| Commit message (Expand) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | Update | Volpeon | 2023-04-07 | 1 | -42/+261 | |
| * | Update | Volpeon | 2023-04-06 | 1 | -19/+32 | |
| * | Add color jitter | Volpeon | 2023-04-05 | 1 | -3/+12 | |
| * | Fix choice args | Volpeon | 2023-04-04 | 1 | -7/+7 | |
| * | Bring back Lion optimizer | Volpeon | 2023-04-03 | 1 | -3/+27 | |
| * | Lora: Only register params with grad to optimizer | Volpeon | 2023-04-02 | 1 | -3/+7 | |
| * | Update | Volpeon | 2023-04-01 | 1 | -1/+0 | |
| * | Add support for Adafactor, add TI initializer noise | Volpeon | 2023-04-01 | 1 | -1/+15 | |
| * | Update | Volpeon | 2023-03-31 | 1 | -1/+3 | |
| * | Update | Volpeon | 2023-03-31 | 1 | -0/+7 | |
| * | Fix | Volpeon | 2023-03-31 | 1 | -2/+2 | |
| * | Support Dadaptation d0, adjust sample freq when steps instead of epochs are used | Volpeon | 2023-03-31 | 1 | -4/+11 | |
| * | Fix | Volpeon | 2023-03-31 | 1 | -1/+2 | |
| * | Fix | Volpeon | 2023-03-28 | 1 | -1/+1 | |
| * | Support num_train_steps arg again | Volpeon | 2023-03-28 | 1 | -6/+11 | |
| * | Improved inverted tokens | Volpeon | 2023-03-26 | 1 | -0/+1 | |
| * | Update | Volpeon | 2023-03-25 | 1 | -5/+11 | |
| * | Update | Volpeon | 2023-03-24 | 1 | -0/+7 | |
| * | Refactoring, fixed Lora training | Volpeon | 2023-03-24 | 1 | -1/+72 | |
| * | Update | Volpeon | 2023-03-23 | 1 | -3/+0 | |
| * | Log DAdam/DAdan d | Volpeon | 2023-03-21 | 1 | -2/+2 | |
| * | Added dadaptation | Volpeon | 2023-03-21 | 1 | -0/+28 | |
| * | Fixed SNR weighting, re-enabled xformers | Volpeon | 2023-03-21 | 1 | -27/+9 | |
| * | Update | Volpeon | 2023-03-07 | 1 | -7/+16 | |
| * | Pipeline: Perlin noise for init image | Volpeon | 2023-03-04 | 1 | -1/+1 | |
| * | Implemented different noise offset | Volpeon | 2023-03-03 | 1 | -1/+1 | |
| * | Update | Volpeon | 2023-03-01 | 1 | -1/+1 | |
| * | Don't rely on Accelerate for gradient accumulation | Volpeon | 2023-02-21 | 1 | -1/+1 | |
| * | Embedding normalization: Ignore tensors with grad = 0 | Volpeon | 2023-02-21 | 1 | -9/+2 | |
| * | Update | Volpeon | 2023-02-18 | 1 | -3/+5 | |
| * | Added Lion optimizer | Volpeon | 2023-02-17 | 1 | -11/+27 | |
| * | Back to xformers | Volpeon | 2023-02-17 | 1 | -2/+2 | |
| * | Remove xformers, switch to Pytorch Nightly | Volpeon | 2023-02-17 | 1 | -2/+2 | |
| * | Integrated WIP UniPC scheduler | Volpeon | 2023-02-16 | 1 | -1/+2 | |
| * | Update | Volpeon | 2023-02-13 | 1 | -5/+5 | |
| * | Integrate Self-Attention-Guided (SAG) Stable Diffusion in my custom pipeline | Volpeon | 2023-02-08 | 1 | -8/+0 | |
| * | Fixed Lora training | Volpeon | 2023-02-08 | 1 | -7/+18 | |
| * | Fix Lora memory usage | Volpeon | 2023-02-07 | 1 | -2/+2 | |
| * | Add Lora | Volpeon | 2023-02-07 | 1 | -0/+566 | |
| * | Various cleanups | Volpeon | 2023-01-05 | 1 | -946/+0 | |
| * | Training script improvements | Volpeon | 2022-12-30 | 1 | -1/+1 | |
| * | Integrated updates from diffusers | Volpeon | 2022-12-28 | 1 | -6/+4 | |
| * | Set default dimensions to 768; add config inheritance | Volpeon | 2022-12-26 | 1 | -4/+3 | |
| * | Some LoRA fixes (still broken) | Volpeon | 2022-12-21 | 1 | -125/+34 | |
| * | Fix training | Volpeon | 2022-12-20 | 1 | -0/+1040 | |
 |
index : textual-inversion-diff | |
| textual-inversion-diff |
| summaryrefslogtreecommitdiffstats |
path: root/train_lora.py