Commit message (Collapse) | Author | Age | Files | Lines | ||
---|---|---|---|---|---|---|
... | ||||||
* | 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 | |
| | ||||||
* | Improved aspect ratio bucketing | Volpeon | 2023-01-08 | 1 | -1/+1 | |
| | ||||||
* | Cleanup | Volpeon | 2023-01-07 | 1 | -0/+54 | |
| | ||||||
* | Made aspect ratio bucketing configurable | Volpeon | 2023-01-07 | 1 | -7/+2 | |
| | ||||||
* | Added progressive aspect ratio bucketing | Volpeon | 2023-01-07 | 1 | -2/+2 | |
| | ||||||
* | Update | Volpeon | 2023-01-06 | 1 | -6/+6 | |
| | ||||||
* | Use context manager for EMA, on_train/eval hooks | Volpeon | 2023-01-06 | 2 | -27/+26 | |
| | ||||||
* | Add contextmanager to EMAModel to apply weights temporarily | Volpeon | 2023-01-06 | 1 | -0/+12 | |
| | ||||||
* | Added EMA to TI | Volpeon | 2023-01-05 | 1 | -5/+95 | |
| | ||||||
* | Fix LR finder | Volpeon | 2023-01-05 | 1 | -7/+23 | |
| | ||||||
* | Update | Volpeon | 2023-01-05 | 1 | -1/+4 | |
| | ||||||
* | Various cleanups | Volpeon | 2023-01-05 | 1 | -0/+75 | |
| | ||||||
* | Update | Volpeon | 2023-01-04 | 1 | -1/+6 | |
| | ||||||
* | Various updates | Volpeon | 2023-01-04 | 1 | -4/+0 | |
| | ||||||
* | Better eval generator | Volpeon | 2023-01-04 | 1 | -3/+3 | |
| | ||||||
* | Fixed reproducibility, more consistant validation | Volpeon | 2023-01-04 | 2 | -30/+68 | |
| | ||||||
* | Added vector dropout | Volpeon | 2023-01-03 | 1 | -3/+6 | |
| | ||||||
* | Fixed LR finder | Volpeon | 2023-01-02 | 1 | -17/+21 | |
| | ||||||
* | Update | Volpeon | 2023-01-02 | 1 | -2/+31 | |
| | ||||||
* | Fix | Volpeon | 2023-01-02 | 1 | -1/+1 | |
| | ||||||
* | Improved one cycle scheduler | Volpeon | 2023-01-02 | 1 | -30/+62 | |
| | ||||||
* | Update | Volpeon | 2023-01-01 | 1 | -3/+3 | |
| | ||||||
* | Updates | Volpeon | 2023-01-01 | 2 | -1/+7 | |
| | ||||||
* | Fixed accuracy calc, other improvements | Volpeon | 2023-01-01 | 1 | -48/+0 | |
| | ||||||
* | Added multi-vector embeddings | Volpeon | 2022-12-31 | 1 | -4/+56 | |
| | ||||||
* | Training script improvements | Volpeon | 2022-12-30 | 1 | -5/+8 | |
| | ||||||
* | Update | Volpeon | 2022-12-29 | 2 | -11/+16 | |
| | ||||||
* | Training improvements | Volpeon | 2022-12-29 | 2 | -23/+27 | |
| | ||||||
* | Updated 1-cycle scheduler | Volpeon | 2022-12-28 | 2 | -9/+15 | |
| | ||||||
* | Integrated updates from diffusers | Volpeon | 2022-12-28 | 2 | -15/+36 | |
| | ||||||
* | Improved learning rate finder | Volpeon | 2022-12-27 | 1 | -13/+25 | |
| | ||||||
* | Added validation phase to learn rate finder | Volpeon | 2022-12-27 | 1 | -11/+23 | |
| | ||||||
* | Added learning rate finder | Volpeon | 2022-12-27 | 1 | -0/+115 | |
| | ||||||
* | Code simplifications, avoid autocast | Volpeon | 2022-12-25 | 1 | -57/+49 | |
| | ||||||
* | Update | Volpeon | 2022-12-25 | 2 | -2/+3 | |
| | ||||||
* | Update | Volpeon | 2022-12-24 | 1 | -3/+3 | |
| |