Automated Movie Generation via Multi-Agent CoT Planning
Weijia Wu, Zeyu Zhu, Mike Zheng Shou
2025-03-11
Summary
This paper talks about MovieAgent, an AI system that makes movies automatically by using multiple AI helpers that act like a director, writer, and artist team to plan scenes, characters, and camera angles.
What's the problem?
Making movies with AI is hard because current tools need humans to plan every detail like storylines and character movements, which takes a lot of time and money.
What's the solution?
MovieAgent uses a step-by-step AI team approach where different AI agents handle specific jobs (like writing or camera setup) and work together to create full movies from scripts with consistent characters and smooth scenes.
Why it matters?
This could let creators make movies faster and cheaper, especially for things like social media content or indie films, while keeping stories logical and characters looking the same throughout.
Abstract
Existing long-form video generation frameworks lack automated planning, requiring manual input for storylines, scenes, cinematography, and character interactions, resulting in high costs and inefficiencies. To address these challenges, we present MovieAgent, an automated movie generation via multi-agent Chain of Thought (CoT) planning. MovieAgent offers two key advantages: 1) We firstly explore and define the paradigm of automated movie/long-video generation. Given a script and character bank, our MovieAgent can generates multi-scene, multi-shot long-form videos with a coherent narrative, while ensuring character consistency, synchronized subtitles, and stable audio throughout the film. 2) MovieAgent introduces a hierarchical CoT-based reasoning process to automatically structure scenes, camera settings, and cinematography, significantly reducing human effort. By employing multiple LLM agents to simulate the roles of a director, screenwriter, storyboard artist, and location manager, MovieAgent streamlines the production pipeline. Experiments demonstrate that MovieAgent achieves new state-of-the-art results in script faithfulness, character consistency, and narrative coherence. Our hierarchical framework takes a step forward and provides new insights into fully automated movie generation. The code and project website are available at: https://github.com/showlab/MovieAgent and https://weijiawu.github.io/MovieAgent.