| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Improved dataset prompt handling, fixed | Volpeon | 2022-12-19 | 1 | -1034/+0 |
| | | |||||
| * | Avoid increased VRAM usage on validation | Volpeon | 2022-12-15 | 1 | -3/+8 |
| | | |||||
| * | More generic datset filter | Volpeon | 2022-12-14 | 1 | -3/+10 |
| | | |||||
| * | Unified loading of TI embeddings | Volpeon | 2022-12-13 | 1 | -12/+11 |
| | | |||||
| * | Optimized Textual Inversion training by filtering dataset by existence of ↵ | Volpeon | 2022-12-13 | 1 | -3/+10 |
| | | | | | added tokens | ||||
| * | Fixed sample/checkpoint frequency | Volpeon | 2022-12-13 | 1 | -11/+9 |
| | | |||||
| * | Add support for resume in Textual Inversion | Volpeon | 2022-12-13 | 1 | -65/+54 |
| | | |||||
| * | Dreambooth: Support loading Textual Inversion embeddings | Volpeon | 2022-12-12 | 1 | -14/+23 |
| | | |||||
| * | Support attention_mask of text encoder | Volpeon | 2022-12-10 | 1 | -4/+5 |
| | | |||||
| * | Update | Volpeon | 2022-12-04 | 1 | -1/+3 |
| | | |||||
| * | Update | Volpeon | 2022-12-01 | 1 | -3/+3 |
| | | |||||
| * | Update | Volpeon | 2022-12-01 | 1 | -4/+5 |
| | | |||||
| * | Update | Volpeon | 2022-12-01 | 1 | -0/+1 |
| | | |||||
| * | Adjusted training to upstream | Volpeon | 2022-11-28 | 1 | -23/+26 |
| | | |||||
| * | Fixed noise calculation for v-prediction | Volpeon | 2022-11-28 | 1 | -9/+20 |
| | | |||||
| * | Fixed and improved Textual Inversion training | Volpeon | 2022-11-27 | 1 | -44/+68 |
| | | |||||
| * | Fix | Volpeon | 2022-11-27 | 1 | -1/+0 |
| | | |||||
| * | Generic loading of scheduler (training) | Volpeon | 2022-11-27 | 1 | -14/+9 |
| | | |||||
| * | Refactoring | Volpeon | 2022-11-14 | 1 | -4/+4 |
| | | |||||
| * | Update | Volpeon | 2022-11-14 | 1 | -4/+9 |
| | | |||||
| * | Update | Volpeon | 2022-11-03 | 1 | -3/+11 |
| | | |||||
| * | Added CLI arg to set dataloader worker num; improved text encoder handling ↵ | Volpeon | 2022-10-27 | 1 | -0/+10 |
| | | | | | with Dreambooth | ||||
| * | New Euler_a scheduler | Volpeon | 2022-10-26 | 1 | -3/+3 |
| | | |||||
| * | Advanced datasets | Volpeon | 2022-10-24 | 1 | -24/+34 |
| | | |||||
| * | Training update | Volpeon | 2022-10-22 | 1 | -1/+0 |
| | | |||||
| * | Add optional TI functionality to Dreambooth | Volpeon | 2022-10-21 | 1 | -7/+8 |
| | | |||||
| * | 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 | -17/+24 |
| | | |||||
| * | Update | Volpeon | 2022-10-16 | 1 | -2/+4 |
| | | |||||
| * | Update | Volpeon | 2022-10-16 | 1 | -11/+17 |
| | | |||||
| * | Update | Volpeon | 2022-10-15 | 1 | -12/+21 |
| | | |||||
| * | Removed aesthetic gradients; training improvements | Volpeon | 2022-10-14 | 1 | -18/+14 |
| | | |||||
| * | Added support for Aesthetic Gradients | Volpeon | 2022-10-13 | 1 | -10/+0 |
| | | |||||
| * | Added TI+Dreambooth training | Volpeon | 2022-10-13 | 1 | -3/+8 |
| | | |||||
| * | Various updates | Volpeon | 2022-10-12 | 1 | -60/+14 |
| | | |||||
| * | Added EMA support to Textual Inversion | Volpeon | 2022-10-10 | 1 | -6/+48 |
| | | |||||
| * | TI: Use different lr scheduler | Volpeon | 2022-10-10 | 1 | -1/+1 |
| | | |||||
| * | Updated default params | Volpeon | 2022-10-10 | 1 | -3/+3 |
| | | |||||
| * | Update | Volpeon | 2022-10-09 | 1 | -6/+4 |
| | | |||||
| * | Update | Volpeon | 2022-10-08 | 1 | -29/+28 |
| | | |||||
| * | Fix small details | Volpeon | 2022-10-07 | 1 | -35/+35 |
| | | |||||
| * | Training: Create multiple class images per training image | Volpeon | 2022-10-07 | 1 | -13/+35 |
| | | |||||
| * | Update | Volpeon | 2022-10-06 | 1 | -11/+101 |
| | | |||||
| * | Add Textual Inversion with class dataset (a la Dreambooth) | Volpeon | 2022-10-04 | 1 | -7/+6 |
| | | |||||
| * | Default sample steps 30 -> 40 | Volpeon | 2022-10-04 | 1 | -1/+1 |
| | | |||||
| * | Dreambooth: Generate specialized class images from input prompts | Volpeon | 2022-10-03 | 1 | -4/+2 |
| | | |||||
| * | Small perf improvements | Volpeon | 2022-10-03 | 1 | -2/+4 |
| | | |||||
| * | Added negative prompt support for training scripts | Volpeon | 2022-10-03 | 1 | -60/+23 |
| | | |||||
| * | Fixed euler_a generator argument | Volpeon | 2022-10-03 | 1 | -8/+0 |
| | | |||||
| * | Assign unused images in validation dataset to train dataset | Volpeon | 2022-10-03 | 1 | -3/+9 |
| | | |||||
 |
index : textual-inversion-diff | |
| textual-inversion-diff |
| summaryrefslogtreecommitdiffstats |
path: root/textual_inversion.py