summaryrefslogtreecommitdiffstats
path: root/training
Commit message (Collapse)AuthorAgeFilesLines
...
* 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
|
* UpdateVolpeon2023-04-012-7/+18
|
* Add support for Adafactor, add TI initializer noiseVolpeon2023-04-012-1/+5
|
* UpdateVolpeon2023-03-311-0/+2
|
* Fix TIVolpeon2023-03-271-8/+10
|
* Sparse TI embeddings without sparse tensorsVolpeon2023-03-271-10/+8
|
* Improved TI embeddingsVolpeon2023-03-261-2/+1
|
* 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
|
* Fixed Lora training perf issueVolpeon2023-03-241-7/+8
|
* Lora fix: Save config JSON, tooVolpeon2023-03-241-0/+3
|
* Refactoring, fixed Lora trainingVolpeon2023-03-244-65/+32
|
* Bring back Perlin offset noiseVolpeon2023-03-231-1/+14
|
* UpdateVolpeon2023-03-234-17/+14
|
* FixVolpeon2023-03-221-1/+1
|
* Log DAdam/DAdan dVolpeon2023-03-211-0/+14
|
* Fixed SNR weighting, re-enabled xformersVolpeon2023-03-212-21/+84
|
* 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
|
* UpdateVolpeon2023-03-072-15/+16
|
* UpdateVolpeon2023-03-061-16/+0
|
* Added Perlin noise to trainingVolpeon2023-03-041-0/+17
|
* Removed offset noise from training, added init offset to pipelineVolpeon2023-03-031-10/+2
|
* Implemented different noise offsetVolpeon2023-03-032-22/+10
|
* Low freq noise with randomized strengthVolpeon2023-03-031-1/+8
|
* Better low freq noiseVolpeon2023-03-021-1/+1
|
* Changed low freq noiseVolpeon2023-03-011-23/+10
|
* UpdateVolpeon2023-03-014-28/+32
|
* Fixed TI normalization orderVolpeon2023-02-213-15/+19
|
* FixVolpeon2023-02-211-6/+3
|
* Don't rely on Accelerate for gradient accumulationVolpeon2023-02-212-30/+29
|
* Embedding normalization: Ignore tensors with grad = 0Volpeon2023-02-212-6/+16
|