623251ce2b
allow pascal onwards
2022-10-10 19:54:07 +03:00
9d33baba58
Always show previous mask and fix extras_send dest
2022-10-10 19:39:24 +03:00
d5c14365fd
Add back in output hidden states parameter
2022-10-10 18:54:48 +03:00
460bbae587
Pad beginning of textual inversion embedding
2022-10-10 18:54:48 +03:00
b340439586
Unlimited Token Works
...
Unlimited tokens actually work now. Works with textual inversion too. Replaces the previous not-so-much-working implementation.
2022-10-10 18:54:48 +03:00
f347ddfd80
Remove max_batch_count from ui.py
2022-10-10 18:53:40 +03:00
df6d0d9286
convert back to rgb as some hosts add alpha
2022-10-10 15:43:09 +01:00
707a431100
add pixel data footer
2022-10-10 15:34:49 +01:00
ce2d7f7eac
Merge branch 'master' into embed-embeddings-in-images
2022-10-10 15:13:48 +01:00
7a20f914ed
Custom Width and Height
2022-10-10 17:05:12 +03:00
6ad3a53e36
Fixed progress bar output for epoch
2022-10-10 17:05:12 +03:00
ea00c1624b
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
2022-10-10 17:05:12 +03:00
8f1efdc130
--no-half-vae pt2
2022-10-10 17:03:45 +03:00
04c745ea4f
Custom Width and Height
2022-10-10 22:35:35 +09:00
7349088d32
--no-half-vae
2022-10-10 16:16:29 +03:00
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
2022-10-10 03:34:00 -05:00
4ee7519fc2
Fixed progress bar output for epoch
2022-10-10 17:31:33 +09:00
8ec069e64d
removed duplicate run_preprocess.click by creating run_preprocess_inputs list and appending deepbooru variable to input list if in scope
2022-10-10 03:23:24 -05:00
3110f895b2
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
2022-10-10 17:07:46 +09:00
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.
2022-10-10 08:04:52 +03:00
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.
2022-10-09 23:58:18 -05:00
6fdad291bd
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master
2022-10-09 23:20:39 -04:00
cc92dc1f8d
add vae path args
2022-10-09 23:17:29 -04:00
6435691bb1
Add "Scale to" option to Extras
2022-10-09 19:26:52 -06:00
4117afff11
Merge branch 'master' into embed-embeddings-in-images
2022-10-10 00:38:54 +01:00
e2c2925eb4
remove braces from steps
2022-10-10 00:12:53 +01:00
d6a599ef9b
change caption method
2022-10-10 00:07:52 +01:00
0ac3a07eec
add caption image with overlay
2022-10-10 00:05:36 +01:00
01fd9cf0d2
change source of step count
2022-10-09 22:17:02 +01:00
96f1e6be59
source checkpoint hash from current checkpoint
2022-10-09 22:14:50 +01:00
6684610510
correct case on embeddingFromB64
2022-10-09 22:06:42 +01:00
d0184b8f76
change json tensor key name
2022-10-09 22:06:12 +01:00
5d12ec82d3
add encoder and decoder classes
2022-10-09 22:05:09 +01:00
969bd8256e
add alternate checkpoint hash source
2022-10-09 22:02:28 +01:00
03694e1f99
add embedding load and save from b64 json
2022-10-09 21:58:14 +01:00
a65476718f
add DoubleStorage to list of allowed classes for pickle
2022-10-09 23:38:49 +03:00
fa0c5eb81b
Add pretty image captioning functions
2022-10-09 20:41:22 +01:00
8d340cfb88
do not add clip skip to parameters if it's 1 or 0
2022-10-09 22:31:35 +03:00
1824e9ee3a
Removed unnecessary tmp variable
2022-10-09 22:31:23 +03:00
ad3ae44108
Updated code for legibility
2022-10-09 22:31:23 +03:00
ec2bd9be75
Fix issues with CLIP ignore option name change
2022-10-09 22:31:23 +03:00
a14f7bf113
Corrected CLIP Layer Ignore description and updated its range to the max possible
