Commit message (Expand) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Added Perlin noise to training | Volpeon | 2023-03-04 | 1 | -0/+17 |
* | Removed offset noise from training, added init offset to pipeline | Volpeon | 2023-03-03 | 1 | -10/+2 |
* | Implemented different noise offset | Volpeon | 2023-03-03 | 2 | -22/+10 |
* | Low freq noise with randomized strength | Volpeon | 2023-03-03 | 1 | -1/+8 |
* | Better low freq noise | Volpeon | 2023-03-02 | 1 | -1/+1 |
* | Changed low freq noise | Volpeon | 2023-03-01 | 1 | -23/+10 |
* | Update | Volpeon | 2023-03-01 | 4 | -28/+32 |
* | Fixed TI normalization order | Volpeon | 2023-02-21 | 3 | -15/+19 |
* | Fix | Volpeon | 2023-02-21 | 1 | -6/+3 |
* | Don't rely on Accelerate for gradient accumulation | Volpeon | 2023-02-21 | 2 | -30/+29 |
* | Embedding normalization: Ignore tensors with grad = 0 | Volpeon | 2023-02-21 | 2 | -6/+16 |
* | Update | Volpeon | 2023-02-18 | 1 | -7/+14 |
* | Added Lion optimizer | Volpeon | 2023-02-17 | 1 | -4/+5 |
* | Remove xformers, switch to Pytorch Nightly | Volpeon | 2023-02-17 | 4 | -9/+8 |
* | Fix | Volpeon | 2023-02-16 | 1 | -4/+2 |
* | Integrated WIP UniPC scheduler | Volpeon | 2023-02-16 | 1 | -8/+22 |
* | Update | Volpeon | 2023-02-15 | 1 | -1/+1 |
* | Made low-freq noise configurable | Volpeon | 2023-02-14 | 1 | -6/+11 |
* | Better noise generation during training: https://www.crosslabs.org/blog/diffu... | Volpeon | 2023-02-13 | 1 | -0/+7 |
* | Update | Volpeon | 2023-02-13 | 3 | -3/+3 |
* | Fixed Lora training | Volpeon | 2023-02-08 | 1 | -18/+5 |
* | Fix Lora memory usage | Volpeon | 2023-02-07 | 4 | -9/+3 |
* | Add Lora | Volpeon | 2023-02-07 | 4 | -37/+214 |
* | Restored LR finder | Volpeon | 2023-01-20 | 6 | -393/+82 |
* | Move Accelerator preparation into strategy | Volpeon | 2023-01-19 | 3 | -16/+48 |
* | Update | Volpeon | 2023-01-17 | 4 | -14/+19 |
* | Fix | Volpeon | 2023-01-17 | 1 | -4/+5 |
* | Fix | Volpeon | 2023-01-17 | 1 | -1/+0 |
* | Make embedding decay work like Adam decay | Volpeon | 2023-01-17 | 1 | -9/+5 |
* | Update | Volpeon | 2023-01-17 | 2 | -8/+8 |
* | Update | Volpeon | 2023-01-17 | 4 | -21/+38 |
* | Training update | Volpeon | 2023-01-16 | 3 | -12/+15 |
* | Moved multi-TI code from Dreambooth to TI script | Volpeon | 2023-01-16 | 1 | -3/+14 |
* | More training adjustments | Volpeon | 2023-01-16 | 3 | -8/+9 |
* | Handle empty validation dataset | Volpeon | 2023-01-16 | 3 | -47/+58 |
* | Extended Dreambooth: Train TI tokens separately | Volpeon | 2023-01-16 | 1 | -0/+1 |
* | Implemented extended Dreambooth training | Volpeon | 2023-01-16 | 1 | -3/+4 |
* | Added Dreambooth strategy | Volpeon | 2023-01-15 | 1 | -0/+183 |
* | Restored functional trainer | Volpeon | 2023-01-15 | 2 | -27/+83 |
* | Update | Volpeon | 2023-01-15 | 3 | -119/+64 |
* | Removed unused code, put training callbacks in dataclass | Volpeon | 2023-01-15 | 2 | -44/+39 |
* | Added functional TI strategy | Volpeon | 2023-01-15 | 2 | -0/+282 |
* | Added functional trainer | Volpeon | 2023-01-15 | 1 | -1/+74 |
* | Update | Volpeon | 2023-01-14 | 2 | -122/+24 |
* | Update | Volpeon | 2023-01-14 | 1 | -10/+9 |
* | WIP: Modularization ("free(): invalid pointer" my ass) | Volpeon | 2023-01-14 | 3 | -220/+130 |
* | TI: Prepare UNet with Accelerate as well | Volpeon | 2023-01-14 | 2 | -27/+26 |
* | Fix | Volpeon | 2023-01-14 | 1 | -1/+1 |
* | Cleanup | Volpeon | 2023-01-14 | 2 | -60/+63 |
* | Reverted modularization mostly | Volpeon | 2023-01-13 | 5 | -531/+70 |