Video-Coder 9B Model
This repository contains the Video-Coder-9B for Video-Coder: Reinforcing Agentic Coding for Video Generation.
🌐 Project Page | 📖 Paper | 💻 Code
👀 Intro
We introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to construct a dynamic 3D scene (Draft Video) that provides structure and motion signals to downstream video generators.
We curate two high-quality datasets, Video-Coder-SFT-10k and Video-Coder-RL-4k, which contain diverse prompts and ground-truth reference videos.
We further develop the Video-Coder Harness, a unified interactive environment integrating code execution, 3D scene rendering, and execution feedback for agent training and inference.
Video-Coder achieves significant gains, improving Minimax-H3 by approximately 7 points on PhyGenBench and 24 points on VBench-2.0.
🎥 Demo
🚀 Training and Inference
For detailed instructions on setup, SFT/RL training, and inference, please refer to the official GitHub repository.
Citation
If you find this work helpful for your research, please consider citing: