Existing DiT-based audio-driven avatar generation methods have achieved considerable progress, yet their broader application is constrained by limitations such as high computational overhead and the inability to synthesize long-duration videos. Autoregressive methods address this problem by applying block-wise autoregressive diffusion methods. However, these methods suffer from the problem of error accumulation and quality degradation. To address this, we propose JoyStreamer-Flash, an audio-driven autoregressive model capable of real-time inference and infinite-length video generation with the following contributions: (1) Progressive Step Bootstrapping (PSB), which allocates more denoising steps to initial frames to stabilize generation and reduce error accumulation; (2) Motion Condition Injection (MCI), enhancing temporal coherence by injecting noise-corrupted previous frames as motion condition; and (3) Unbounded RoPE via Cache-Resetting (URCR), enabling infinite-length generation through dynamic positional encoding. Our 1.3B-parameter causal model achieves 16 FPS on a single GPU and achieves competitive results in visual quality, temporal consistency, and lip synchronization.
@article{arxiv.2512.11423,
title = {JoyStreamer-Flash: Real-time and Infinite Audio-Driven Avatar Generation with Autoregressive Diffusion},
author = {Chaochao Li and Ruikui Wang and Liangbo Zhou and Jinheng Feng and Huaishao Luo and Huan Zhang and Youzheng Wu and Xiaodong He},
journal= {arXiv preprint arXiv:2512.11423},
year = {2026}
}