2022-10-09 22:31:23 +03:00
e59c66c008
Optimized code for Ignoring last CLIP layers
2022-10-09 22:31:23 +03:00
6c383d2e82
show model selection setting on top of page
2022-10-09 22:24:07 +03:00
9ecea0a8d6
fix missing png info when Extras Batch Process
2022-10-09 18:35:25 +03:00
875ddfeecf
added guard for torch.load to prevent loading pickles with unknown content
2022-10-09 17:58:43 +03:00
9d1138e294
fix typo in filename for ESRGAN arch
2022-10-09 15:08:27 +03:00
e6e8cabe0c
change up #2056 to make it work how i want it to plus make xy plot write correct values to images
2022-10-09 14:57:48 +03:00
594cbfd8fb
Sanitize infotext output (for now)
2022-10-09 14:49:15 +03:00
006791c13d
Fix grabbing the model name for infotext
2022-10-09 14:49:15 +03:00
d6d10a37bf
Added extended model details to infotext
2022-10-09 14:49:15 +03:00
542a3d3a4a
fix btoken hypernetworks in XY plot
2022-10-09 14:33:22 +03:00
77a719648d
fix logic error in #1832
2022-10-09 13:48:04 +03:00
f4578b343d
fix model switching not working properly if there is a different yaml config
2022-10-09 13:23:30 +03:00
bd833409ac
additional changes for saving pnginfo for #1803
2022-10-09 13:10:15 +03:00
0609ce06c0
Removed duplicate definition model_path
2022-10-09 12:46:07 +03:00
6f6798ddab
prevent a possible code execution error (thanks, RyotaK)
2022-10-09 12:33:37 +03:00
0241d811d2
Revert "Fix for Prompts_from_file showing extra textbox."
...
This reverts commit e2930f9821
2022-10-09 12:04:44 +03:00
ab4fe4f44c
hide filenames for save button by default
2022-10-09 11:59:41 +03:00
cbf6dad02d
Handle case where on_show returns the wrong number of arguments
2022-10-09 11:16:38 +03:00
86cb16886f
Pull Request Code Review Fixes
2022-10-09 11:16:38 +03:00
e2930f9821
Fix for Prompts_from_file showing extra textbox.
2022-10-09 11:16:38 +03:00
1ffeb42d38
Fix typo
2022-10-09 11:10:13 +03:00
ef93acdc73
remove line break
2022-10-09 11:09:17 +03:00
03e570886f
Fix incorrect sampler name in output
2022-10-09 11:09:17 +03:00
122d42687b
Fix VRAM Issue by only loading in hypernetwork when selected in settings
2022-10-09 11:08:11 +03:00
e00b4df7c6
Merge pull request #1752 from Greendayle/dev/deepdanbooru
...
Added DeepDanbooru interrogator
2022-10-09 10:52:21 +03:00
14192c5b20
Support `Download` for txt files.
2022-10-09 10:49:11 +03:00
5ab7e88d9b
Add `Download` & `Download as zip`
2022-10-09 10:49:11 +03:00
4e569fd888
fixed incorrect message about loading config; thanks anon!
2022-10-09 10:31:47 +03:00
c77c89cc83
make main model loading and model merger use the same code
2022-10-09 10:23:31 +03:00
cd8673bd9b
add embed embedding to ui
2022-10-09 05:40:57 +01:00
5841990b0d
Update textual_inversion.py
2022-10-09 05:38:38 +01:00
050a6a798c
support loading .yaml config with same name as model
...
support EMA weights in processing (????)
2022-10-08 23:26:48 +03:00
432782163a
chore: Fix typos
2022-10-08 22:42:30 +03:00
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
2022-10-08 22:35:04 +03:00
3b2141c5fb
add 'Ignore last layers of CLIP model' option as a parameter to the infotext
2022-10-08 22:21:15 +03:00
e6e42f98df
make --force-enable-xformers work without needing --xformers
2022-10-08 22:12:23 +03:00
1371d7608b
Added ability to ignore last n layers in FrozenCLIPEmbedder
2022-10-08 22:10:37 +03:00
b458fa48fe
Update ui.py
2022-10-08 20:38:35 +03:00
15c4278f1a
TI preprocess wording
...
