Data

Tools

Indexes

Applications

Experiments

Open Sustainable Technology

https://github.com/yk7333/d3po

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"
diffusion-models human-feedback reinforcement-learning
Added: over 1 year ago - Last Synced: 11 months ago - Created: November 23, 2023

  • Relevant topics? true
  • External users? true
  • Open source license? true
  • Active? true
  • Fork? false
  • Main Language: Python
  • Commits: 36
  • Committers: 2
  • Issues: 6
  • Pull Requests: 2
  • Owner: yk7333
  • Stars: 121
  • Forks: 9
  • Packages: 0