Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Abstract

Audio-driven avatar interaction demands real-time, stream-ing, and in_x001C_nite-length generation_x0016_capabilities fundamentally at oddswith the sequential denoising and long-horizon drift of current di_x001B_usionmodels. We present Live Avatar, an algorithm-system co-designed frame-work that addresses both challenges for a 14-billion-parameter di_x001B_usionmodel. On the algorithm side, a two-stage pipeline distills a pre-trained bidirectional model into a causal, few-step streaming one whoseKV cache stores noisy rather than clean history. This lossy condition-ing, counter-intuitively, suppresses error accumulation and enables mod-els trained on short clips to generalize stably beyond 10,000 seconds.On the system side, this noisy conditioning also breaks the sequen-tial sampling bottleneck, allowing Timestep-forcing Pipeline Parallelism(TPP) to assign each GPU a _x001C_xed denoising timestep, converting the se-quential di_x001B_usion chain into an asynchronous spatial pipeline that simul-taneously boosts throughput and improves temporal consistency. LiveAvatar achieves 45 FPS with a TTFF of 1.21 s on 5 H100 GPUs, andto our knowledge is the _x001C_rst to enable practical real-time streaming ofa 14B di_x001B_usion model for in_x001C_nite-length avatar generation. Our projectpage is at https://liveavatar.github.io/.