Commit message (Expand) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | New loss scaling | Volpeon | 2023-06-24 | 1 | -67/+41 |
* | Added Prodigy optimizer | Volpeon | 2023-06-24 | 1 | -1/+9 |
* | Fix | Volpeon | 2023-06-24 | 1 | -4/+5 |
* | Fixes | Volpeon | 2023-06-24 | 2 | -5/+5 |
* | Update | Volpeon | 2023-06-23 | 1 | -1/+25 |
* | Update | Volpeon | 2023-06-22 | 1 | -1/+2 |
* | Update | Volpeon | 2023-06-22 | 1 | -4/+7 |
* | Remove training guidance_scale | Volpeon | 2023-06-22 | 1 | -17/+1 |
* | Remove convnext | Volpeon | 2023-06-22 | 1 | -13/+0 |
* | Update | Volpeon | 2023-06-21 | 2 | -13/+10 |
* | Update | Volpeon | 2023-06-21 | 7 | -117/+245 |
* | Fix LoRA training with DAdan | Volpeon | 2023-05-16 | 2 | -3/+3 |
* | Avoid model recompilation due to varying prompt lengths | Volpeon | 2023-05-16 | 2 | -49/+2 |
* | Patch xformers to cast dtypes | Volpeon | 2023-05-16 | 1 | -6/+5 |
* | Support LoRA training for token embeddings | Volpeon | 2023-05-16 | 2 | -11/+5 |
* | Fix for latest PEFT | Volpeon | 2023-05-12 | 1 | -0/+47 |
* | Update | Volpeon | 2023-05-11 | 1 | -9/+15 |
* | Update | Volpeon | 2023-05-06 | 3 | -13/+171 |
* | Update | Volpeon | 2023-05-05 | 1 | -12/+21 |
* | torch.compile won't work yet, keep code prepared | Volpeon | 2023-04-29 | 1 | -0/+3 |
* | Fixed model compilation | Volpeon | 2023-04-29 | 1 | -3/+3 |
* | Support torch.compile | Volpeon | 2023-04-28 | 1 | -4/+8 |
* | Fixed loss/acc logging | Volpeon | 2023-04-28 | 2 | -17/+22 |
* | Update | Volpeon | 2023-04-27 | 3 | -34/+54 |
* | Update | Volpeon | 2023-04-21 | 3 | -6/+8 |
* | Fix | Volpeon | 2023-04-17 | 1 | -1/+1 |
* | Fix | Volpeon | 2023-04-16 | 1 | -1/+1 |
* | Improved automation caps | Volpeon | 2023-04-16 | 4 | -14/+34 |
* | Fix | Volpeon | 2023-04-16 | 1 | -4/+3 |
* | Fix | Volpeon | 2023-04-15 | 1 | -19/+0 |
* | TI via LoRA | Volpeon | 2023-04-15 | 3 | -9/+15 |
* | Added cycle LR decay | Volpeon | 2023-04-13 | 1 | -1/+4 |
* | Update | Volpeon | 2023-04-13 | 4 | -29/+22 |
* | Experimental convnext discriminator support | Volpeon | 2023-04-11 | 1 | -24/+59 |
* | Store sample images in Tensorboard as well | Volpeon | 2023-04-11 | 1 | -13/+12 |
* | Update | Volpeon | 2023-04-11 | 1 | -12/+10 |
* | Update | Volpeon | 2023-04-10 | 4 | -27/+30 |
* | Fix sample gen: models sometimes weren't in eval mode | Volpeon | 2023-04-10 | 4 | -28/+29 |
* | Update | Volpeon | 2023-04-10 | 4 | -6/+4 |
* | Update | Volpeon | 2023-04-09 | 1 | -1/+1 |
* | Update | Volpeon | 2023-04-09 | 1 | -2/+2 |
* | Fix | Volpeon | 2023-04-09 | 1 | -1/+1 |
* | Update | Volpeon | 2023-04-08 | 2 | -7/+7 |
* | Fix TI | Volpeon | 2023-04-08 | 1 | -1/+2 |
* | Fix | Volpeon | 2023-04-08 | 1 | -3/+2 |
* | Update | Volpeon | 2023-04-08 | 4 | -40/+33 |
* | Fixed Lora PTI | Volpeon | 2023-04-07 | 1 | -16/+19 |
* | Fix | Volpeon | 2023-04-07 | 4 | -19/+8 |
* | Fix | Volpeon | 2023-04-07 | 2 | -6/+8 |
* | Update | Volpeon | 2023-04-07 | 1 | -1/+36 |