1b63afbedc
sort hypernetworks and checkpoints by name
3 years ago
dfb3b8f398
Merge branch 'master' into weighted-learning
3 years ago
edb10092de
Add ability to choose using weighted loss or not
3 years ago
bc50936745
Call weighted_forward during training
3 years ago
4738486d8f
Support for hypernetworks with --upcast-sampling
3 years ago
81823407d9
add --no-hashing
3 years ago
78f59a4e01
enable compact view for train tab
...
prevent previews from ruining hypernetwork training
3 years ago
40ff6db532
extra networks UI
...
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
3 years ago
924e222004
add option to show/hide warnings
...
removed hiding warnings from LDSR
fixed/reworked few places that produced warnings
3 years ago
13445738d9
Fix tensorboard related functions
3 years ago
598f7fcd84
Fix loss_dict problem
3 years ago
16f410893e
fix missing 'mean loss' for tensorboard integration
3 years ago
d8b90ac121
big rework of progressbar/preview system to allow multiple users to prompts at the same time and do not get previews of each other
3 years ago
f9ac3352cb
change hypernets to use sha256 hashes
3 years ago
a95f135308
change hash to sha256
3 years ago
9cd7716753
Merge branch 'master' into tensorboard
3 years ago
3f43d8a966
set descriptions
3 years ago
a4a5475cfa
Variable dropout rate
...
Implements variable dropout rate from #4549
Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training.
Changes function name to match torch.nn.module standard
Fixes RNG reset issue when generating previews by restoring RNG state
3 years ago
1fbb6f9ebe
make a dropdown for prompt template selection
3 years ago
72497895b9
Move batchsize check
3 years ago
669fb18d52
Add checkbox for variable training dims
3 years ago
683287d87f
rework saving training params to file #6372
3 years ago
b6bab2f052
Include model in log file. Exclude directory.
3 years ago
b85c2b5cf4
Clean up ti, add same behavior to hypernetwork.
3 years ago
eeb1de4388
Merge branch 'master' into gradient-clipping
3 years ago
192ddc04d6
add job info to modules
3 years ago
b12de850ae
Merge pull request #5992 from yuvalabou/F541
...
Fix F541: f-string without any placeholders
3 years ago
5f1dfbbc95
implement train api
3 years ago
3bf5591efe
fix F541 f-string without any placeholders
3 years ago
c9a2cfdf2a
Merge branch 'master' into racecond_fix
3 years ago
4d5f1691dd
Use devices.autocast instead of torch.autocast
3 years ago
1bd57cc979
last_layer_dropout default to False
3 years ago
d2c97fc3fe
fix dropout, implement train/eval mode
3 years ago
89d8ecff09
small fixes
3 years ago
5b57f61ba4
fix pin_memory with different latent sampling method
3 years ago
bd68e35de3
Gradient accumulation, autocast fix, new latent sampling method, etc
3 years ago
cdc8020d13
change StableDiffusionProcessing to internally use sampler name instead of sampler index
3 years ago
cabd4e3b3b
Merge branch 'master' into gradient-clipping
3 years ago
62e3d71aa7
rework the code to not use the walrus operator because colab's 3.7 does not support it
3 years ago
cb84a304f0
Merge pull request #4273 from Omegastick/ordered_hypernetworks
...
Sort hypernetworks list
3 years ago
bb832d7725
Simplify grad clip
3 years ago
08feb4c364
Sort straight out of the glob
3 years ago
3277f90e93
Merge branch 'master' into gradient-clipping
3 years ago
fd62727893
Sort hypernetworks
3 years ago
39541d7725
Fixes race condition in training when VAE is unloaded
...
set_current_image can attempt to use the VAE when it is unloaded to
the CPU while training
3 years ago
1ca0bcd3a7
only save if option is enabled
3 years ago
f5d394214d
split before declaring file name
3 years ago
283249d239
apply
3 years ago
179702adc4
Merge branch 'AUTOMATIC1111:master' into force-push-patch-13
3 years ago
0d07cbfa15
I blame code autocomplete
3 years ago
AUTOMATIC
Shondoit
brkirch
aria1th
Vladimir Mandic
dan
timntorres
Yuval Aboulafia
flamelaw
Muhammad Rizqi Nur
Isaac Poulton
Fampai