Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-02-04 | add --no-hashing | AUTOMATIC | |
2023-01-22 | enable compact view for train tab | AUTOMATIC | |
prevent previews from ruining hypernetwork training | |||
2023-01-21 | extra networks UI | AUTOMATIC | |
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | |||
2023-01-18 | add option to show/hide warnings | AUTOMATIC | |
removed hiding warnings from LDSR fixed/reworked few places that produced warnings | |||
2023-01-16 | Fix tensorboard related functions | aria1th | |
2023-01-16 | Fix loss_dict problem | aria1th | |
2023-01-16 | fix missing 'mean loss' for tensorboard integration | AngelBottomless | |
2023-01-15 | big rework of progressbar/preview system to allow multiple users to prompts ↵ | AUTOMATIC | |
at the same time and do not get previews of each other | |||
2023-01-14 | change hypernets to use sha256 hashes | AUTOMATIC | |
2023-01-14 | change hash to sha256 | AUTOMATIC | |
2023-01-13 | Merge branch 'master' into tensorboard | AUTOMATIC1111 | |
2023-01-11 | set descriptions | Vladimir Mandic | |
2023-01-10 | Variable dropout rate | aria1th | |
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 | |||
2023-01-09 | make a dropdown for prompt template selection | AUTOMATIC | |
2023-01-08 | Move batchsize check | dan | |
2023-01-08 | Add checkbox for variable training dims | dan | |
2023-01-06 | rework saving training params to file #6372 | AUTOMATIC | |
2023-01-05 | Include model in log file. Exclude directory. | timntorres | |
2023-01-05 | Clean up ti, add same behavior to hypernetwork. | timntorres | |
2023-01-04 | Merge branch 'master' into gradient-clipping | AUTOMATIC1111 | |
2023-01-03 | add job info to modules | Vladimir Mandic | |
2022-12-25 | Merge pull request #5992 from yuvalabou/F541 | AUTOMATIC1111 | |
Fix F541: f-string without any placeholders | |||
2022-12-24 | implement train api | Vladimir Mandic | |
2022-12-24 | fix F541 f-string without any placeholders | Yuval Aboulafia | |
2022-12-03 | Merge branch 'master' into racecond_fix | AUTOMATIC1111 | |
2022-11-30 | Use devices.autocast instead of torch.autocast | brkirch | |
2022-11-23 | last_layer_dropout default to False | flamelaw | |
2022-11-23 | fix dropout, implement train/eval mode | flamelaw | |
2022-11-23 | small fixes | flamelaw | |
2022-11-21 | fix pin_memory with different latent sampling method | flamelaw | |
2022-11-20 | Gradient accumulation, autocast fix, new latent sampling method, etc | flamelaw | |
2022-11-19 | change StableDiffusionProcessing to internally use sampler name instead of ↵ | AUTOMATIC | |
sampler index | |||
2022-11-07 | Merge branch 'master' into gradient-clipping | Muhammad Rizqi Nur | |
2022-11-05 | rework the code to not use the walrus operator because colab's 3.7 does not ↵ | AUTOMATIC | |
support it | |||
2022-11-05 | Merge pull request #4273 from Omegastick/ordered_hypernetworks | AUTOMATIC1111 | |
Sort hypernetworks list | |||
2022-11-05 | Simplify grad clip | Muhammad Rizqi Nur | |
2022-11-04 | Sort straight out of the glob | Isaac Poulton | |
2022-11-04 | Merge branch 'master' into gradient-clipping | Muhammad Rizqi Nur | |
2022-11-04 | Sort hypernetworks | Isaac Poulton | |
2022-11-04 | Fixes race condition in training when VAE is unloaded | Fampai | |
set_current_image can attempt to use the VAE when it is unloaded to the CPU while training | |||
2022-11-04 | only save if option is enabled | aria1th | |
2022-11-04 | split before declaring file name | aria1th | |
2022-11-04 | apply | aria1th | |
2022-11-04 | Merge branch 'AUTOMATIC1111:master' into force-push-patch-13 | AngelBottomless | |
2022-11-04 | I blame code autocomplete | AngelBottomless | |
2022-11-04 | resolve conflict - first revert | aria1th | |
2022-11-04 | Merge branch 'master' into hn-activation | AUTOMATIC1111 | |
2022-11-03 | use hash to check valid optim | aria1th | |
2022-11-03 | Separate .optim file from model | aria1th | |
2022-10-31 | Fix merge conflicts | Muhammad Rizqi Nur | |