Anima Aesthetic Turbo LoRA

Details

Model description

This Turbo LoRA is extracted by taking the delta difference of Anima Turbo v1.0 and Anima Aesthetic v1.0, then compressed to a 128-rank LoRA.

This works well on Anima Aesthetic-based checkpoint, and half-well on Anima Base-based checkpoint.

Start with CFG 1 and 8-12 steps

Images made by this model