StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation

TL;DR

StableAvatar is an innovative end-to-end video diffusion transformer that generates infinite-length, high-quality audio-driven avatar videos with improved synchronization and identity consistency, addressing limitations of previous models.

Contribution

It introduces a novel Time-step-aware Audio Adapter and Audio Native Guidance Mechanism to prevent error accumulation and enhance audio synchronization in long video generation.

Findings

Effective infinite-length video generation demonstrated on benchmarks.

Improved audio-visual synchronization and identity preservation.

Qualitative and quantitative validation of model performance.

Abstract

Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing. Conditioned on a reference image and audio, StableAvatar integrates tailored training and inference modules to enable infinite-length video generation. We observe that the main reason preventing existing models from generating long videos lies in their audio modeling. They typically rely on third-party off-the-shelf extractors to obtain audio embeddings, which are then directly injected into the diffusion model via cross-attention. Since current diffusion backbones lack any audio-related priors, this approach causes severe latent distribution error accumulation across video clips, leading the latent distribution of subsequent segments to drift away from the optimal distribution gradually. To address this, StableAvatar introduces a novel Time-step-aware Audio Adapter that prevents error accumulation via time-step-aware modulation. During inference, we propose a novel Audio Native Guidance Mechanism to further enhance the audio synchronization by leveraging the diffusion's own evolving joint audio-latent prediction as a dynamic guidance signal. To enhance the smoothness of the infinite-length videos, we introduce a Dynamic Weighted Sliding-window Strategy that fuses latent over time. Experiments on benchmarks show the effectiveness of StableAvatar both qualitatively and quantitatively.