Automated Movie Generation via Multi-Agent CoT Planning

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.

• The paper introduces MovieAgent, a novel framework using hierarchical multi-agent Chain of Thought planning to automate long-form movie generation.
• The system employs multiple AI agents simulating roles like director, screenwriter, and storyboard artist to plan scenes and narratives comprehensively.
• Experiments show MovieAgent achieves state-of-the-art results in script faithfulness, character consistency, and narrative coherence, significantly reducing human effort.

The paper "Automated Movie Generation via Multi-Agent CoT Planning" outlines a novel framework for generating long-form movies through multi-agent Chain of Thought planning.

• MovieAgent automates movie production by leveraging a hierarchical CoT-based reasoning process.
• Multiple agents simulate roles like director, screenwriter, and storyboard artist for comprehensive scene and narrative planning.
• Experiments demonstrate state-of-the-art results in script faithfulness, character consistency, and narrative coherence.

In summary, the paper presents a sophisticated approach that significantly reduces human effort while enhancing the coherence and quality of automated movie generation.