I had to check the code to work out what splitting was 🤷🏿
2022-10-08 20:38:35 +03:00
0ec80f0125
Merge branch 'master' into dev/deepdanbooru
2022-10-08 18:28:22 +02:00
3061cdb7b6
add --force-enable-xformers option and also add messages to console regarding cross attention optimizations
2022-10-08 19:22:15 +03:00
f9c5da1592
add fallback for xformers_attnblock_forward
2022-10-08 19:05:19 +03:00
01f8cb4447
made deepdanbooru optional, added to readme, automatic download of deepbooru model
2022-10-08 18:02:56 +02:00
a5550f0213
alternate prompt
2022-10-08 18:12:19 +03:00
cc0258aea7
check for ampere without destroying the optimizations. again.
2022-10-08 17:54:16 +03:00
017b6b8744
check for ampere
2022-10-08 17:54:16 +03:00
5329d0aba0
Merge branch 'master' into dev/deepdanbooru
2022-10-08 16:30:28 +02:00
cfc33f99d4
why did you do this
2022-10-08 17:29:06 +03:00
2e8ba0fa47
fix conflicts
2022-10-08 16:27:48 +02:00
4f33289d0f
Fixed typo
2022-10-08 17:15:30 +03:00
27032c47df
restore old opt_split_attention/disable_opt_split_attention logic
2022-10-08 17:10:05 +03:00
dc1117233e
simplify xfrmers options: --xformers to enable and that's it
2022-10-08 17:02:18 +03:00
7ff1170a2e
emergency fix for xformers (continue + shared)
2022-10-08 16:33:39 +03:00
48feae37ff
Merge pull request #1851 from C43H66N12O12S2/flash
...
xformers attention
2022-10-08 16:29:59 +03:00
970de9ee68
Update sd_hijack.py
2022-10-08 16:29:43 +03:00
69d0053583
update sd_hijack_opt to respect new env variables
2022-10-08 16:21:40 +03:00
ddfa9a9786
add xformers_available shared variable
2022-10-08 16:20:41 +03:00
26b459a379
default to split attention if cuda is available and xformers is not
2022-10-08 16:20:04 +03:00
5f85a74b00
fix bug where when using prompt composition, hijack_comments generated before the final AND will be dropped
2022-10-08 15:48:04 +03:00
772db721a5
fix glob path in hypernetwork.py
2022-10-08 15:46:54 +03:00
7001bffe02
fix AND broken for long prompts
2022-10-08 15:43:25 +03:00
77f4237d1c
fix bugs related to variable prompt lengths
2022-10-08 15:25:59 +03:00
4999eb2ef9
do not let user choose his own prompt token count limit
2022-10-08 14:25:47 +03:00
00117a07ef
check specifically for skipped
2022-10-08 13:40:39 +03:00
786d9f63aa
Add button to skip the current iteration
2022-10-08 13:40:39 +03:00
45cc0ce3c4
Merge remote-tracking branch 'origin/master'
2022-10-08 13:39:08 +03:00
706d5944a0
let user choose his own prompt token count limit
2022-10-08 13:38:57 +03:00
616b7218f7
fix: handles when state_dict does not exist
2022-10-08 12:38:50 +03:00
91d66f5520
use new attnblock for xformers path
2022-10-08 11:56:01 +03:00
76a616fa6b
Update sd_hijack_optimizations.py
2022-10-08 11:55:38 +03:00
5d54f35c58
add xformers attnblock and hypernetwork support
2022-10-08 11:55:02 +03:00
f2055cb1d4
Add hypernetwork support to split cross attention v1
...
