| Commit message (Expand) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | TI: Use grad clipping from LoRA #104 | Volpeon | 2023-01-11 | 1 | -1/+1 | |
| * | Added arg to disable tag shuffling | Volpeon | 2023-01-10 | 1 | -10/+10 | |
| * | Fixed aspect ratio bucketing; allow passing token IDs to pipeline | Volpeon | 2023-01-08 | 1 | -6/+8 | |
| * | Improved aspect ratio bucketing | Volpeon | 2023-01-08 | 1 | -1/+1 | |
| * | Cleanup | Volpeon | 2023-01-07 | 1 | -0/+54 | |
| * | Made aspect ratio bucketing configurable | Volpeon | 2023-01-07 | 1 | -7/+2 | |
| * | Added progressive aspect ratio bucketing | Volpeon | 2023-01-07 | 1 | -2/+2 | |
| * | Update | Volpeon | 2023-01-06 | 1 | -6/+6 | |
| * | Use context manager for EMA, on_train/eval hooks | Volpeon | 2023-01-06 | 2 | -27/+26 | |
| * | Add contextmanager to EMAModel to apply weights temporarily | Volpeon | 2023-01-06 | 1 | -0/+12 | |
| * | Added EMA to TI | Volpeon | 2023-01-05 | 1 | -5/+95 | |
| * | Fix LR finder | Volpeon | 2023-01-05 | 1 | -7/+23 | |
| * | Update | Volpeon | 2023-01-05 | 1 | -1/+4 | |
| * | Various cleanups | Volpeon | 2023-01-05 | 1 | -0/+75 | |
| * | Update | Volpeon | 2023-01-04 | 1 | -1/+6 | |
| * | Various updates | Volpeon | 2023-01-04 | 1 | -4/+0 | |
| * | Better eval generator | Volpeon | 2023-01-04 | 1 | -3/+3 | |
| * | Fixed reproducibility, more consistant validation | Volpeon | 2023-01-04 | 2 | -30/+68 | |
| * | Added vector dropout | Volpeon | 2023-01-03 | 1 | -3/+6 | |
| * | Fixed LR finder | Volpeon | 2023-01-02 | 1 | -17/+21 | |
| * | Update | Volpeon | 2023-01-02 | 1 | -2/+31 | |
| * | Fix | Volpeon | 2023-01-02 | 1 | -1/+1 | |
| * | Improved one cycle scheduler | Volpeon | 2023-01-02 | 1 | -30/+62 | |
| * | Update | Volpeon | 2023-01-01 | 1 | -3/+3 | |
| * | Updates | Volpeon | 2023-01-01 | 2 | -1/+7 | |
| * | Fixed accuracy calc, other improvements | Volpeon | 2023-01-01 | 1 | -48/+0 | |
| * | Added multi-vector embeddings | Volpeon | 2022-12-31 | 1 | -4/+56 | |
| * | Training script improvements | Volpeon | 2022-12-30 | 1 | -5/+8 | |
| * | Update | Volpeon | 2022-12-29 | 2 | -11/+16 | |
| * | Training improvements | Volpeon | 2022-12-29 | 2 | -23/+27 | |
| * | Updated 1-cycle scheduler | Volpeon | 2022-12-28 | 2 | -9/+15 | |
| * | Integrated updates from diffusers | Volpeon | 2022-12-28 | 2 | -15/+36 | |
| * | Improved learning rate finder | Volpeon | 2022-12-27 | 1 | -13/+25 | |
| * | Added validation phase to learn rate finder | Volpeon | 2022-12-27 | 1 | -11/+23 | |
| * | Added learning rate finder | Volpeon | 2022-12-27 | 1 | -0/+115 | |
| * | Code simplifications, avoid autocast | Volpeon | 2022-12-25 | 1 | -49/+41 | |
| * | Update | Volpeon | 2022-12-25 | 2 | -2/+3 | |
| * | Update | Volpeon | 2022-12-24 | 1 | -3/+3 | |
| * | Fixed Textual Inversion | Volpeon | 2022-12-24 | 1 | -10/+5 | |
| * | Training update | Volpeon | 2022-12-24 | 1 | -2/+0 | |
| * | Fix | Volpeon | 2022-12-24 | 1 | -1/+1 | |
| * | Fix again | Volpeon | 2022-12-24 | 1 | -1/+1 | |
| * | Fix | Volpeon | 2022-12-24 | 1 | -1/+4 | |
| * | Improved class prompt handling | Volpeon | 2022-12-23 | 1 | -3/+1 | |
| * | Simplified trainable embedding code again | Volpeon | 2022-12-23 | 1 | -19/+6 | |
| * | Fixed and simplified trainable embeddings code | Volpeon | 2022-12-23 | 1 | -12/+12 | |
| * | Fixed Textual Inversion | Volpeon | 2022-12-22 | 1 | -6/+3 | |
| * | Improved Textual Inversion: Completely exclude untrained embeddings from trai... | Volpeon | 2022-12-22 | 1 | -0/+70 | |
| * | Some LoRA fixes (still broken) | Volpeon | 2022-12-21 | 1 | -13/+55 | |
| * | Moved common training code into separate module | Volpeon | 2022-12-21 | 2 | -1/+132 | |
 |
index : textual-inversion-diff | |
| textual-inversion-diff |
| summaryrefslogtreecommitdiffstats |