summaryrefslogtreecommitdiffstats
path: root/training
Commit message (Collapse)AuthorAgeFilesLines
* Support LoRA training for token embeddingsVolpeon2023-05-162-11/+5
|
* Fix for latest PEFTVolpeon2023-05-121-0/+47
|
* UpdateVolpeon2023-05-111-9/+15
|
* UpdateVolpeon2023-05-063-13/+171
|
* UpdateVolpeon2023-05-051-12/+21
|
* torch.compile won't work yet, keep code preparedVolpeon2023-04-291-0/+3
|
* Fixed model compilationVolpeon2023-04-291-3/+3
|
* Support torch.compileVolpeon2023-04-281-4/+8
|
* Fixed loss/acc loggingVolpeon2023-04-282-17/+22
|
* UpdateVolpeon2023-04-273-34/+54
|
* UpdateVolpeon2023-04-213-6/+8
|
* FixVolpeon2023-04-171-1/+1
|
* FixVolpeon2023-04-161-1/+1
|
* Improved automation capsVolpeon2023-04-164-14/+34
|
* FixVolpeon2023-04-161-4/+3
|
* FixVolpeon2023-04-151-19/+0
|
* TI via LoRAVolpeon2023-04-153-9/+15
|
* Added cycle LR decayVolpeon2023-04-131-1/+4
|
* UpdateVolpeon2023-04-134-29/+22
|
* Experimental convnext discriminator supportVolpeon2023-04-111-24/+59
|
* Store sample images in Tensorboard as wellVolpeon2023-04-111-13/+12
|
* UpdateVolpeon2023-04-111-12/+10
|
* UpdateVolpeon2023-04-104-27/+30
|
* Fix sample gen: models sometimes weren't in eval modeVolpeon2023-04-104-28/+29
|
* UpdateVolpeon2023-04-104-6/+4
|
* UpdateVolpeon2023-04-091-1/+1
|
* UpdateVolpeon2023-04-091-2/+2
|
* FixVolpeon2023-04-091-1/+1
|
* UpdateVolpeon2023-04-082-7/+7
|
* Fix TIVolpeon2023-04-081-1/+2
|
* FixVolpeon2023-04-081-3/+2
|
* UpdateVolpeon2023-04-084-40/+33
|
* Fixed Lora PTIVolpeon2023-04-071-16/+19
|
* FixVolpeon2023-04-074-19/+8
|
* FixVolpeon2023-04-072-6/+8
|
* UpdateVolpeon2023-04-071-1/+36
|
* UpdateVolpeon2023-04-061-36/+4
|
* MinSNR code from diffusersVolpeon2023-04-051-19/+30
|
* Improved slerp noise offset: Dedicated black image instead of negative offsetVolpeon2023-04-051-72/+40
|
* New offset noise testVolpeon2023-04-051-8/+89
|
* TI: Bring back old embedding decayVolpeon2023-04-042-3/+23
|
* Improved sparse embeddingsVolpeon2023-04-031-4/+4
|
* TI: Delta learningVolpeon2023-04-032-25/+2
|
* Update dataset format: Separate prompt and keywordsVolpeon2023-04-021-3/+6
|
* UpdateVolpeon2023-04-021-3/+3
|
* Lora: Only register params with grad to optimizerVolpeon2023-04-022-5/+0
|
* RevertVolpeon2023-04-012-20/+82
|
* FixVolpeon2023-04-011-1/+3
|
* Combined TI with embedding and LoRAVolpeon2023-04-011-58/+18
|
* Experimental: TI via LoRAVolpeon2023-04-011-26/+4
|