corridorkey-green-screen

corridorkey-green-screen — an installable skill for AI agents.

By reason-machines · 1,323 installs

npx skills add reason-machines/trending-skills --skill corridorkey-green-screen

Source repository · Upstream listing

CorridorKey Green Screen Keying Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. CorridorKey is a neural network that solves the color unmixing problem in green screen footage. For every pixel — including semi transparent ones from motion blur, hair, or out of focus edges — it predicts the true straight (un premultiplied) foreground color and a clean linear alpha channel. It reads/writes 16 bit and 32 bit EXR files for VFX pipeline integration. How It Works Two inputs required per frame: 1. RGB green screen image — sRGB or linear gamma, sRGB/REC709 gamut 2. Alpha Hint — rough coarse B&W mask (doesn't need to be precise) The model fills in fine detail from the hint; it's trained on blurry/eroded masks. Installation Prerequisites [uv](https://docs.astral.sh/uv/) package manager (handles Python automatically) NVIDIA GPU with CUDA 12.8+ drivers (for GPU), or Apple M1+ (for MLX), or CPU fallback Windows Linux / macOS Model download: https://huggingface.co/nikopueringer/CorridorKey v1.0/resolve/main/CorridorKey v1.0.pth Optional Alpha Hint Generators Key CLI Commands Docker (Linux + NVIDIA GPU) Directory Structure Python Usage Examples Basic Inference Pipeline Reading/Writing EXR Files Generating a Coarse Alpha Hint with OpenCV Batch Processing Frames Using clip manager.py Alpha Hint Generators Alpha Hint Best Practices Output Integration (Nuke / Fusion / Resolve) CorridorKey outputs straight (un premultiplied) RGBA EXRs in linear light: Troubleshooting CUDA not detected / falling back to CPU OpenEXR read/write fails Out of VRAM Model file not found Docker GPU passthrough fails Poor keying results Hint too expanded : Erode your alpha hint more — CorridorKey is better at adding edge detail than removing unwanted mask area Wrong color space : Ensure input is sRGB/REC709 gamut; don't pass log encoded footage directly Green spill : The model handles color unmixing, but extreme green spill in source may degrade results; consider a despill pass before inference Static subjects : GVM works best on people; try VideoMaMa with a hand drawn hint for props/objects Community & Resources Discord : https://discord.gg/zvwUrdWXJm (Corridor Creates — share results, forks, ideas) Easy UI : [EZ CorridorKey](https://github.com/edenaion/EZ CorridorKey) — artist friendly interface Model weights : https://huggingface.co/nikopueringer/CorridorKey v1.0 GVM project : https://github.com/aim uofa/GVM VideoMaMa project : https://github.com/cvlab kaist/VideoMaMa