11 15:36:29 +03:00
1eae307607
Remove debug code for checking that first sigma value is same after code cleanup
2022-10-11 15:36:29 +03:00
92d7a13885
Handle different parameters for DPM fast & adaptive
2022-10-11 15:36:29 +03:00
594ab4ba53
images history improvement
2022-10-11 20:23:41 +08:00
7b1db45e1f
images history improvement
2022-10-11 20:17:27 +08:00
530103b586
fixes related to merge
2022-10-11 14:53:02 +03:00
8bacbca0a1
Removed my local edits to checkpoint image generation
2022-10-11 17:35:09 +09:00
b2368a3bce
Switched to exception handling
2022-10-11 17:32:46 +09:00
5de806184f
Merge branch 'master' into hypernetwork-training
2022-10-11 11:14:36 +03:00
948533950c
replace duplicate code with a function
2022-10-11 11:10:17 +03:00
5e2627a1a6
Comma backtrack padding ( #2192 )
...
Comma backtrack padding
2022-10-11 09:55:28 +03:00
8617396c6d
Added slider for deepbooru score threshold in settings
2022-10-11 09:43:16 +03:00
8b7d3f1bef
Make the ctrl+enter shortcut use the generate button on the current tab
2022-10-11 09:32:03 +03:00
7aa8fcac1e
use simple lcg in xor
2022-10-11 04:17:36 +01:00
DepFA