| Commit message (Expand) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Update | Volpeon | 2023-06-25 | 1 | -6/+36 |
| * | Update | Volpeon | 2023-06-24 | 1 | -3/+3 |
| * | Fixes | Volpeon | 2023-06-24 | 1 | -6/+12 |
| * | Update | Volpeon | 2023-06-23 | 1 | -19/+1 |
| * | Added prompt dropout | Volpeon | 2023-06-22 | 1 | -1/+1 |
| * | Remove training guidance_scale | Volpeon | 2023-06-22 | 1 | -7/+0 |
| * | Remove convnext | Volpeon | 2023-06-22 | 1 | -10/+0 |
| * | Update | Volpeon | 2023-06-21 | 1 | -7/+0 |
| * | Update | Volpeon | 2023-06-21 | 1 | -178/+201 |
| * | Support LoRA training for token embeddings | Volpeon | 2023-05-16 | 1 | -6/+4 |
| * | Update | Volpeon | 2023-05-11 | 1 | -0/+24 |
| * | Update | Volpeon | 2023-05-06 | 1 | -0/+17 |
| * | Update | Volpeon | 2023-05-05 | 1 | -13/+32 |
| * | Update | Volpeon | 2023-04-27 | 1 | -2/+11 |
| * | Fix cycle loop | Volpeon | 2023-04-23 | 1 | -3/+5 |
| * | Update | Volpeon | 2023-04-20 | 1 | -4/+9 |
| * | Fix | Volpeon | 2023-04-17 | 1 | -3/+3 |
| * | Improved automation caps | Volpeon | 2023-04-16 | 1 | -20/+33 |
| * | Added option to use constant LR on cycles > 1 | Volpeon | 2023-04-16 | 1 | -0/+9 |
| * | Fix | Volpeon | 2023-04-16 | 1 | -14/+7 |
| * | Update | Volpeon | 2023-04-16 | 1 | -1/+5 |
| * | TI via LoRA | Volpeon | 2023-04-15 | 1 | -6/+22 |
| * | Added cycle LR decay | Volpeon | 2023-04-13 | 1 | -3/+5 |
| * | Update | Volpeon | 2023-04-13 | 1 | -3/+10 |
| * | Experimental convnext discriminator support | Volpeon | 2023-04-11 | 1 | -0/+14 |
| * | Update | Volpeon | 2023-04-11 | 1 | -7/+16 |
| * | Randomize dataset across cycles | Volpeon | 2023-04-10 | 1 | -2/+4 |
| * | Update | Volpeon | 2023-04-10 | 1 | -27/+41 |
| * | Update | Volpeon | 2023-04-09 | 1 | -3/+14 |
| * | Fix | Volpeon | 2023-04-09 | 1 | -1/+1 |
| * | Update | Volpeon | 2023-04-09 | 1 | -24/+42 |
| * | Update | Volpeon | 2023-04-08 | 1 | -5/+18 |
| * | Update | Volpeon | 2023-04-08 | 1 | -7/+5 |
| * | Run PTI only if placeholder tokens arg isn't empty | Volpeon | 2023-04-07 | 1 | -6/+6 |
| * | Update | Volpeon | 2023-04-07 | 1 | -3/+3 |
| * | Add color jitter | Volpeon | 2023-04-05 | 1 | -1/+12 |
| * | Fix choice args | Volpeon | 2023-04-04 | 1 | -8/+9 |
| * | TI: Bring back old embedding decay | Volpeon | 2023-04-04 | 1 | -5/+19 |
| * | Improved sparse embeddings | Volpeon | 2023-04-03 | 1 | -1/+1 |
| * | TI: Delta learning | Volpeon | 2023-04-03 | 1 | -26/+11 |
| * | TI: No tag dropout by default | Volpeon | 2023-04-03 | 1 | -1/+1 |
| * | Bring back Lion optimizer | Volpeon | 2023-04-03 | 1 | -3/+27 |
| * | Update dataset format: Separate prompt and keywords | Volpeon | 2023-04-02 | 1 | -1/+1 |
| * | Revert | Volpeon | 2023-04-01 | 1 | -6/+46 |
| * | Combined TI with embedding and LoRA | Volpeon | 2023-04-01 | 1 | -25/+5 |
| * | Experimental: TI via LoRA | Volpeon | 2023-04-01 | 1 | -22/+2 |
| * | Update | Volpeon | 2023-04-01 | 1 | -1/+0 |
| * | Add support for Adafactor, add TI initializer noise | Volpeon | 2023-04-01 | 1 | -2/+23 |
| * | Update | Volpeon | 2023-03-31 | 1 | -1/+3 |
| * | Update | Volpeon | 2023-03-31 | 1 | -0/+7 |
 |
index : textual-inversion-diff | |
| textual-inversion-diff |
| summaryrefslogtreecommitdiffstats |
path: root/train_ti.py