| Commit message (Expand) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | Fix | Volpeon | 2023-01-14 | 1 | -2/+2 | |
| * | Cleanup | Volpeon | 2023-01-14 | 1 | -21/+12 | |
| * | Unified training script structure | Volpeon | 2023-01-13 | 1 | -3/+6 | |
| * | Reverted modularization mostly | Volpeon | 2023-01-13 | 1 | -81/+386 | |
| * | More modularization | Volpeon | 2023-01-13 | 1 | -409/+70 | |
| * | Simplified step calculations | Volpeon | 2023-01-13 | 1 | -13/+11 | |
| * | Removed PromptProcessor, modularized training loop | Volpeon | 2023-01-13 | 1 | -215/+53 | |
| * | Added TI decay start offset | Volpeon | 2023-01-13 | 1 | -2/+8 | |
| * | Code deduplication | Volpeon | 2023-01-13 | 1 | -60/+26 | |
| * | Update | Volpeon | 2023-01-12 | 1 | -16/+14 | |
| * | Fixed TI decay | Volpeon | 2023-01-12 | 1 | -8/+3 | |
| * | Disable Adam weight decay | Volpeon | 2023-01-12 | 1 | -1/+1 | |
| * | Fix | Volpeon | 2023-01-11 | 1 | -3/+3 | |
| * | Heck | Volpeon | 2023-01-11 | 1 | -1/+1 | |
| * | TI: Use grad clipping from LoRA #104 | Volpeon | 2023-01-11 | 1 | -8/+11 | |
| * | Better defaults | Volpeon | 2023-01-10 | 1 | -4/+4 | |
| * | Fix | Volpeon | 2023-01-10 | 1 | -1/+1 | |
| * | Added arg to disable tag shuffling | Volpeon | 2023-01-10 | 1 | -6/+16 | |
| * | Enable buckets for validation, fixed vaildation repeat arg | Volpeon | 2023-01-09 | 1 | -4/+1 | |
| * | Add --valid_set_repeat | Volpeon | 2023-01-09 | 1 | -0/+22 | |
| * | Fix | Volpeon | 2023-01-08 | 1 | -1/+1 | |
| * | Improved aspect ratio bucketing | Volpeon | 2023-01-08 | 1 | -1/+15 | |
| * | Fixed aspect ratio bucketing; allow passing token IDs to pipeline | Volpeon | 2023-01-08 | 1 | -11/+13 | |
| * | Improved aspect ratio bucketing | Volpeon | 2023-01-08 | 1 | -48/+37 | |
| * | Cleanup | Volpeon | 2023-01-07 | 1 | -44/+16 | |
| * | Made aspect ratio bucketing configurable | Volpeon | 2023-01-07 | 1 | -0/+13 | |
| * | Added progressive aspect ratio bucketing | Volpeon | 2023-01-07 | 1 | -48/+46 | |
| * | Update | Volpeon | 2023-01-07 | 1 | -3/+3 | |
| * | Relaxed ema_power for TI | Volpeon | 2023-01-06 | 1 | -1/+1 | |
| * | Update | Volpeon | 2023-01-06 | 1 | -24/+17 | |
| * | Use context manager for EMA, on_train/eval hooks | Volpeon | 2023-01-06 | 1 | -54/+66 | |
| * | Add contextmanager to EMAModel to apply weights temporarily | Volpeon | 2023-01-06 | 1 | -33/+24 | |
| * | Log EMA decay | Volpeon | 2023-01-05 | 1 | -1/+2 | |
| * | Added EMA to TI | Volpeon | 2023-01-05 | 1 | -1/+58 | |
| * | Update | Volpeon | 2023-01-05 | 1 | -7/+7 | |
| * | Fix | Volpeon | 2023-01-05 | 1 | -8/+11 | |
| * | Various cleanups | Volpeon | 2023-01-05 | 1 | -65/+21 | |
| * | Update | Volpeon | 2023-01-04 | 1 | -1/+1 | |
| * | Various updates | Volpeon | 2023-01-04 | 1 | -0/+8 | |
| * | Better eval generator | Volpeon | 2023-01-04 | 1 | -6/+6 | |
| * | Fixed reproducibility, more consistant validation | Volpeon | 2023-01-04 | 1 | -5/+19 | |
| * | Don't use vector_dropout by default | Volpeon | 2023-01-03 | 1 | -1/+1 | |
| * | Added vector dropout | Volpeon | 2023-01-03 | 1 | -5/+19 | |
| * | Fixed LR finder | Volpeon | 2023-01-02 | 1 | -3/+3 | |
| * | Update | Volpeon | 2023-01-02 | 1 | -3/+12 | |
| * | Fix | Volpeon | 2023-01-02 | 1 | -4/+2 | |
| * | Save args before training, too | Volpeon | 2023-01-02 | 1 | -0/+4 | |
| * | Fix | Volpeon | 2023-01-02 | 1 | -2/+1 | |
| * | Update | Volpeon | 2023-01-02 | 1 | -6/+6 | |
| * | Improved one cycle scheduler | Volpeon | 2023-01-02 | 1 | -1/+1 | |
 |
index : textual-inversion-diff | |
| textual-inversion-diff |
| summaryrefslogtreecommitdiffstats |
path: root/train_ti.py