Add a LoraLoader node to apply loras to models and clip.

The models are modified in place before being used and unpatched after.
I think this is better than monkeypatching since it might make it easier
to use faster non pytorch unet inference in the future.
This commit is contained in:
comfyanonymous
2023-02-03 02:06:34 -05:00
parent 96664f5d5e
commit ef90e9c376
3 changed files with 233 additions and 33 deletions

View File