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
4918eb6ce4
Merge branch 'master' into hn-activation
3 years ago
d5ea878b2a
Fix merge conflicts
3 years ago
4123be632a
Fix merge conflicts
3 years ago
cd4d59c0de
Merge master
3 years ago
17a2076f72
Merge pull request #3928 from R-N/validate-before-load
...
Optimize training a little
3 years ago
3d58510f21
Fix dataset still being loaded even when training will be skipped
3 years ago
a07f054c86
Add missing info on hypernetwork/embedding model log
...
Mentioned here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528#discussioncomment-3991513
Also group the saving into one
3 years ago
ab05a74ead
Revert "Add cleanup after training"
...
This reverts commit 3ce2bfdf95
3 years ago
3ce2bfdf95
Add cleanup after training
3 years ago
ab27c111d0
Add input validations before loading dataset for training
3 years ago
05e2e40537
Merge branch 'master' into gradient-clipping
3 years ago
e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info
3 years ago
810e6a407d
Merge pull request #3858 from R-N/log-csv
...
Fix log off by 1 #3847
3 years ago
9ceef81f77
Fix log off by 1
3 years ago
16451ca573
Learning rate sched syntax support for grad clipping
3 years ago
db5a354c48
Always ignore "None.pt" in the hypernet directory.
3 years ago
b2a8b263b2
Add missing support for linear activation in hypernetwork
3 years ago
2a25729623
Gradient clipping in train tab
3 years ago
029d7c7543
Revert unresolved changes in Bias initialization
...
it should be zeros_ or parameterized in future properly.
3 years ago
cc56df996e
Fix dropout logic
3 years ago
85fcccc105
Squashed commit of fixing dropout silently
...
fix dropouts for future hypernetworks
add kwargs for Hypernetwork class
hypernet UI for gradio input
add recommended options
remove as options
revert adding options in ui
3 years ago
b6a8bb123b
Fix merge
3 years ago
a524d137d0
patch bug (SeverianVoid's comment on 5245c7a)
3 years ago
91bb35b1e6
Merge fix
3 years ago
649d79a8ec
Merge branch 'master' into hn-activation
3 years ago
877d94f97c
Back compatibility
3 years ago
AUTOMATIC1111
Vladimir Mandic
Yuval Aboulafia
brkirch
flamelaw
Muhammad Rizqi Nur
Isaac Poulton
Fampai
aria1th
timntorres
timntorres
benkyoujouzu
guaneec