d3po
Public[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"
Creat:2023-11-23T16:08:20
Update:2025-03-27T10:24:16
https://arxiv.org/abs/2311.13231
236
Stars
2
Stars Increase
[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"