It introduces an explicit reasoning paradigm that generates physics-accurate motion before committing to pixels, decoupling physical fidelity from visual style and enabling verifiable draft-edit workflows.
Official repository for VideoCoCo, a physics-faithful video generation pipeline that uses code as a chain-of-thought to draft physics before committing to pixels.
We propose VideoCoCo, an interleaved reasoning paradigm that carries a physical prior through an explicit visual draft before committing to pixels.
Our method 🎨 first has a code agent write simulation code and render it in a sandbox as a neutral white/clay proxy video that carries the correct motion, causality, and physics — meaning is expressed by shape, transparency, deformation, and coverage, never by color.
Then we 🔎 verify the proxy against the physical plan (a caused state must stay hidden until its causing transition), and 🖼️ restyle the proxy into a photorealistic video driven by a per-case edit instruction.
skill/ — the five Agent Skills forming the pipeline: physical-state-planner
→ physical-video-blender-implementer → blender-mcp-video →
seedance-edit-prompt → seedance-distill.data/toy_cases/ — 8 hand-checked video-to-video (v2v) triplets.inference/ — batch inference scripts + a patch against upstream OmniWeaving.mickyhimself/VideoCoCo — the tuned transformer.data/toy_cases/ — 8 v2v triplets, one directory per case:
data/toy_cases/
├── manifest.jsonl # one JSON line per case (index)
├── 0000_buoyancy/
│ ├── video.mp4 # source: neutral white/clay physics proxy
│ ├── seedance.mp4 # target: photoreal restyle
│ └── edit_prompt.txt # instruction used to restyle proxy -> photoreal
└── ...
Each manifest.jsonl line:
{"case_id": "0000_buoyancy", "source": "0000_buoyancy/video.mp4", "target": "0000_buoyancy/seedance.mp4", "instruction": "...", "category": "buoyancy"}
video.mp4) — a grayscale/white-material rendCode-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Similar projects matched by category, topics, and programming language.
A Remotion-based tool that converts Chinese story text or ordered hand-drawn images into vertical hand-drawn diary-comic animation with handwritten captions, left-to-right reveals, optional page-curl transitions, and silent H.264 output for post-production dubbing.
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
Kill AI Slop is a multilingual field guide and agent skill that catalogues 33 common AI-generated design tells with interactive before-after demos, and provides a tool to scan and fix web projects.