3 papers
cs.CV2024
FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation
Tianyun Zhong, Chao Liang, Jianwen Jiang +3
Diffusion-based audio-driven talking avatar methods have recently gained attention for their high-fidelity, vivid, and expressive results. However, their slow inference speed limit…
cs.CV2024
Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
Jianwen Jiang, Chao Liang, Jiaqi Yang +3
With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalne…
cs.CV2024
CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention
Gaojie Lin, Jianwen Jiang, Chao Liang +3
Diffusion-based video generation technology has advanced significantly, catalyzing a proliferation of research in human animation. However, the majority of these studies are confin…