summaryrefslogtreecommitdiffstats
path: root/dreambooth.py
Commit message (Collapse)AuthorAgeFilesLines
* More generic datset filterVolpeon2022-12-141-1/+5
|
* Unified loading of TI embeddingsVolpeon2022-12-131-21/+5
|
* Optimized Textual Inversion training by filtering dataset by existence of ↵Volpeon2022-12-131-0/+6
| | | | added tokens
* Fixed sample/checkpoint frequencyVolpeon2022-12-131-3/+1
|
* Add support for resume in Textual InversionVolpeon2022-12-131-26/+23
|
* Dreambooth: Support loading Textual Inversion embeddingsVolpeon2022-12-121-11/+25
|
* Remove embedding checkpoints from Dreambooth trainingVolpeon2022-12-111-40/+16
|
* Training improvements such as tag dropoutVolpeon2022-12-111-33/+58
|
* Support attention_mask of text encoderVolpeon2022-12-101-4/+5
|
* Various updated; shuffle prompt content during trainingVolpeon2022-12-101-4/+6
|
* Fix sample stepsVolpeon2022-12-061-1/+1
|
* UpdateVolpeon2022-12-041-1/+3
|
* UpdateVolpeon2022-12-011-3/+3
|
* UpdateVolpeon2022-12-011-8/+9
|
* UpdateVolpeon2022-12-011-2/+9
|
* UpdateVolpeon2022-11-301-11/+8
|
* Adjusted training to upstreamVolpeon2022-11-281-27/+30
|
* Fixed noise calculation for v-predictionVolpeon2022-11-281-4/+17
|
* FixVolpeon2022-11-271-1/+0
|
* Generic loading of scheduler (training)Volpeon2022-11-271-20/+9
|
* UpdateVolpeon2022-11-271-16/+38
|
* RefactoringVolpeon2022-11-141-4/+4
|
* UpdateVolpeon2022-11-141-30/+41
|
* UpdateVolpeon2022-11-031-3/+11
|
* UpdateVolpeon2022-11-011-1/+1
|
* FixVolpeon2022-10-271-6/+6
|
* Added CLI arg to set dataloader worker num; improved text encoder handling ↵Volpeon2022-10-271-8/+33
| | | | with Dreambooth
* Euler_a: Re-introduce generator arg for reproducible outputVolpeon2022-10-271-2/+2
|
* New Euler_a schedulerVolpeon2022-10-261-3/+3
|
* Advanced datasetsVolpeon2022-10-241-26/+42
|
* UpdateVolpeon2022-10-241-0/+34
|
* Revert lat; fix skip attribute in datasetVolpeon2022-10-221-75/+86
|
* Training updateVolpeon2022-10-221-86/+75
|
* Add optional TI functionality to DreamboothVolpeon2022-10-211-35/+66
|
* Dreambooth: Added option to insert a new input token; removed Dreambooth PlusVolpeon2022-10-191-6/+42
|
* Updated Dreambooth trainingVolpeon2022-10-191-33/+71
|
* Adapted other scripts for new prompt processingVolpeon2022-10-181-7/+10
|
* Upstream updates; better handling of textual embeddingVolpeon2022-10-171-10/+16
|
* UpdateVolpeon2022-10-161-4/+6
|
* UpdateVolpeon2022-10-161-9/+32
|
* Removed aesthetic gradients; training improvementsVolpeon2022-10-141-5/+5
|
* Added support for Aesthetic GradientsVolpeon2022-10-131-10/+0
|
* Added TI+Dreambooth trainingVolpeon2022-10-131-5/+10
|
* Various updatesVolpeon2022-10-121-30/+23
|
* Added EMA support to Textual InversionVolpeon2022-10-101-11/+12
|
* Dreambooth: Add EMA supportVolpeon2022-10-101-6/+44
|
* Updated default paramsVolpeon2022-10-101-4/+4
|
* UpdateVolpeon2022-10-091-5/+2
|
* UpdateVolpeon2022-10-081-30/+45
|
* Fix small detailsVolpeon2022-10-071-22/+23
|