Post #2938718

Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation The method adopts a causal dual-stream DiT model to generate synchronized avatar video and speech in a streaming manner. Hallo-Live reaches 20.38 FPS with 0.94 s latency on two NVIDIA H200 GPUs, while preserving strong lip-sync accuracy, visual fidelity, and speech quality. Built on #LMDB https://github.com/fudan-generative-vision/Hallo-Live