AINeutralarXiv – CS AI · 9h ago6/10
🧠
AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation
AsymTalker introduces a diffusion-based method for generating long-form talking head videos with consistent identity and synchronized audio. The approach solves critical challenges in extended video synthesis through temporal reference encoding and asymmetric knowledge distillation, achieving real-time performance at 66 FPS on videos up to 10 minutes long.