Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generation
This addresses the issue of fragmented storytelling and limited filmic quality in automated video generation for applications in filmmaking and content creation, representing an incremental improvement over existing agentic pipelines.
The paper tackled the problem of generating narrative videos with explicit cinematic language by proposing Camera Artist, a multi-agent framework that models a real-world filmmaking workflow, resulting in consistent outperformance over baselines in narrative consistency, dynamic expressiveness, and perceived film quality.
We propose Camera Artist, a multi-agent framework that models a real-world filmmaking workflow to generate narrative videos with explicit cinematic language. While recent multi-agent systems have made substantial progress in automating filmmaking workflows from scripts to videos, they often lack explicit mechanisms to structure narrative progression across adjacent shots and deliberate use of cinematic language, resulting in fragmented storytelling and limited filmic quality. To address this, Camera Artist builds upon established agentic pipelines and introduces a dedicated Cinematography Shot Agent, which integrates recursive storyboard generation to strengthen shot-to-shot narrative continuity and cinematic language injection to produce more expressive, film-oriented shot designs. Extensive quantitative and qualitative results demonstrate that our approach consistently outperforms existing baselines in narrative consistency, dynamic expressiveness, and perceived film quality.