This is a turbo diffusion model. All versions work with 12 steps, simple scheduler and CFG 1. Version 2.0 nvfp4 has a hyper-turbo LoRA included and works well with as few as 6 steps.
My first attempt at a Krea2 merge, based on Kroma 0.3.1 turbo with additional furry concept training, and LoRAs extracted from Willy's Furry Mix and Wulver. Good style flexibility, and excellent LoRA compatibility. LoRAs should be trained on Krea2 base.
Description
Lightest weight version, only 6-steps needed. simple scheduler, CFG 1
FAQ
Comments (1)
This is a really good model. Just like everyone else said. It knowing furry art makes it much more versatile, even if you never create furry art.