MAViS is an end-to-end multi-agent collaborative framework for feature-length video storytelling. It coordinates specialized agents across multiple stages, including script writing, shot design, character modeling, keyframe generation, video animation, and audio generation. At each stage, agents operate according to the 3E principles of Explore, Examine, and Enhance to ensure the quality of the intermediate output. Considering the limitations of current generative models, we present script writing guidelines to optimize compatibility between scripts and generation tools. Experimental results demonstrate that MAViS achieves state-of-the-art performance in assistive features, visual quality, and video expressiveness. Its modular framework enables extensibility with various generative models and tools. With just brief user prompts, it generates high-quality, expressive feature-length video storytelling, enriching users' inspiration and creativity. MAViS is the only framework that provides multimodal design outputs, such as videos with narrative and background music.
