121 Commits (d8b90ac121cbf0c18b1dc9d56a5e1d14ca51e74e)

Author SHA1 Message Date
AUTOMATIC 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
AUTOMATIC f9ac3352cb change hypernets to use sha256 hashes 3 years ago
AUTOMATIC a95f135308 change hash to sha256 3 years ago
AUTOMATIC1111 9cd7716753
Merge branch 'master' into tensorboard 3 years ago
Vladimir Mandic 3f43d8a966
set descriptions 3 years ago
aria1th 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
AUTOMATIC 1fbb6f9ebe make a dropdown for prompt template selection 3 years ago
dan 72497895b9 Move batchsize check 3 years ago
dan 669fb18d52 Add checkbox for variable training dims 3 years ago
AUTOMATIC 683287d87f rework saving training params to file #6372 3 years ago
timntorres b6bab2f052 Include model in log file. Exclude directory. 3 years ago
timntorres b85c2b5cf4 Clean up ti, add same behavior to hypernetwork. 3 years ago
AUTOMATIC1111 eeb1de4388
Merge branch 'master' into gradient-clipping 3 years ago
Vladimir Mandic 192ddc04d6
add job info to modules 3 years ago
AUTOMATIC1111 b12de850ae
Merge pull request #5992 from yuvalabou/F541
Fix F541: f-string without any placeholders
3 years ago
Vladimir Mandic 5f1dfbbc95 implement train api 3 years ago
Yuval Aboulafia 3bf5591efe fix F541 f-string without any placeholders 3 years ago
AUTOMATIC1111 c9a2cfdf2a
Merge branch 'master' into racecond_fix 3 years ago
brkirch 4d5f1691dd Use devices.autocast instead of torch.autocast 3 years ago
flamelaw 1bd57cc979 last_layer_dropout default to False 3 years ago
flamelaw d2c97fc3fe fix dropout, implement train/eval mode 3 years ago
flamelaw 89d8ecff09 small fixes 3 years ago
flamelaw 5b57f61ba4 fix pin_memory with different latent sampling method 3 years ago
flamelaw bd68e35de3 Gradient accumulation, autocast fix, new latent sampling method, etc 3 years ago
AUTOMATIC cdc8020d13 change StableDiffusionProcessing to internally use sampler name instead of sampler index 3 years ago
Muhammad Rizqi Nur cabd4e3b3b Merge branch 'master' into gradient-clipping 3 years ago
AUTOMATIC 62e3d71aa7 rework the code to not use the walrus operator because colab's 3.7 does not support it 3 years ago
AUTOMATIC1111 cb84a304f0
Merge pull request #4273 from Omegastick/ordered_hypernetworks
Sort hypernetworks list
3 years ago
Muhammad Rizqi Nur bb832d7725 Simplify grad clip 3 years ago
Isaac Poulton 08feb4c364
Sort straight out of the glob 3 years ago
Muhammad Rizqi Nur 3277f90e93 Merge branch 'master' into gradient-clipping 3 years ago
Isaac Poulton fd62727893
Sort hypernetworks 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
aria1th 1ca0bcd3a7 only save if option is enabled 3 years ago
aria1th f5d394214d split before declaring file name 3 years ago
aria1th 283249d239 apply 3 years ago
AUTOMATIC1111 4918eb6ce4
Merge branch 'master' into hn-activation 3 years ago
Muhammad Rizqi Nur d5ea878b2a Fix merge conflicts 3 years ago
Muhammad Rizqi Nur 4123be632a Fix merge conflicts 3 years ago
Muhammad Rizqi Nur cd4d59c0de Merge master 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 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 05e2e40537 Merge branch 'master' into gradient-clipping 3 years ago
timntorres e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info 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