MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

1 code implementation • 5 Jul 2024 • Zhaorun Chen, Yichao Du, Zichen Wen, Yiyang Zhou, Chenhang Cui, Zhenzhen Weng, Haoqin Tu, Chaoqi Wang, Zhengwei Tong, Qinglan Huang, Canyu Chen, Qinghao Ye, Zhihong Zhu, Yuqing Zhang, Jiawei Zhou, Zhuokai Zhao, Rafael Rafailov, Chelsea Finn, Huaxiu Yao

Compared with open-source VLMs, smaller-sized scoring models can provide better feedback regarding text-image alignment and image quality, while VLMs provide more accurate feedback regarding safety and generation bias due to their stronger reasoning capabilities.

Hallucination Text to Image Generation +1