Login / Signup

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model.

Kai YangJian TaoJiafei LyuChunjiang GeJiaxin ChenQimai LiWeihan ShenXiaolong ZhuXiu Li
Published in: CoRR (2023)
Keyphrases
  • diffusion models
  • fine tune
  • diffusion model
  • real time
  • objective function
  • mathematical model
  • neural network
  • artificial neural networks
  • social interaction