Introduction
This model is fine-tuned from Anima Base 1.0.
It focuses on cute and diverse anime-style outputs while improving overall stability.
Recommended Settings
Steps: 20–30
CFG scale: 4–5
Sampler: ER SDE / Euler A
Notes
If you encounter any issues, please leave feedback so I can try to improve them in future versions.
Description
For v2, DPO training was conducted on approximately 3,000 preference pairs to improve model quality.