Age | Commit message (Collapse) | Author | Lines | |
---|---|---|---|---|
2023-12-05 | change state dict comparison to ref compare | Jabasukuriputo Wang | -1/+1 | |
2023-08-16 | send weights to target device instead of CPU memory | AUTOMATIC1111 | -9/+15 | |
2023-08-16 | RAM optimization round 2 | AUTOMATIC1111 | -7/+44 | |
2023-07-24 | Use less RAM when creating models | AUTOMATIC1111 | -5/+101 | |
2023-05-10 | autofixes from ruff | AUTOMATIC | -1/+1 | |
2023-02-05 | make it possible to load SD1 checkpoints without CLIP | AUTOMATIC | -7/+10 | |
2023-01-22 | fix missing field for aesthetic embedding extension | AUTOMATIC | -1/+3 | |
2023-01-11 | fix for an error caused by skipping initialization, for realsies this time: ↵ | AUTOMATIC | -39/+32 | |
TypeError: expected str, bytes or os.PathLike object, not NoneType | ||||
2023-01-10 | add support for transformers==4.25.1 | AUTOMATIC | -6/+36 | |
add fallback for when quick model creation fails | ||||
2023-01-10 | add more stuff to ignore when creating model from config | AUTOMATIC | -4/+25 | |
prevent .vae.safetensors files from being listed as stable diffusion models | ||||
2023-01-10 | disable torch weight initialization and CLIP downloading/reading checkpoint ↵ | AUTOMATIC | -0/+44 | |
to speedup creating sd model from config |