Wang, Longyue ORCID: 0000-0002-9062-6183 and Zhang, Min and Others (2024) FilmAgent: Automating Virtual Film Production through a Multi-Agent Collaborative Framework. SA '24: SIGGRAPH Asia 2024 Technical Communications (15). pp. 1-4. ISSN 979-8-4007-1140-4
Virtual film production requires intricate decision-making processes, including scriptwriting, virtual cinematography, and precise actor positioning and actions. Remarkable progress in automated decision-making have utilized agent societies powered by large language models (LLMs). This paper introduces FilmAgent, a novel LLM-based multi-agent collaborative framework designed to automate and streamline the film production process. FilmAgent simulates key crew roles—directors, screenwriters, actors, and cinematographers—within a sandbox environment, integrating efficient human workflows. The process is divided into three stages: planning, scriptwriting, and cinematography. Each stage engages a team of film crews providing iterative feedback, thus verifying intermediate results and reducing errors. Our evaluation of generated videos reveals that collaborative FilmAgent significantly
outperforms individual efforts in line consistency, script coherence,
character actions, and camera settings. Further analysis highlights
the importance of feedback and verification in reducing hallucinations, enhancing script quality, and improving camera choices. We
hope that this project lays the groundwork and shows the potential
of integrating LLMs into creative multimedia tasks
Item Type: | Article (Published) |
---|---|
Refereed: | Yes |
Uncontrolled Keywords: | Multi-agent system, large language model, virtual cinematography |
Subjects: | Computer Science > Computer engineering Computer Science > Computer networks Computer Science > Computer software |
DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing |
Publisher: | Association for Computing Machinery |
Official URL: | https://dl.acm.org/doi/10.1145/3681758.3698014 |
Copyright Information: | Authors |
ID Code: | 30711 |
Deposited On: | 28 Jan 2025 11:02 by Gordon Kennedy . Last Modified 28 Jan 2025 11:02 |
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0 6MB |
Dimensions Badge
Downloads
Downloads per month over past year
Archive Staff Only: edit this record