Verified record · from the answer index
lucataco/dpo-sdxl
modeltested · static-verifiedscore 49/100signed passport ✓published 1037d ago · verified 2026-10-202,200 uses
Direct Preference Optimization (DPO) is a method to align diffusion models to text human preferences by directly optimizing on human comparison data
Declared tools (1)
lucataco/dpo-sdxl
model:replicate:lucataco/dpo-sdxl