AUTOMATIC
50b5504401
remove parsing command line from devices.py
2022-10-22 14:04:14 +03:00
AUTOMATIC1111
e80bdcab91
Merge pull request #3377 from Extraltodeus/cuda-device-id-selection
...
Implementation of CUDA device id selection (--device-id 0/1/2)
2022-10-22 13:58:00 +03:00
AUTOMATIC1111
1fa53dab2c
Merge branch 'master' into cuda-device-id-selection
2022-10-22 13:57:20 +03:00
AUTOMATIC
5aa9525046
updated readme with info about Aesthetic Gradients
2022-10-22 13:40:07 +03:00
discus0434
6a02841fff
Merge pull request #2 from aria1th/patch-6
...
generalized some functions and option for ignoring first layer
2022-10-22 19:35:56 +09:00
AUTOMATIC
6398dc9b10
further support for extensions
2022-10-22 13:34:49 +03:00
AUTOMATIC
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
2022-10-22 12:23:58 +03:00
yfszzx
67b78f0ea6
inspiration perfected
2022-10-22 10:29:23 +08:00
yfszzx
d93ea5cdeb
inspiration perfected
2022-10-22 10:21:21 +08:00
yfszzx
40ddb6df61
inspiration perfected
2022-10-22 10:16:22 +08:00
Extraltodeus
29bfacd63c
implement CUDA device selection, --device-id arg
2022-10-22 00:12:46 +02:00
Extraltodeus
57eb54b838
implement CUDA device selection by ID
2022-10-22 00:11:07 +02:00
yfszzx
58ee008f0f
inspiration finished
2022-10-22 01:30:12 +08:00
yfszzx
2797b2cbf2
inspiration finished
2022-10-22 01:28:02 +08:00
yfszzx
bb0f1a2cda
inspiration finished
2022-10-22 01:23:00 +08:00
AUTOMATIC
26d1073745
Merge remote-tracking branch 'historytab/master'
2022-10-21 18:49:56 +03:00
AUTOMATIC
f49c08ea56
prevent error spam when processing images without txt files for captions
2022-10-21 18:46:02 +03:00
AUTOMATIC1111
7464f367c3
Merge pull request #3246 from Milly/fix/train-preprocess-keep-ratio
...
Preprocess: fixed keep ratio and changed split behavior
2022-10-21 18:36:55 +03:00
AUTOMATIC1111
5e9afa5c8a
Merge branch 'master' into fix/train-preprocess-keep-ratio
2022-10-21 18:36:29 +03:00
AUTOMATIC
24ce67a13b
make aspect ratio overlay work regardless of selected localization, pt2
2022-10-21 17:41:47 +03:00
AUTOMATIC
ac0aa2b18e
loading SD VAE, see PR #3303
2022-10-21 17:35:51 +03:00
AUTOMATIC
3d898044e5
batch_size does not affect job count
2022-10-21 17:26:30 +03:00
AUTOMATIC
a7aa00d46a
Merge remote-tracking branch 'mk2/outpainting-mk2-batch-out'
2022-10-21 17:22:47 +03:00
AUTOMATIC
704036ff07
make aspect ratio overlay work regardless of selected localization
2022-10-21 17:11:42 +03:00
Rcmcpe
02e4d4694d
Change option description of unload_models_when_training
2022-10-21 16:53:06 +03:00
timntorres
272fa527bb
Remove unused variable.
2022-10-21 16:52:24 +03:00
timntorres
fccad18a59
Refer to Hypernet's name, sensibly, by its name variable.
2022-10-21 16:52:24 +03:00
timntorres
19818f023c
Match hypernet name with filename in all cases.
2022-10-21 16:52:24 +03:00
timntorres
51e3dc9cca
Sanitize hypernet name input.
2022-10-21 16:52:24 +03:00
AUTOMATIC1111
3e12b5295c
Merge pull request #3321 from AUTOMATIC1111/features-to-readme
...
Features to readme
2022-10-21 16:51:08 +03:00
AUTOMATIC1111
ec37f8a45f
Merge branch 'master' into features-to-readme
2022-10-21 16:51:01 +03:00
parsec501
85cb5918ee
Make commit hash mandatory field
2022-10-21 16:48:13 +03:00
DepFA
306e2ff6ab
Update image_embedding.py
2022-10-21 16:47:37 +03:00
DepFA
d0ea471b0c
Use opts in textual_inversion image_embedding.py for dynamic fonts
2022-10-21 16:47:37 +03:00
AUTOMATIC
9286fe53de
make aestetic embedding ciompatible with prompts longer than 75 tokens
2022-10-21 16:38:06 +03:00
AUTOMATIC
e89e2f7c2c
Merge remote-tracking branch 'origin/master'
2022-10-21 16:16:34 +03:00
AUTOMATIC
df57064093
do not load aesthetic clip model until it's needed
...
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
2022-10-21 16:10:51 +03:00
ClashSAN
003d2c7fe4
Update README.md
2022-10-21 11:40:37 +00:00
AUTOMATIC
7d6b388d71
Merge branch 'ae'
2022-10-21 13:35:01 +03:00
Leo Mozoloa
1ed227b3b5
wtf is happening
2022-10-21 12:16:48 +03:00
AUTOMATIC
bf30673f51
Fix Hypernet infotext string split bug for PR #3283
2022-10-21 10:19:25 +03:00
AUTOMATIC
03a1e288c4
turns out LayerNorm also has weight and bias and needs to be pre-multiplied and trained for hypernets
2022-10-21 10:13:24 +03:00
AUTOMATIC1111
e4877722e3
Merge pull request #3197 from AUTOMATIC1111/training-help-text
...
Training UI Changes
2022-10-21 09:58:16 +03:00
AUTOMATIC1111
0c5522ea21
Merge branch 'master' into training-help-text
2022-10-21 09:57:55 +03:00
timntorres
2273e752fb
Remove redundant try/except.
2022-10-21 09:55:00 +03:00
timntorres
4ff274e1e3
Revise comments.
2022-10-21 09:55:00 +03:00
timntorres
6014fb8afb
Do nothing if image file already exists.
2022-10-21 09:55:00 +03:00
timntorres
5245c7a493
Issue #2921-Give PNG info to Hypernet previews.
2022-10-21 09:55:00 +03:00
guaneec
b69c37d25e
Allow datasets with only 1 image in TI
2022-10-21 09:54:09 +03:00
Patryk Wychowaniec
7157e5d064
interrogate: Fix CLIP-interrogation on CPU
...
Currently, trying to perform CLIP interrogation on a CPU fails, saying:
```
RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
```
This merge request fixes this issue by detecting whether the target
device is CPU and, if so, force-enabling `--no-half` and passing
`device="cpu"` to `clip.load()` (which then does some extra tricks to
ensure it works correctly on CPU).
2022-10-21 09:52:12 +03:00
