MrCheeze
|
0df94d3fcf
|
fix aesthetic gradients doing nothing after loading a different model
|
3 years ago |
AUTOMATIC
|
324c7c732d
|
record First pass size as 0x0 for #3328
|
3 years ago |
Kris57
|
774be6d2f2
|
improve ja translation
|
3 years ago |
|
Kris57
|
f613c6b8c5
|
improve ja translation
|
3 years ago |
|
Kris57
|
0262bf64dd
|
improve ja translation
|
3 years ago |
|
Kris57
|
7043f4eff3
|
improve ja translation
|
3 years ago |
|
Kris57
|
070fda592b
|
add ja translation
|
3 years ago |
|
Kris57
|
eb2dae196e
|
add ja translation
|
3 years ago |
|
Kris57
|
96ee7d7707
|
add ja localization
|
3 years ago |
random_thoughtss
|
7613ea12f2
|
Fixed img2imgalt after inpainting update
|
3 years ago |
|
AUTOMATIC1111
|
ffea9b1509
|
Merge pull request #3414 from discus0434/master
[Hypernetworks] Add a feature to use dropout / more activation functions
|
3 years ago |
Greendayle
|
e38625011c
|
fix part2
|
3 years ago |
|
Greendayle
|
72383abacd
|
Deepdanbooru linux fix
|
3 years ago |
|
AUTOMATIC
|
dbc8ab65f6
|
typo
|
3 years ago |
|
AUTOMATIC
|
d37cfffd53
|
added callback for creating new settings in extensions
|
3 years ago |
discus0434
|
6a4fa73a38
|
small fix
|
3 years ago |
discus0434
|
97749b7c7d
|
Merge branch 'AUTOMATIC1111:master' into master
|
3 years ago |
|
discus0434
|
7912acef72
|
small fix
|
3 years ago |
|
discus0434
|
fccba4729d
|
add an option to avoid dying relu
|
3 years ago |
|
AUTOMATIC
|
7fd90128eb
|
added a guard for hypernet training that will stop early if weights are getting no gradients
|
3 years ago |
|
AUTOMATIC
|
1cd3ed7def
|
fix for extensions without style.css
|
3 years ago |
|
discus0434
|
dcb45dfecf
|
Merge branch 'master' of upstream
|
3 years ago |
|
discus0434
|
0e8ca8e7af
|
add dropout
|
3 years ago |
|
AUTOMATIC
|
50b5504401
|
remove parsing command line from devices.py
|
3 years ago |
|
AUTOMATIC1111
|
e80bdcab91
|
Merge pull request #3377 from Extraltodeus/cuda-device-id-selection
Implementation of CUDA device id selection (--device-id 0/1/2)
|
3 years ago |
|
AUTOMATIC1111
|
1fa53dab2c
|
Merge branch 'master' into cuda-device-id-selection
|
3 years ago |
|
AUTOMATIC
|
5aa9525046
|
updated readme with info about Aesthetic Gradients
|
3 years ago |
|
discus0434
|
6a02841fff
|
Merge pull request #2 from aria1th/patch-6
generalized some functions and option for ignoring first layer
|
3 years ago |
|
AUTOMATIC
|
6398dc9b10
|
further support for extensions
|
3 years ago |
|
AUTOMATIC
|
2b91251637
|
removed aesthetic gradients as built-in
added support for extensions
|
3 years ago |
yfszzx
|
67b78f0ea6
|
inspiration perfected
|
3 years ago |
|
yfszzx
|
d93ea5cdeb
|
inspiration perfected
|
3 years ago |
|
yfszzx
|
40ddb6df61
|
inspiration perfected
|
3 years ago |
Extraltodeus
|
29bfacd63c
|
implement CUDA device selection, --device-id arg
|
3 years ago |
|
Extraltodeus
|
57eb54b838
|
implement CUDA device selection by ID
|
3 years ago |
|
yfszzx
|
58ee008f0f
|
inspiration finished
|
3 years ago |
|
yfszzx
|
2797b2cbf2
|
inspiration finished
|
3 years ago |
|
yfszzx
|
bb0f1a2cda
|
inspiration finished
|
3 years ago |
|
AUTOMATIC
|
26d1073745
|
Merge remote-tracking branch 'historytab/master'
|
3 years ago |
|
AUTOMATIC
|
f49c08ea56
|
prevent error spam when processing images without txt files for captions
|
3 years ago |
|
AUTOMATIC1111
|
7464f367c3
|
Merge pull request #3246 from Milly/fix/train-preprocess-keep-ratio
Preprocess: fixed keep ratio and changed split behavior
|
3 years ago |
|
AUTOMATIC1111
|
5e9afa5c8a
|
Merge branch 'master' into fix/train-preprocess-keep-ratio
|
3 years ago |
|
AUTOMATIC
|
24ce67a13b
|
make aspect ratio overlay work regardless of selected localization, pt2
|
3 years ago |
|
AUTOMATIC
|
ac0aa2b18e
|
loading SD VAE, see PR #3303
|
3 years ago |
|
AUTOMATIC
|
3d898044e5
|
batch_size does not affect job count
|
3 years ago |
|
AUTOMATIC
|
a7aa00d46a
|
Merge remote-tracking branch 'mk2/outpainting-mk2-batch-out'
|
3 years ago |
|
AUTOMATIC
|
704036ff07
|
make aspect ratio overlay work regardless of selected localization
|
3 years ago |
Rcmcpe
|
02e4d4694d
|
Change option description of unload_models_when_training
|
3 years ago |
timntorres
|
272fa527bb
|
Remove unused variable.
|
3 years ago |
|
timntorres
|
fccad18a59
|
Refer to Hypernet's name, sensibly, by its name variable.
|
3 years ago |