Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Pipeline: Perlin noise for init image | Volpeon | 2023-03-04 | 1 | -1/+1 |
| | |||||
* | Update | Volpeon | 2023-02-18 | 1 | -0/+2 |
| | |||||
* | Added Lion optimizer | Volpeon | 2023-02-17 | 1 | -2/+5 |
| | |||||
* | Inference script: Better scheduler config | Volpeon | 2023-02-17 | 1 | -19/+37 |
| | |||||
* | Back to xformers | Volpeon | 2023-02-17 | 1 | -2/+2 |
| | |||||
* | Remove xformers, switch to Pytorch Nightly | Volpeon | 2023-02-17 | 1 | -3/+4 |
| | |||||
* | Integrated WIP UniPC scheduler | Volpeon | 2023-02-16 | 1 | -3/+12 |
| | |||||
* | Update | Volpeon | 2023-02-13 | 1 | -7/+7 |
| | |||||
* | Add Lora | Volpeon | 2023-02-07 | 1 | -3/+18 |
| | |||||
* | WIP: Modularization ("free(): invalid pointer" my ass) | Volpeon | 2023-01-14 | 1 | -4/+15 |
| | |||||
* | Cleanup | Volpeon | 2023-01-14 | 1 | -15/+4 |
| | |||||
* | Added progressive aspect ratio bucketing | Volpeon | 2023-01-07 | 1 | -11/+12 |
| | |||||
* | Add prompt template argument to inference | Volpeon | 2023-01-06 | 1 | -0/+7 |
| | |||||
* | Update | Volpeon | 2023-01-05 | 1 | -1/+1 |
| | |||||
* | Update | Volpeon | 2023-01-05 | 1 | -11/+29 |
| | |||||
* | Various cleanups | Volpeon | 2023-01-05 | 1 | -3/+3 |
| | |||||
* | Update | Volpeon | 2023-01-04 | 1 | -4/+3 |
| | |||||
* | Various updates | Volpeon | 2023-01-04 | 1 | -12/+44 |
| | |||||
* | Bugfixes for multi-vector token handling | Volpeon | 2022-12-31 | 1 | -4/+9 |
| | |||||
* | Added multi-vector embeddings | Volpeon | 2022-12-31 | 1 | -5/+9 |
| | |||||
* | Set default dimensions to 768; add config inheritance | Volpeon | 2022-12-26 | 1 | -6/+5 |
| | |||||
* | Code simplifications, avoid autocast | Volpeon | 2022-12-25 | 1 | -24/+24 |
| | |||||
* | Avoid increased VRAM usage on validation | Volpeon | 2022-12-15 | 1 | -2/+2 |
| | |||||
* | More generic datset filter | Volpeon | 2022-12-14 | 1 | -2/+3 |
| | |||||
* | Unified loading of TI embeddings | Volpeon | 2022-12-13 | 1 | -32/+2 |
| | |||||
* | Add support for resume in Textual Inversion | Volpeon | 2022-12-13 | 1 | -1/+1 |
| | |||||
* | Dreambooth: Support loading Textual Inversion embeddings | Volpeon | 2022-12-12 | 1 | -1/+1 |
| | |||||
* | Various updated; shuffle prompt content during training | Volpeon | 2022-12-10 | 1 | -5/+22 |
| | |||||
* | Fix sample steps | Volpeon | 2022-12-06 | 1 | -1/+1 |
| | |||||
* | Update | Volpeon | 2022-12-01 | 1 | -0/+1 |
| | |||||
* | Update | Volpeon | 2022-12-01 | 1 | -1/+2 |
| | |||||
* | Update | Volpeon | 2022-11-27 | 1 | -29/+23 |
| | |||||
* | Refactoring | Volpeon | 2022-11-14 | 1 | -3/+4 |
| | |||||
* | Update | Volpeon | 2022-11-14 | 1 | -8/+13 |
| | |||||
* | Update | Volpeon | 2022-11-03 | 1 | -1/+1 |
| | |||||
* | New Euler_a scheduler | Volpeon | 2022-10-26 | 1 | -12/+4 |
| | |||||
* | Add optional TI functionality to Dreambooth | Volpeon | 2022-10-21 | 1 | -3/+3 |
| | |||||
* | Improved prompt handling | Volpeon | 2022-10-18 | 1 | -10/+5 |
| | |||||
* | Implemented extended prompt limit | Volpeon | 2022-10-17 | 1 | -1/+11 |
| | |||||
* | Removed aesthetic gradients; training improvements | Volpeon | 2022-10-14 | 1 | -28/+4 |
| | |||||
* | Added support for Aesthetic Gradients | Volpeon | 2022-10-13 | 1 | -23/+52 |
| | |||||
* | Added TI+Dreambooth training | Volpeon | 2022-10-13 | 1 | -4/+4 |
| | |||||
* | Various updates | Volpeon | 2022-10-12 | 1 | -5/+5 |
| | |||||
* | Update | Volpeon | 2022-10-09 | 1 | -2/+2 |
| | |||||
* | Update | Volpeon | 2022-10-08 | 1 | -5/+7 |
| | |||||
* | Training: Create multiple class images per training image | Volpeon | 2022-10-07 | 1 | -1/+4 |
| | |||||
* | Update | Volpeon | 2022-10-06 | 1 | -0/+14 |
| | |||||
* | Inference: Add support for embeddings | Volpeon | 2022-10-04 | 1 | -2/+30 |
| | |||||
* | Small perf improvements | Volpeon | 2022-10-03 | 1 | -2/+3 |
| | |||||
* | Small performance improvements | Volpeon | 2022-10-02 | 1 | -5/+13 |
| |