summaryrefslogtreecommitdiffstats
path: root/training/functional.py
Commit message (Expand)AuthorAgeFilesLines
* Fixed model compilationVolpeon2023-04-291-3/+3
* Support torch.compileVolpeon2023-04-281-4/+8
* Fixed loss/acc loggingVolpeon2023-04-281-16/+16
* UpdateVolpeon2023-04-271-26/+32
* UpdateVolpeon2023-04-211-2/+2
* FixVolpeon2023-04-161-1/+1
* Improved automation capsVolpeon2023-04-161-8/+9
* FixVolpeon2023-04-161-4/+3
* TI via LoRAVolpeon2023-04-151-2/+9
* Added cycle LR decayVolpeon2023-04-131-1/+4
* UpdateVolpeon2023-04-131-18/+17
* Experimental convnext discriminator supportVolpeon2023-04-111-24/+59
* Store sample images in Tensorboard as wellVolpeon2023-04-111-13/+12
* UpdateVolpeon2023-04-111-12/+10
* UpdateVolpeon2023-04-101-24/+27
* Fix sample gen: models sometimes weren't in eval modeVolpeon2023-04-101-0/+3
* UpdateVolpeon2023-04-101-3/+1
* UpdateVolpeon2023-04-091-2/+2
* FixVolpeon2023-04-091-1/+1
* UpdateVolpeon2023-04-081-35/+22
* FixVolpeon2023-04-071-6/+0
* 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 decayVolpeon2023-04-041-2/+2
* TI: Delta learningVolpeon2023-04-031-2/+2
* Update dataset format: Separate prompt and keywordsVolpeon2023-04-021-3/+6
* UpdateVolpeon2023-04-021-3/+3
* RevertVolpeon2023-04-011-1/+1
* UpdateVolpeon2023-04-011-5/+13
* Add support for Adafactor, add TI initializer noiseVolpeon2023-04-011-1/+2
* Improved inverted tokensVolpeon2023-03-261-10/+9
* Fix training with guidanceVolpeon2023-03-251-3/+9
* UpdateVolpeon2023-03-251-15/+21
* UpdateVolpeon2023-03-241-6/+5
* Refactoring, fixed Lora trainingVolpeon2023-03-241-7/+2
* Bring back Perlin offset noiseVolpeon2023-03-231-1/+14
* UpdateVolpeon2023-03-231-5/+2
* FixVolpeon2023-03-221-1/+1
* Log DAdam/DAdan dVolpeon2023-03-211-0/+14
* Fixed SNR weighting, re-enabled xformersVolpeon2023-03-211-10/+25
* Restore min SNRVolpeon2023-03-191-13/+12
* New loss weighting from arxiv.org:2204.00227Volpeon2023-03-181-2/+5
* Better SNR weightingVolpeon2023-03-181-3/+3
* Fixed snr weight calculationVolpeon2023-03-171-1/+4
* Fix loss=nanVolpeon2023-03-171-2/+2
* Test: https://arxiv.org/pdf/2303.09556.pdfVolpeon2023-03-171-3/+8
* UpdateVolpeon2023-03-071-1/+5
* UpdateVolpeon2023-03-061-16/+0