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
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
AUTOMATIC
Rae Fu
Ljzd-PRO
Gugubo
Buckzor
brkirch
不会画画的中医不是好程序员
Melan
Greg Fuller
Trung Ngo
d8ahazard
DepFA
hentailord85ez
Milly
supersteve3d
JC_Array
JC-Array