Yuval Aboulafia
|
3bf5591efe
|
fix F541 f-string without any placeholders
|
3 years ago |
Jim Hays
|
c0355caefe
|
Fix various typos
|
3 years ago |
AUTOMATIC1111
|
c9a2cfdf2a
|
Merge branch 'master' into racecond_fix
|
3 years ago |
|
AUTOMATIC1111
|
a2feaa95fc
|
Merge pull request #5194 from brkirch/autocast-and-mps-randn-fixes
Use devices.autocast() and fix MPS randn issues
|
3 years ago |
PhytoEpidemic
|
119a945ef7
|
Fix divide by 0 error
Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script.
|
3 years ago |
brkirch
|
4d5f1691dd
|
Use devices.autocast instead of torch.autocast
|
3 years ago |
|
AUTOMATIC1111
|
39827a3998
|
Merge pull request #4688 from parasi22/resolve-embedding-name-in-filewords
resolve [name] after resolving [filewords] in training
|
3 years ago |
|
AUTOMATIC
|
b48b7999c8
|
Merge remote-tracking branch 'flamelaw/master'
|
3 years ago |
flamelaw
|
755df94b2a
|
set TI AdamW default weight decay to 0
|
3 years ago |
|
AUTOMATIC
|
ce6911158b
|
Add support Stable Diffusion 2.0
|
3 years ago |
|
flamelaw
|
89d8ecff09
|
small fixes
|
3 years ago |
|
flamelaw
|
5b57f61ba4
|
fix pin_memory with different latent sampling method
|
3 years ago |
|
AUTOMATIC
|
c81d440d87
|
moved deepdanbooru to pure pytorch implementation
|
3 years ago |
|
flamelaw
|
2d22d72cda
|
fix random sampling with pin_memory
|
3 years ago |
|
flamelaw
|
a4a5735d0a
|
remove unnecessary comment
|
3 years ago |
|
flamelaw
|
bd68e35de3
|
Gradient accumulation, autocast fix, new latent sampling method, etc
|
3 years ago |
|
AUTOMATIC1111
|
89daf778fb
|
Merge pull request #4812 from space-nuko/feature/interrupt-preprocessing
Add interrupt button to preprocessing
|
3 years ago |
|
AUTOMATIC
|
cdc8020d13
|
change StableDiffusionProcessing to internally use sampler name instead of sampler index
|
3 years ago |
space-nuko
|
c8c40c8a64
|
Add interrupt button to preprocessing
|
3 years ago |
parasi
|
9a1aff645a
|
resolve [name] after resolving [filewords] in training
|
3 years ago |
|
AUTOMATIC1111
|
73776907ec
|
Merge pull request #4117 from TinkTheBoush/master
Adding optional tag shuffling for training
|
3 years ago |
KyuSeok Jung
|
a1e271207d
|
Update dataset.py
|
3 years ago |
|
KyuSeok Jung
|
b19af67d29
|
Update dataset.py
|
3 years ago |
|
KyuSeok Jung
|
13a2f1dca3
|
adding tag drop out option
|
3 years ago |
|
AUTOMATIC
|
8011be33c3
|
move functions out of main body for image preprocessing for easier hijacking
|
3 years ago |
TinkTheBoush
|
821e2b883d
|
change option position to Training setting
|
3 years ago |
Fampai
|
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 |
|
KyuSeok Jung
|
af6fba2475
|
Merge branch 'master' into master
|
3 years ago |
|
TinkTheBoush
|
467cae167a
|
append_tag_shuffle
|
3 years ago |
|
Fampai
|
890e68aaf7
|
Fixed minor bug
when unloading vae during TI training, generating images after
training will error out
|
3 years ago |
|
Fampai
|
3b0127e698
|
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations
|
3 years ago |
|
Fampai
|
006756f9cd
|
Added TI training optimizations
option to use xattention optimizations when training
option to unload vae when training
|
3 years ago |
|
AUTOMATIC1111
|
17a2076f72
|
Merge pull request #3928 from R-N/validate-before-load
Optimize training a little
|
3 years ago |
Muhammad Rizqi Nur
|
3d58510f21
|
Fix dataset still being loaded even when training will be skipped
|
3 years ago |
|
Muhammad Rizqi Nur
|
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 |
|
Muhammad Rizqi Nur
|
ab05a74ead
|
Revert "Add cleanup after training"
This reverts commit 3ce2bfdf95.
|
3 years ago |
|
Muhammad Rizqi Nur
|
a27d19de2e
|
Additional assert on dataset
|
3 years ago |
|
Muhammad Rizqi Nur
|
3ce2bfdf95
|
Add cleanup after training
|
3 years ago |
|
Muhammad Rizqi Nur
|
ab27c111d0
|
Add input validations before loading dataset for training
|
3 years ago |
|
Muhammad Rizqi Nur
|
ef4c94e1cf
|
Improve lr schedule error message
|
3 years ago |
|
Muhammad Rizqi Nur
|
a5f3adbdd7
|
Allow trailing comma in learning rate
|
3 years ago |
|
AUTOMATIC1111
|
810e6a407d
|
Merge pull request #3858 from R-N/log-csv
Fix log off by 1 #3847
|
3 years ago |
|
Muhammad Rizqi Nur
|
9ceef81f77
|
Fix log off by 1
|
3 years ago |
FlameLaw
|
a0a7024c67
|
Fix random dataset shuffle on TI
|
3 years ago |
DepFA
|
737eb28fac
|
typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir
|
3 years ago |
timntorres
|
f4e1464217
|
Implement PR #3625 but for embeddings.
|
3 years ago |
|
timntorres
|
4875a6c217
|
Implement PR #3309 but for embeddings.
|
3 years ago |
|
timntorres
|
c2dc9bfa89
|
Implement PR #3189 but for embeddings.
|
3 years ago |
|
AUTOMATIC
|
cbb857b675
|
enable creating embedding with --medvram
|
3 years ago |
captin411
|
df0c5ea29d
|
update default weights
|
3 years ago |