summaryrefslogtreecommitdiffstats
Commit message (Expand)AuthorAgeFilesLines
* 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 wi...Volpeon2022-10-273-11/+50
* 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
* Adapted other scripts for new prompt processingVolpeon2022-10-183-17/+23
* Improved prompt handlingVolpeon2022-10-185-129/+100
* Implemented extended prompt limitVolpeon2022-10-174-58/+108
* Upstream updates; better handling of textual embeddingVolpeon2022-10-175-59/+82
* UpdateVolpeon2022-10-163-9/+15
* UpdateVolpeon2022-10-163-33/+69
* UpdateVolpeon2022-10-153-26/+49
* Removed aesthetic gradients; training improvementsVolpeon2022-10-146-243/+77
* Added support for Aesthetic GradientsVolpeon2022-10-138-61/+245
* Added TI+Dreambooth trainingVolpeon2022-10-134-12/+961
* Various updatesVolpeon2022-10-127-223/+142
* Added EMA support to Textual InversionVolpeon2022-10-102-17/+60
* Remove unused codeVolpeon2022-10-101-138/+0
* TI: Use different lr schedulerVolpeon2022-10-101-1/+1
* Dreambooth: Add EMA supportVolpeon2022-10-101-6/+44
* Updated default paramsVolpeon2022-10-102-7/+7
* UpdateVolpeon2022-10-094-13/+146
* UpdateVolpeon2022-10-086-144/+169
* Fix small detailsVolpeon2022-10-073-57/+59
* Training: Create multiple class images per training imageVolpeon2022-10-074-34/+101
* UpdateVolpeon2022-10-068-1116/+159
* Inference: Add support for embeddingsVolpeon2022-10-041-2/+30
* Multi-vector TI was brokenVolpeon2022-10-041-69/+38
* Add Textual Inversion with class dataset (a la Dreambooth)Volpeon2022-10-045-47/+968
* Default sample steps 30 -> 40Volpeon2022-10-042-2/+2
* Fix: PromptsVolpeon2022-10-041-2/+6