Search

More Filters

Show More
Add Listing
Go Back

FilmAgent

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

FilmAgent is a research-grade multi-agent system and codebase designed to automate end-to-end film production inside prebuilt 3D virtual spaces. The repository implements a studio-style pipeline that simulates core crew roles including directors, screenwriters, actors, and cinematographers and orchestrates their interaction to generate coherent scripts, actor profiles, camera shot plans, and audio assets. It provides Python code, example tests, instructions to run language models, guidance to integrate a separate text-to-speech repository for voice acting, and steps to execute generated scripts in a supplied Unity project. The project also accompanies a paper, slides, and video material and documents experiment scripts and model choices used in the authors' evaluations. The goal is to reproduce and extend the published FilmAgent experiments and to prototype multi-agent workflows for automated storytelling in 3D environments.

Links

Stars
1009
App URL
https://github.com/HITsz-TMG/FilmAgent
Github Repository
https://github.com/HITsz-TMG/FilmAgent/blob/main/README.md

Categorization

App Details

Features
A multi-stage film pipeline that follows idea development, scriptwriting, and cinematography with explicit collaboration strategies such as Critique-Correct-Verify and Debate-Judge. Role-based agents (director, screenwriter, actor, cinematographer) collectively produce line-level annotations including actor positions, actions, dialogue, and camera shots. Integration points for large language models are included with examples using gpt-4o and DeepSeek variants and configurable model selection. Utilities generate script.json, actors_profile.json and .wav audio files. Support for external text-to-speech via a ChatTTS repository is documented. The repo includes Unity project instructions and compatibility notes including a recommended Unity version and a required Newtonsoft JSON package. Evaluation artifacts include test_full.py, test_no_interation.py, and test_cot.py for comparative experiments.
Use Cases
FilmAgent serves researchers and developers who want to build, test, or extend automated film production systems driven by multiple collaborating agents. It provides a reproducible environment to compare single-agent and multi-agent approaches, to evaluate different LLMs and model-selection strategies, and to inspect the effects of agent debates and critiques on script coherence and camera planning. The included pipeline and Unity playback enable end-to-end verification from prompt to playable scene, while the TTS integration produces voice acting for characters. The repo also contains case studies and comparisons with related systems that help users understand trade-offs in consistency, storytelling, and shot design. Overall it lowers the barrier to experiment with agent orchestration for virtual filmmaking.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*