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
6435691bb1
Add "Scale to" option to Extras
3 years ago
4117afff11
Merge branch 'master' into embed-embeddings-in-images
3 years ago
e2c2925eb4
remove braces from steps
3 years ago
d6a599ef9b
change caption method
3 years ago
0ac3a07eec
add caption image with overlay
3 years ago
01fd9cf0d2
change source of step count
3 years ago
96f1e6be59
source checkpoint hash from current checkpoint
3 years ago
6684610510
correct case on embeddingFromB64
3 years ago
d0184b8f76
change json tensor key name
3 years ago
5d12ec82d3
add encoder and decoder classes
3 years ago
969bd8256e
add alternate checkpoint hash source
3 years ago
03694e1f99
add embedding load and save from b64 json
3 years ago
a65476718f
add DoubleStorage to list of allowed classes for pickle
3 years ago
fa0c5eb81b
Add pretty image captioning functions
3 years ago
8d340cfb88
do not add clip skip to parameters if it's 1 or 0
3 years ago
1824e9ee3a
Removed unnecessary tmp variable
3 years ago
ad3ae44108
Updated code for legibility
3 years ago
ec2bd9be75
Fix issues with CLIP ignore option name change
3 years ago
a14f7bf113
Corrected CLIP Layer Ignore description and updated its range to the max possible
3 years ago
e59c66c008
Optimized code for Ignoring last CLIP layers
3 years ago
6c383d2e82
show model selection setting on top of page
3 years ago
9ecea0a8d6
fix missing png info when Extras Batch Process
3 years ago
875ddfeecf
added guard for torch.load to prevent loading pickles with unknown content
3 years ago
9d1138e294
fix typo in filename for ESRGAN arch
3 years ago
e6e8cabe0c
change up #2056 to make it work how i want it to plus make xy plot write correct values to images
3 years ago
594cbfd8fb
Sanitize infotext output (for now)
3 years ago
006791c13d
Fix grabbing the model name for infotext
3 years ago
d6d10a37bf
Added extended model details to infotext
3 years ago
542a3d3a4a
fix btoken hypernetworks in XY plot
3 years ago
77a719648d
fix logic error in #1832
3 years ago
f4578b343d
fix model switching not working properly if there is a different yaml config
3 years ago
bd833409ac
additional changes for saving pnginfo for #1803
3 years ago
0609ce06c0
Removed duplicate definition model_path
3 years ago
6f6798ddab
prevent a possible code execution error (thanks, RyotaK)
3 years ago
AUTOMATIC1111
yfszzx
DepFA
hentailord85ez
Milly
brkirch
Greg Fuller
supersteve3d
JC_Array
JC-Array
papuSpartan
JamnedZ
Ben
Martin Cairns
alg-wiki
Kenneth
Jairo Correa
Fampai
alg-wiki
Justin Maier
ssysm
C43H66N12O12S2
Vladimir Repin
RW21
Fampai
Artem Zagidulin
William Moorehouse