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
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
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
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
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
a65476718f
add DoubleStorage to list of allowed classes for pickle
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
0241d811d2
Revert "Fix for Prompts_from_file showing extra textbox."
...
This reverts commit e2930f9821
3 years ago
ab4fe4f44c
hide filenames for save button by default
3 years ago
cbf6dad02d
Handle case where on_show returns the wrong number of arguments
3 years ago
86cb16886f
Pull Request Code Review Fixes
3 years ago
e2930f9821
Fix for Prompts_from_file showing extra textbox.
3 years ago
1ffeb42d38
Fix typo
3 years ago
ef93acdc73
remove line break
3 years ago
03e570886f
Fix incorrect sampler name in output
3 years ago
122d42687b
Fix VRAM Issue by only loading in hypernetwork when selected in settings
3 years ago
e00b4df7c6
Merge pull request #1752 from Greendayle/dev/deepdanbooru
...
Added DeepDanbooru interrogator
3 years ago
14192c5b20
Support `Download` for txt files.
3 years ago
5ab7e88d9b
Add `Download` & `Download as zip`
3 years ago
4e569fd888
fixed incorrect message about loading config; thanks anon!
3 years ago
c77c89cc83
make main model loading and model merger use the same code
3 years ago
050a6a798c
support loading .yaml config with same name as model
...
support EMA weights in processing (????)
3 years ago
432782163a
chore: Fix typos
3 years ago
610a7f4e14
Break after finding the local directory of stable diffusion
...
Otherwise, we may override it with one of the next two path (. or ..) if it is present there, and then the local paths of other modules (taming transformers, codeformers, etc.) wont be found in sd_path/../.
Fix https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/1085
3 years ago
3b2141c5fb
add 'Ignore last layers of CLIP model' option as a parameter to the infotext
3 years ago
e6e42f98df
make --force-enable-xformers work without needing --xformers
3 years ago
1371d7608b
Added ability to ignore last n layers in FrozenCLIPEmbedder
3 years ago
b458fa48fe
Update ui.py
3 years ago
15c4278f1a
TI preprocess wording
...
I had to check the code to work out what splitting was 🤷🏿
3 years ago
0ec80f0125
Merge branch 'master' into dev/deepdanbooru
3 years ago
3061cdb7b6
add --force-enable-xformers option and also add messages to console regarding cross attention optimizations
3 years ago
f9c5da1592
add fallback for xformers_attnblock_forward
3 years ago
01f8cb4447
made deepdanbooru optional, added to readme, automatic download of deepbooru model
3 years ago
a5550f0213
alternate prompt
3 years ago
cc0258aea7
check for ampere without destroying the optimizations. again.
3 years ago
017b6b8744
check for ampere
3 years ago
5329d0aba0
Merge branch 'master' into dev/deepdanbooru
3 years ago
cfc33f99d4
why did you do this
3 years ago
2e8ba0fa47
fix conflicts
3 years ago
4f33289d0f
Fixed typo
3 years ago
27032c47df
restore old opt_split_attention/disable_opt_split_attention logic
3 years ago
dc1117233e
simplify xfrmers options: --xformers to enable and that's it
3 years ago
7ff1170a2e
emergency fix for xformers (continue + shared)
3 years ago
48feae37ff
Merge pull request #1851 from C43H66N12O12S2/flash
...
xformers attention
3 years ago
970de9ee68
Update sd_hijack.py
3 years ago
69d0053583
update sd_hijack_opt to respect new env variables
3 years ago
ddfa9a9786
add xformers_available shared variable
3 years ago
26b459a379
default to split attention if cuda is available and xformers is not
3 years ago
5f85a74b00
fix bug where when using prompt composition, hijack_comments generated before the final AND will be dropped
3 years ago
772db721a5
fix glob path in hypernetwork.py
3 years ago
7001bffe02
fix AND broken for long prompts
3 years ago
77f4237d1c
fix bugs related to variable prompt lengths
3 years ago
4999eb2ef9
do not let user choose his own prompt token count limit
3 years ago
00117a07ef
check specifically for skipped
3 years ago
786d9f63aa
Add button to skip the current iteration
3 years ago
45cc0ce3c4
Merge remote-tracking branch 'origin/master'
3 years ago
706d5944a0
let user choose his own prompt token count limit
3 years ago
alg-wiki
alg-wiki
AUTOMATIC
ssysm
C43H66N12O12S2
Vladimir Repin
hentailord85ez
RW21
JC_Array
brkirch
Fampai
Artem Zagidulin
William Moorehouse
Milly
Tony Beeman
Nicolas Noullet
frostydad
aoirusann
aoirusann
Aidan Holland
Edouard Leurent
DepFA
Greendayle
Greendayle
MrCheeze
ddPn08
Trung Ngo