summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
...
* Improved Textual Inversion: Completely exclude untrained embeddings from ↵Volpeon2022-12-222-18/+76
| | | | training
* Some LoRA fixes (still broken)Volpeon2022-12-212-138/+89
|
* Moved common training code into separate moduleVolpeon2022-12-214-231/+203
|
* Fix trainingVolpeon2022-12-205-15/+1073
|
* Dependency cleanup/upgradesVolpeon2022-12-202-27/+12
|
* Fix Textual Inversion dataset filteringVolpeon2022-12-201-1/+5
|
* Upstream patchesVolpeon2022-12-191-5/+17
|
* Improved dataset prompt handling, fixedVolpeon2022-12-194-23/+25
|
* Avoid increased VRAM usage on validationVolpeon2022-12-154-12/+29
|
* More generic datset filterVolpeon2022-12-145-13/+25
|
* Unified loading of TI embeddingsVolpeon2022-12-134-65/+54
|
* Optimized Textual Inversion training by filtering dataset by existence of ↵Volpeon2022-12-133-10/+47
| | | | added tokens
* Fixed sample/checkpoint frequencyVolpeon2022-12-132-14/+10
|
* Add support for resume in Textual InversionVolpeon2022-12-134-111/+101
|
* Dreambooth: Support loading Textual Inversion embeddingsVolpeon2022-12-124-31/+57
|
* Remove embedding checkpoints from Dreambooth trainingVolpeon2022-12-111-40/+16
|
* Package updatesVolpeon2022-12-111-3/+3
|
* Training improvements such as tag dropoutVolpeon2022-12-112-36/+68
|
* Support attention_mask of text encoderVolpeon2022-12-104-15/+29
|
* Various updated; shuffle prompt content during trainingVolpeon2022-12-103-18/+48
|
* Fix sample stepsVolpeon2022-12-062-2/+2
|
* UpdateVolpeon2022-12-044-18/+15
|
* UpdateVolpeon2022-12-012-6/+6
|
* UpdateVolpeon2022-12-014-13/+16
|
* UpdateVolpeon2022-12-014-19/+23
|
* UpdateVolpeon2022-11-302-12/+34
|
* Adjusted training to upstreamVolpeon2022-11-282-50/+56
|
* Fixed noise calculation for v-predictionVolpeon2022-11-282-13/+37
|
* Fixed and improved Textual Inversion trainingVolpeon2022-11-271-44/+68
|
* FixVolpeon2022-11-272-2/+0
|
* Generic loading of scheduler (training)Volpeon2022-11-272-34/+18
|
* Make prompt processor compatible with any modelVolpeon2022-11-271-1/+2
|
* UpdateVolpeon2022-11-273-47/+63
|
* UpdateVolpeon2022-11-141-6/+1
|
* RefactoringVolpeon2022-11-144-115/+226
|
* UpdateVolpeon2022-11-147-316/+87
|
* UpdateVolpeon2022-11-031-4/+4
|
* UpdateVolpeon2022-11-036-11/+102
|
* UpdateVolpeon2022-11-014-63/+117
|
* FixVolpeon2022-10-271-6/+6
|
* Added CLI arg to set dataloader worker num; improved text encoder handling ↵Volpeon2022-10-273-11/+50
| | | | with Dreambooth
* Euler_a: Re-introduce generator arg for reproducible outputVolpeon2022-10-272-3/+10
|
* New Euler_a schedulerVolpeon2022-10-266-318/+215
|
* Advanced datasetsVolpeon2022-10-243-75/+115
|
* UpdateVolpeon2022-10-246-17/+415
|
* Revert lat; fix skip attribute in datasetVolpeon2022-10-222-76/+87
|
* Training updateVolpeon2022-10-222-87/+75
|
* Add optional TI functionality to DreamboothVolpeon2022-10-213-45/+77
|
* Dreambooth: Added option to insert a new input token; removed Dreambooth PlusVolpeon2022-10-192-1029/+42
|
* Updated Dreambooth trainingVolpeon2022-10-193-37/+76
|