summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* 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
|
* BugfixVolpeon2022-10-042-6/+6
|
* FixVolpeon2022-10-031-8/+2
|
* Dreambooth: Generate specialized class images from input promptsVolpeon2022-10-035-164/+129
|
* Small perf improvementsVolpeon2022-10-035-51/+58
|
* Added negative prompt support for training scriptsVolpeon2022-10-034-133/+63
|
* Fixed euler_a generator argumentVolpeon2022-10-035-23/+10
|
* Assign unused images in validation dataset to train datasetVolpeon2022-10-034-9/+26
|
* Added script to convert Differs -> SDVolpeon2022-10-031-0/+234
|
* Use euler_a for samples in learning scripts; backported improvement from ↵Volpeon2022-10-034-203/+230
| | | | Dreambooth to Textual Inversion
* Small performance improvementsVolpeon2022-10-023-17/+28
|
* Fix img2imgVolpeon2022-10-023-60/+38
|
* More consistent euler_aVolpeon2022-10-023-45/+33
|
* WIP: img2imgVolpeon2022-10-022-39/+131
|
* Fix seed, better progress bar, fix euler_a for batch size > 1Volpeon2022-10-013-15/+15
|
* Made inference script interactiveVolpeon2022-10-013-216/+113
|
* Added custom SD pipeline + euler_a schedulerVolpeon2022-09-305-36/+869
|
* Better sample file structureVolpeon2022-09-281-5/+5
|
* Batches of size 1 cause error: Expected query.is_contiguous() to be true, ↵Volpeon2022-09-282-29/+16
| | | | but got false
* Improved sample output and progress barsVolpeon2022-09-283-66/+50
|
* Infer script: Store args, better path/file namesVolpeon2022-09-281-3/+11
|
* Dreamooth script: Fixed step calculation, added file logVolpeon2022-09-281-24/+24
|
* Better output dir structureVolpeon2022-09-274-6/+4
|
* Various improvements, added inference scriptVolpeon2022-09-274-46/+175
|
* Incorporate upstream changesVolpeon2022-09-272-8/+66
|
* Supply dataset CSV file instead of dir with hardcoded CSV filenameVolpeon2022-09-272-21/+25
|
* Freeze models that aren't trainedVolpeon2022-09-271-8/+8
|
* Fix error when saving modelVolpeon2022-09-271-2/+2
|
* Added Dreambooth training scriptVolpeon2022-09-274-0/+1019
|
* Undo textual inversion dataset improvementsVolpeon2022-09-271-10/+21
|
* More cleanupVolpeon2022-09-272-25/+11
|
* Use diffusers fork with Flash AttentionVolpeon2022-09-271-1/+3
|
* CleanupVolpeon2022-09-271-31/+71
|
* Better sample filenames, optimizationsVolpeon2022-09-273-19/+32
|
* Autocast on sample generation, progress bar cleanupVolpeon2022-09-261-19/+30
|
* InitVolpeon2022-09-268-0/+1847
generated by cgit v1.2.3-70-g09d2 (git 2.47.0) at 2024-11-19 15:56:07 +0000