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 = +1Γ—
- 0.1 weight  = +10Γ—
- 1.0 weight  = +100Γ—
Downloads last month
18,302
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ 1 Ask for provider support

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

Base model

krea/Krea-2-Raw
Adapter
(1719)
this model

Spaces using Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers 3