Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Various updated; shuffle prompt content during training | Volpeon | 2022-12-10 | 1 | -4/+6 |
| | |||||
* | Fix sample steps | Volpeon | 2022-12-06 | 1 | -1/+1 |
| | |||||
* | Update | Volpeon | 2022-12-04 | 1 | -1/+3 |
| | |||||
* | Update | Volpeon | 2022-12-01 | 1 | -3/+3 |
| | |||||
* | Update | Volpeon | 2022-12-01 | 1 | -8/+9 |
| | |||||
* | Update | Volpeon | 2022-12-01 | 1 | -2/+9 |
| | |||||
* | Update | Volpeon | 2022-11-30 | 1 | -11/+8 |
| | |||||
* | Adjusted training to upstream | Volpeon | 2022-11-28 | 1 | -27/+30 |
| | |||||
* | Fixed noise calculation for v-prediction | Volpeon | 2022-11-28 | 1 | -4/+17 |
| | |||||
* | Fix | Volpeon | 2022-11-27 | 1 | -1/+0 |
| | |||||
* | Generic loading of scheduler (training) | Volpeon | 2022-11-27 | 1 | -20/+9 |
| | |||||
* | Update | Volpeon | 2022-11-27 | 1 | -16/+38 |
| | |||||
* | Refactoring | Volpeon | 2022-11-14 | 1 | -4/+4 |
| | |||||
* | Update | Volpeon | 2022-11-14 | 1 | -30/+41 |
| | |||||
* | Update | Volpeon | 2022-11-03 | 1 | -3/+11 |
| | |||||
* | Update | Volpeon | 2022-11-01 | 1 | -1/+1 |
| | |||||
* | Fix | Volpeon | 2022-10-27 | 1 | -6/+6 |
| | |||||
* | Added CLI arg to set dataloader worker num; improved text encoder handling ↵ | Volpeon | 2022-10-27 | 1 | -8/+33 |
| | | | | with Dreambooth | ||||
* | Euler_a: Re-introduce generator arg for reproducible output | Volpeon | 2022-10-27 | 1 | -2/+2 |
| | |||||
* | New Euler_a scheduler | Volpeon | 2022-10-26 | 1 | -3/+3 |
| | |||||
* | Advanced datasets | Volpeon | 2022-10-24 | 1 | -26/+42 |
| | |||||
* | Update | Volpeon | 2022-10-24 | 1 | -0/+34 |
| | |||||
* | Revert lat; fix skip attribute in dataset | Volpeon | 2022-10-22 | 1 | -75/+86 |
| | |||||
* | Training update | Volpeon | 2022-10-22 | 1 | -86/+75 |
| | |||||
* | Add optional TI functionality to Dreambooth | Volpeon | 2022-10-21 | 1 | -35/+66 |
| | |||||
* | Dreambooth: Added option to insert a new input token; removed Dreambooth Plus | Volpeon | 2022-10-19 | 1 | -6/+42 |
| | |||||
* | Updated Dreambooth training | Volpeon | 2022-10-19 | 1 | -33/+71 |
| | |||||
* | Adapted other scripts for new prompt processing | Volpeon | 2022-10-18 | 1 | -7/+10 |
| | |||||
* | Upstream updates; better handling of textual embedding | Volpeon | 2022-10-17 | 1 | -10/+16 |
| | |||||
* | Update | Volpeon | 2022-10-16 | 1 | -4/+6 |
| | |||||
* | Update | Volpeon | 2022-10-16 | 1 | -9/+32 |
| | |||||
* | Removed aesthetic gradients; training improvements | Volpeon | 2022-10-14 | 1 | -5/+5 |
| | |||||
* | Added support for Aesthetic Gradients | Volpeon | 2022-10-13 | 1 | -10/+0 |
| | |||||
* | Added TI+Dreambooth training | Volpeon | 2022-10-13 | 1 | -5/+10 |
| | |||||
* | Various updates | Volpeon | 2022-10-12 | 1 | -30/+23 |
| | |||||
* | Added EMA support to Textual Inversion | Volpeon | 2022-10-10 | 1 | -11/+12 |
| | |||||
* | Dreambooth: Add EMA support | Volpeon | 2022-10-10 | 1 | -6/+44 |
| | |||||
* | Updated default params | Volpeon | 2022-10-10 | 1 | -4/+4 |
| | |||||
* | Update | Volpeon | 2022-10-09 | 1 | -5/+2 |
| | |||||
* | Update | Volpeon | 2022-10-08 | 1 | -30/+45 |
| | |||||
* | Fix small details | Volpeon | 2022-10-07 | 1 | -22/+23 |
| | |||||
* | Training: Create multiple class images per training image | Volpeon | 2022-10-07 | 1 | -6/+22 |
| | |||||
* | Update | Volpeon | 2022-10-06 | 1 | -1/+1 |
| | |||||
* | Add Textual Inversion with class dataset (a la Dreambooth) | Volpeon | 2022-10-04 | 1 | -15/+10 |
| | |||||
* | Default sample steps 30 -> 40 | Volpeon | 2022-10-04 | 1 | -1/+1 |
| | |||||
* | Fix: Prompts | Volpeon | 2022-10-04 | 1 | -2/+6 |
| | |||||
* | Bugfix | Volpeon | 2022-10-04 | 1 | -4/+4 |
| | |||||
* | Fix | Volpeon | 2022-10-03 | 1 | -8/+2 |
| | |||||
* | Dreambooth: Generate specialized class images from input prompts | Volpeon | 2022-10-03 | 1 | -98/+70 |
| | |||||
* | Small perf improvements | Volpeon | 2022-10-03 | 1 | -43/+46 |
| |