* Add hypernetwork support to split_cross_attention_forward_v1
* Fix device check in esrgan_model.py to use devices.device_esrgan instead of shared.device
2022-10-08 09:39:17 +03:00
b70eaeb200
delete broken and unnecessary aliases
2022-10-08 04:10:35 +03:00
c9cc65b201
switch to the proper way of calling xformers
2022-10-08 04:09:18 +03:00
12c4d5c6b5
hypernetwork training mk1
2022-10-07 23:22:22 +03:00
5f12e7efd9
linux test
2022-10-07 20:58:30 +02:00
fa2ea648db
even more powerfull fix
2022-10-07 20:46:38 +02:00
54fa613c83
loading tf only in interrogation process
2022-10-07 20:37:43 +02:00
537da7a304
Merge branch 'master' into dev/deepdanbooru
2022-10-07 18:31:49 +02:00
f7c787eb7c
make it possible to use hypernetworks without opt split attention
2022-10-07 16:39:51 +03:00
97bc0b9504
do not stop working on failed hypernetwork load
2022-10-07 13:22:50 +03:00
d15b3ec001
support loading VAE
2022-10-07 10:40:22 +03:00
bad7cb29ce
added support for hypernetworks (???)
2022-10-07 10:17:52 +03:00
5e3ff846c5
Update sd_hijack.py
2022-10-07 06:38:01 +03:00
5303df2428
Update sd_hijack.py
2022-10-07 06:01:14 +03:00
35d6b23162
Update sd_hijack.py
2022-10-07 05:31:53 +03:00
da4ab2707b
Update shared.py
2022-10-07 05:23:06 +03:00
2eb911b056
Update sd_hijack.py
2022-10-07 05:22:28 +03:00
f174fb2922
add xformers attention
2022-10-07 05:21:49 +03:00
b34b25b4c9
karras samplers for img2img?
2022-10-06 23:27:01 +03:00
405c8171d1
Prefer using `Processed.sd_model_hash` attribute when filename pattern
2022-10-06 20:41:23 +03:00
1cc36d170a
Added job_timestamp to Processed
...
So `[job_timestamp]` pattern can use in saving image UI.
2022-10-06 20:41:23 +03:00
070b7d60cf
Added styles to Processed
...
So `[styles]` pattern can use in saving image UI.
2022-10-06 20:41:23 +03:00
cf7c784fcc
Removed duplicate defined models_path
...
Use `modules.paths.models_path` instead `modules.shared.model_path`.
2022-10-06 20:29:12 +03:00
dbc8a4d351
add generation parameters to images shown in web ui
2022-10-06 20:27:50 +03:00
0bb458f0ca
Removed duplicate image saving codes
...
Use `modules.images.save_image()` instead.
2022-10-06 20:15:39 +03:00
b66aa334a9
Merge branch 'master' into fix-vram
2022-10-06 13:41:37 -03:00
fec71e4de2
Default window title progress updates on
2022-10-06 17:58:52 +03:00
be71115b1a
Update shared.py
2022-10-06 17:58:52 +03:00
5993df24a1
integrate the new samplers PR
2022-10-06 14:12:52 +03:00
3ddf80a9db
add variant setting
2022-10-06 13:42:21 +03:00
71901b3d3b
add karras scheduling variants
2022-10-06 13:42:21 +03:00
2d3ea42a2d
workaround for a mysterious bug where prompt weights can't be matched
2022-10-06 13:21:12 +03:00
5f24b7bcf4
option to let users select which samplers they want to hide
2022-10-06 12:08:59 +03:00
4288e53fc2
removed unused import, fixed typo
2022-10-06 08:52:29 +03:00
2499fb4e19
Add sanitizer for captions in Textual inversion
2022-10-06 08:52:29 +03:00
0e92c36707
Merge pull request #1755 from AUTOMATIC1111/use-typing-list
...
use typing.list in prompt_parser.py for wider python version support
2022-10-06 08:50:06 +03:00
55400c981b
Set gradio-img2img-tool default to 'editor'
2022-10-06 08:46:32 +03:00
C43H66N12O12S2