CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration

2026-04-26

AI Summary

Existing automated film generation approaches struggle to simultaneously ensure cross-scene character consistency, multimodal coherence, and narrative continuity. This work proposes a hierarchical multi-agent framework that leverages large language models to collaboratively generate a cinematic blueprint, integrating a decoupled character-centric generation pipeline, instance-level character tracking, cross-modal synthesis, and frame-level audio-visual alignment mechanisms to enable high-quality automatic synthesis of multi-scene, multi-character videos. Experimental results demonstrate that, compared to baseline methods, the proposed approach improves overall consistency by 40%, character consistency by 28.7%, and achieves gains of 4.4% and 5.4% in subject consistency and aesthetic quality, respectively.

Technology Category

• Computer Vision: Multi-modal Vision
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Automated movie creation requires coordinating multiple characters, modalities, and narrative elements across extended sequences -- a challenge that existing end-to-end approaches struggle to address effectively. We present \textbf{CineAGI}, a hierarchical movie generation framework that decomposes this complex task through specialized multi-agent orchestration. Our framework employs three key innovations: (1) a multi-agent narrative synthesis module where specialized LLM agents collaboratively generate comprehensive cinematic blueprints with character profiles, scene descriptions, and cross-modal specifications; (2) a decoupled character-centric pipeline that maintains identity consistency through instance-level tracking and integration while enabling flexible multi-character composition; and (3) a hierarchical audio-visual synchronization mechanism ensuring frame-level alignment of dialogue, expressions, and music. Extensive experiments demonstrate that CineAGI achieves 40\% improvement in overall consistency, 4.4\% gain in subject consistency, 5.4\% enhancement in aesthetic quality, and 28.7\% higher character consistency compared to baselines. Our work establishes a principled foundation for automated multi-scene video generation that preserves narrative coherence and character authenticity.

Problem

• automated movie creation
• character consistency
• multi-modal generation
• cross-scene integration
• narrative coherence

Innovation

• multi-agent orchestration
• character consistency
• hierarchical generation
• cross-modal synthesis
• audio-visual synchronization