| Commit message (Expand) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | 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 | |
| * | More modularization | Volpeon | 2023-01-13 | 6 | -32/+541 | |
| * | Simplified step calculations | Volpeon | 2023-01-13 | 1 | -20/+22 | |
| * | Removed PromptProcessor, modularized training loop | Volpeon | 2023-01-13 | 2 | -10/+208 | |
| * | Code deduplication | Volpeon | 2023-01-13 | 1 | -0/+55 | |
| * | Update | Volpeon | 2023-01-12 | 1 | -4/+7 | |
| * | Fix | Volpeon | 2023-01-11 | 1 | -2/+2 | |
| * | 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 | |
 |
index : textual-inversion-diff | |
| textual-inversion-diff |
| summaryrefslogtreecommitdiffstats |