Spaces:
Running on Zero
Running on Zero
multimodalart HF Staff
Restore working harness app (SFT prompt, per-step GPU requests); add bird example
cb5eccc verified | title: Video-Coder | |
| emoji: 🎬 | |
| colorFrom: yellow | |
| colorTo: pink | |
| sdk: gradio | |
| sdk_version: 6.31.0 | |
| app_file: app.py | |
| short_description: Agent writes Blender code to build a 3D draft video | |
| python_version: "3.12" | |
| startup_duration_timeout: 1h | |
| license: apache-2.0 | |
| models: | |
| - Video-Coder/Video-Coder-9B | |
| # Video-Coder | |
| Demo of [Video-Coder: Reinforcing Agentic Coding for Video Generation](https://huggingface.co/papers/2611.09894) | |
| ([code](https://github.com/CYWang735/Video-Coder), [model](https://huggingface.co/Video-Coder/Video-Coder-9B)). | |
| **Video-Coder-9B** runs inside a port of the authors' *Video-Coder Harness*: it writes a Blender 4.5 Python script | |
| for the scene description, renders it (`run_blender`, bpy 4.5.14 / Workbench on CPU), looks at the rendered frames, | |
| fixes problems and submits. The output is the **draft video** (white-model render with the scene's layout, motion and | |
| camera). | |
| The paper then turns the draft video into a final video with MiniMax-H3 (Ref2VA). That ~33B audio-video generator | |
| (plus its large text encoder) does not fit alongside the agent in this Space, so this demo stops at the draft video. | |
| The harness code in `harness/` is taken from the Video-Coder repository (`Video-Coder-RL/uni-agent`, Apache-2.0). | |
| Example prompts are from the Video-Coder project page and repository. | |