You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Generates a LoRA from the difference of two models. If you specify a dimension, it will be created with the specified dimension. If no demension is specified, LoRAs are created with dim 128. The blend ratio can be adjusted by alpha and beta. (alpha x Model_A - beta x Model B) alpha, beta = 1 is the normal LoRA creation.
So instead of doing the merging to get an inpainting version of a custom model could you just make a LoRA out of the difference between sd-v1-5-inpainting and v1-5-pruned so that we could just load it onto whatever model model and make it work for inpainting?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Generates a LoRA from the difference of two models. If you specify a dimension, it will be created with the specified dimension. If no demension is specified, LoRAs are created with dim 128. The blend ratio can be adjusted by alpha and beta. (alpha x Model_A - beta x Model B) alpha, beta = 1 is the normal LoRA creation.So instead of doing the merging to get an inpainting version of a custom model could you just make a LoRA out of the difference between
sd-v1-5-inpaintingandv1-5-prunedso that we could just load it onto whatever model model and make it work for inpainting?Beta Was this translation helpful? Give feedback.
All reactions