YingVideo-MV: Music-Driven Multi-Stage Video Generation

TL;DR

YingVideo-MV is a novel cascaded framework that automatically generates high-quality, music-driven long videos with synchronized camera motions, leveraging audio analysis, shot planning, and diffusion architectures for improved coherence.

Contribution

It introduces the first cascaded approach for music-driven long-video generation, integrating camera motion control and adaptive denoising strategies for enhanced video quality.

Findings

Achieves high-quality, synchronized music videos with camera motions.

Outperforms existing methods in coherence and expressiveness.

Demonstrates effective long-sequence consistency and synchronization.

Abstract

While diffusion model for audio-driven avatar video generation have achieved notable process in synthesizing long sequences with natural audio-visual synchronization and identity consistency, the generation of music-performance videos with camera motions remains largely unexplored. We present YingVideo-MV, the first cascaded framework for music-driven long-video generation. Our approach integrates audio semantic analysis, an interpretable shot planning module (MV-Director), temporal-aware diffusion Transformer architectures, and long-sequence consistency modeling to enable automatic synthesis of high-quality music performance videos from audio signals. We construct a large-scale Music-in-the-Wild Dataset by collecting web data to support the achievement of diverse, high-quality results. Observing that existing long-video generation methods lack explicit camera motion control, we introduce a camera adapter module that embeds camera poses into latent noise. To enhance continulity between clips during long-sequence inference, we further propose a time-aware dynamic window range strategy that adaptively adjust denoising ranges based on audio embedding. Comprehensive benchmark tests demonstrate that YingVideo-MV achieves outstanding performance in generating coherent and expressive music videos, and enables precise music-motion-camera synchronization. More videos are available in our project page: https://giantailab.github.io/YingVideo-MV/ .