Commit graph

1796 commits

Author SHA1 Message Date
AUTOMATIC
ee015a1af6 change textual inversion tab to train
remake train interface to use tabs
2022-10-12 11:05:57 +03:00
Milly
2fffd4bddc xy_grid: Refactor confirm functions 2022-10-12 10:40:10 +03:00
Milly
7dba1c07cb xy_grid: Confirm that hypernetwork options are valid before starting 2022-10-12 10:40:10 +03:00
Milly
2d006ce16c xy_grid: Find hypernetwork by closest name 2022-10-12 10:40:10 +03:00
AUTOMATIC1111
4aeacaefbf
Merge pull request #2110 from JustMaier/feature/scale_to
Add "Scale to" option to Extras
2022-10-12 10:36:21 +03:00
AUTOMATIC1111
dc1432e0dd
Merge branch 'master' into feature/scale_to 2022-10-12 10:35:42 +03:00
LunixWasTaken
ca5efc316b Typo fix in watermark hint. 2022-10-12 10:11:06 +03:00
aoirusann
f421f2af2d [img2imgalt] Fix seed & Allow batch. 2022-10-12 10:03:46 +03:00
brkirch
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
AUTOMATIC
8aead63f1a emergency fix 2022-10-12 09:32:14 +03:00
James Noeckel
7edd58d90d update environment-wsl2.yaml 2022-10-12 09:08:44 +03:00
AUTOMATIC1111
c15c3b08df
Merge pull request #2312 from AUTOMATIC1111/edit-attention-nan-fix
edit attention key handler: return early when weight parse returns NaN
2022-10-12 09:07:49 +03:00
AUTOMATIC
fd07b103ae prevent SD model from loading when running in deepdanbooru process 2022-10-12 09:00:39 +03:00
AUTOMATIC
336bd8703c just add the deepdanbooru settings unconditionally 2022-10-12 09:00:07 +03:00
AUTOMATIC
ee10c41e2a Merge remote-tracking branch 'origin/steve3d' 2022-10-12 08:35:52 +03:00
AUTOMATIC1111
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
Greg Fuller
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
AUTOMATIC
6ac2ec2b78 create dir for hypernetworks 2022-10-12 07:01:20 +03:00
Greg Fuller
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
supersteve3d
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
DepFA
6d408c06c6
Prevent nans from failed float parsing from overwriting weights 2022-10-12 00:19:28 +01:00
JC_Array
f53f703aeb resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled 2022-10-11 18:12:12 -05:00
JC-Array
963d986396
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process 2022-10-11 17:33:15 -05:00
AUTOMATIC
6be32b31d1 reports that training with medvram is possible. 2022-10-11 23:07:09 +03:00
DepFA
66ec505975
add file based test 2022-10-11 20:21:30 +01:00
DepFA
7e6a6e00ad
Add files via upload 2022-10-11 20:20:46 +01:00
DepFA
5f3317376b
spacing 2022-10-11 20:09:49 +01:00
DepFA
91d7ee0d09
update imports 2022-10-11 20:09:10 +01:00
DepFA
aa75d5cfe8
correct conflict resolution typo 2022-10-11 20:06:13 +01:00
AUTOMATIC
2f6ea2fbca Merge remote-tracking branch 'origin/master' 2022-10-11 22:03:57 +03:00
AUTOMATIC
d6fcc6b87b apply lr schedule to hypernets 2022-10-11 22:03:05 +03:00
DepFA
db71290d26
remove old caption method 2022-10-11 19:55:54 +01:00
DepFA
61788c0538
shift embedding logic out of textual_inversion 2022-10-11 19:50:50 +01:00
AUTOMATIC1111
12f4f4761b
Merge pull request #1795 from MarkovInequality/learnschedule
Added learning_rate scheduling for TI
2022-10-11 21:50:30 +03:00
AUTOMATIC1111
419e539fe3
Merge branch 'learning_rate-scheduling' into learnschedule 2022-10-11 21:50:19 +03:00
DepFA
e5fbf5c755
remove embedding related image functions from images 2022-10-11 19:46:33 +01:00
DepFA
c080f52cea
move embedding logic to separate file 2022-10-11 19:37:58 +01:00
nai-degen
9e5f6b5580 triggers 'input' event when using arrow keys to edit attention 2022-10-11 21:19:30 +03:00
AUTOMATIC
d7474a5185 bump gradio to 3.4.1 2022-10-11 21:10:55 +03:00
AUTOMATIC
6a9ea5b41c prevent extra modules from being saved/loaded with hypernet 2022-10-11 19:22:30 +03:00
AUTOMATIC
d4ea5f4d86 add an option to unload models during hypernetwork training to save VRAM 2022-10-11 19:03:08 +03:00
AUTOMATIC
6d09b8d1df produce error when training with medvram/lowvram enabled 2022-10-11 18:33:57 +03:00
JC_Array
ff4ef13dd5 removed unneeded print 2022-10-11 10:24:27 -05:00
AUTOMATIC
d682444ecc add option to select hypernetwork modules when creating 2022-10-11 18:04:47 +03:00
AUTOMATIC
5ba23cb41f change default for XY plot's Y to Nothing. 2022-10-11 17:28:17 +03:00
AUTOMATIC1111
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
brkirch
861db783c7 Use apply_hypernetwork function 2022-10-11 17:24:00 +03:00
brkirch
574c8e554a Add InvokeAI and lstein to credits, add back CUDA support 2022-10-11 17:24:00 +03:00
brkirch
98fd5cde72 Add check for psutil 2022-10-11 17:24:00 +03:00
brkirch
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