Effectively increases prompt adherence in a manner that's a bit different than CFG. Helps when the model isn't following instructions correctly.

- -0.005 weight = -0.5x
- 0.01 weight = +1ร—
- 0.1 weight  = +10ร—
- 1.0 weight  = +100ร—
Downloads last month
28,782
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ 1 Ask for provider support

Model tree for Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers

Base model

krea/Krea-2-Raw
Adapter
(1380)
this model

Space using Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers 1