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
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
08feb4c364
Sort straight out of the glob
3 years ago
fd62727893
Sort hypernetworks
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
0abb39f461
resolve conflict - first revert
3 years ago
4918eb6ce4
Merge branch 'master' into hn-activation
3 years ago
1764ac3c8b
use hash to check valid optim
3 years ago
0b143c1163
Separate .optim file from model
3 years ago
9d96d7d0a0
resolve conflicts
3 years ago
20194fd975
We have duplicate linear now
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
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
d3b4b9d7ec
Merge pull request #3717 from benkyoujouzu/master
...
Add missing support for linear activation in hypernetwork
3 years ago
f361e804eb
Re enable linear
3 years ago
9ceef81f77
Fix log off by 1
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
462e6ba667
Disable unavailable or duplicate options
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
7207e3bf49
remove duplicate keys and lowercase
3 years ago
de096d0ce7
Weight initialization and More activation func
...
add weight init
add weight init option in create_hypernetwork
fstringify hypernet info
save weight initialization info for further debugging
fill bias with zero for He/Xavier
initialize LayerNorm with Normal
fix loading weight_init
3 years ago
c702d4d0df
Fix off-by-one
3 years ago
2f4c91894d
Remove activation from final layer of HNs
3 years ago
e9a410b535
check length for variance
3 years ago
0d2e1dac40
convert deque -> list
...
I don't feel this being efficient
3 years ago
348f89c8d4
statistics for pbar
3 years ago
flamelaw
AUTOMATIC
Isaac Poulton
aria1th
Muhammad Rizqi Nur
timntorres
timntorres
benkyoujouzu
guaneec