Picture for Qinkai Li

Qinkai Li

ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

Add code
Apr 13, 2023
Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, Yuxiao Dong

Figure 1 for ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Figure 2 for ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Figure 3 for ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Figure 4 for ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

We present ImageReward -- the first general-purpose text-to-image human preference reward model -- to address various prevalent issues in generative models and align them with human values and preferences. Its training is based on our systematic annotation pipeline that covers both the rating and ranking components, collecting a dataset of 137k expert comparisons to date. In human evaluation, ImageReward outperforms existing scoring methods (e.g., CLIP by 38.6\%), making it a promising automatic metric for evaluating and improving text-to-image synthesis. The reward model is publicly available via the \texttt{image-reward} package at \url{https://github.com/THUDM/ImageReward}.

* 24 pages 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon