FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

Mengchao Wang1* Qiang Wang1* Fan Jiang1† Yaqi Fan2 Yunpeng Zhang1,2 YongGang Qi2‡ Kun Zhao1. Mu Xu1
1AMAP,Alibaba Group 2Beijing University of Posts and Telecommunications
1 9
1 9
0.1 3
1 50
Examples
Input Image Input Audio