| --- |
| license: apache-2.0 |
| --- |
| |
|
|
| # Video-Coder SFT Model |
|
|
|
|
| This repository contains the Video-Coder-SFT-9B for [Video-Coder: Reinforcing Agentic Coding for Video Generation](). |
|
|
|
|
| [**🌐 Project Page**]() | [**📖 Paper**]() | [**💻 Code**]() |
|
|
|
|
| # 👀 Intro |
|
|
|
|
| <div align="center"> |
| <img src="https://raw.githubusercontent.com/CYWang735/Video-Coder/main/assets/teaser.png" alt="Video-Coder Overview" width="80%"> |
| </div> |
|
|
| 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 |
|
|
|
|
| <div align="center"> |
| <img src="https://raw.githubusercontent.com/CYWang735/Video-Coder/main/assets/qualitative.png" alt="Inference Process" width="85%"> |
| </div> |
|
|
|
|
| ## Citation |
|
|
|
|
| If you find this work helpful for your research, please consider citing: |
|
|
|
|
| ```bibtex |
| |
| |
| ``` |
