summaryrefslogtreecommitdiffstats
path: root/training
Commit message (Collapse)AuthorAgeFilesLines
* CleanupVolpeon2023-01-071-0/+54
|
* Made aspect ratio bucketing configurableVolpeon2023-01-071-7/+2
|
* Added progressive aspect ratio bucketingVolpeon2023-01-071-2/+2
|
* UpdateVolpeon2023-01-061-6/+6
|
* Use context manager for EMA, on_train/eval hooksVolpeon2023-01-062-27/+26
|
* Add contextmanager to EMAModel to apply weights temporarilyVolpeon2023-01-061-0/+12
|
* Added EMA to TIVolpeon2023-01-051-5/+95
|
* Fix LR finderVolpeon2023-01-051-7/+23
|
* UpdateVolpeon2023-01-051-1/+4
|
* Various cleanupsVolpeon2023-01-051-0/+75
|
* UpdateVolpeon2023-01-041-1/+6
|
* Various updatesVolpeon2023-01-041-4/+0
|
* Better eval generatorVolpeon2023-01-041-3/+3
|
* Fixed reproducibility, more consistant validationVolpeon2023-01-042-30/+68
|
* Added vector dropoutVolpeon2023-01-031-3/+6
|
* Fixed LR finderVolpeon2023-01-021-17/+21
|
* UpdateVolpeon2023-01-021-2/+31
|
* FixVolpeon2023-01-021-1/+1
|
* Improved one cycle schedulerVolpeon2023-01-021-30/+62
|
* UpdateVolpeon2023-01-011-3/+3
|
* UpdatesVolpeon2023-01-012-1/+7
|
* Fixed accuracy calc, other improvementsVolpeon2023-01-011-48/+0
|
* Added multi-vector embeddingsVolpeon2022-12-311-4/+56
|
* Training script improvementsVolpeon2022-12-301-5/+8
|
* UpdateVolpeon2022-12-292-11/+16
|
* Training improvementsVolpeon2022-12-292-23/+27
|
* Updated 1-cycle schedulerVolpeon2022-12-282-9/+15
|
* Integrated updates from diffusersVolpeon2022-12-282-15/+36
|
* Improved learning rate finderVolpeon2022-12-271-13/+25
|
* Added validation phase to learn rate finderVolpeon2022-12-271-11/+23
|
* Added learning rate finderVolpeon2022-12-271-0/+115
|
* Code simplifications, avoid autocastVolpeon2022-12-251-57/+49
|
* UpdateVolpeon2022-12-252-2/+3
|
* UpdateVolpeon2022-12-241-3/+3
|
* Fixed Textual InversionVolpeon2022-12-241-10/+5
|
* Training updateVolpeon2022-12-241-2/+0
|
* FixVolpeon2022-12-241-1/+1
|
* Fix againVolpeon2022-12-241-1/+1
|
* FixVolpeon2022-12-241-1/+4
|
* Improved class prompt handlingVolpeon2022-12-231-3/+1
|
* Simplified trainable embedding code againVolpeon2022-12-231-19/+6
|
* Fixed and simplified trainable embeddings codeVolpeon2022-12-231-12/+12
|
* Fixed Textual InversionVolpeon2022-12-221-6/+3
|
* Improved Textual Inversion: Completely exclude untrained embeddings from ↵Volpeon2022-12-221-0/+70
| | | | training
* Some LoRA fixes (still broken)Volpeon2022-12-211-13/+55
|
* Moved common training code into separate moduleVolpeon2022-12-212-1/+132
|
* Fix trainingVolpeon2022-12-201-0/+27
|
* UpdateVolpeon2022-11-141-1/+1
|
* UpdateVolpeon2022-11-031-4/+4
|
* UpdateVolpeon2022-11-031-0/+42