Corridorkey Green Screen
Key green-screen footage with CorridorKey’s neural unmixing to get clean linear alphas and foreground colors for VFX compositing in EXR-based pipelines.
Overview
corridorkey-green-screen is an agent skill for the Build phase that configures and runs CorridorKey neural green-screen keying with alpha hints and EXR pipeline I/O.
Install
npx skills add https://github.com/aradotso/trending-skills --skill corridorkey-green-screenWhat is this skill?
- Neural color unmixing per pixel for motion blur, hair, and soft edges—not classic chroma crush.
- Requires RGB plate plus coarse alpha hint; model refines detail from blurry or eroded masks.
- 16-bit and 32-bit EXR read/write for professional compositing workflows.
- Install paths for Windows batch flow plus uv; GPU (CUDA 12.8+), Apple MLX, or CPU fallback.
- Triggers span setup, alpha matte generation, and VFX compositing in Python.
- Reads and writes 16-bit and 32-bit EXR for pipeline integration
- Two required inputs per frame: RGB plate and coarse alpha hint
Adoption & trust: 1.2k installs on skills.sh; 31 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your green-screen edges look muddy or clipped in comp because traditional chroma keys cannot unmix foreground color and transparency on hair, blur, and soft edges.
Who is it for?
Indie VFX, motion designers, and technical artists already working in linear EXR comps who need AI-assisted keys from hinted masks.
Skip if: Casual creators who only need a one-click MP4 background remover without alpha hints, color management, or GPU setup.
When should I use this skill?
User mentions AI green screen keying, CorridorKey setup, alpha matte from green screen, neural unmixing, or VFX compositing with Python.
What do I get? / Deliverables
You produce clean linear alpha mattes and un-premultiplied foreground colors per frame, ready for EXR-based compositing.
- Clean linear alpha channel per frame
- Straight (un-premultiplied) foreground color output
- EXR assets suitable for compositing tools
Recommended Skills
Journey fit
Build is where pipeline tools and media integrations land before Ship polish; this is production asset prep, not distribution. integrations reflects hooking a Python inference pipeline into existing VFX ingest/export (16/32-bit EXR), not general UI layout.
How it compares
Pipeline-oriented neural keying with hints and EXR—not a browser toy remover or simple FFmpeg chromakey filter.
Common Questions / FAQ
Who is corridorkey-green-screen for?
Solo builders and small teams doing VFX or motion work who export EXR and want agent-guided CorridorKey inference instead of hand-tuning despill on every shot.
When should I use corridorkey-green-screen?
During Build when you are wiring a Python keying step into a compositing pipeline, generating alpha mattes from green screen plus rough masks, or evaluating CorridorKey on CUDA, MLX, or CPU.
Is corridorkey-green-screen safe to install?
Review the Security Audits panel on this Prism page and vet the CorridorKey repo and install scripts before running inference on machines with sensitive footage.
SKILL.md
READMESKILL.md - Corridorkey Green Screen
# 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 ```bat # Double-click or run from terminal: Install_CorridorKey_Windows.bat # Optional heavy modules: Install_GVM_Windows.bat Install_VideoMaMa_Windows.bat ``` ### Linux / macOS ```bash # Install uv curl -LsSf https://astral.sh/uv/install.sh | sh # Install dependencies — pick one: uv sync # CPU / Apple MPS (universal) uv sync --extra cuda # NVIDIA GPU (Linux/Windows) uv sync --extra mlx # Apple Silicon MLX # Download required model (~300MB) mkdir -p CorridorKeyModule/checkpoints # Place downloaded CorridorKey_v1.0.pth as: # CorridorKeyModule/checkpoints/CorridorKey.pth ``` Model download: https://huggingface.co/nikopueringer/CorridorKey_v1.0/resolve/main/CorridorKey_v1.0.pth ### Optional Alpha Hint Generators ```bash # GVM (automatic, ~80GB VRAM, good for people) uv run hf download geyongtao/gvm --local-dir gvm_core/weights # VideoMaMa (requires mask hint, <24GB VRAM with community tweaks) uv run hf download SammyLim/VideoMaMa \ --local-dir VideoMaMaInferenceModule/checkpoints/VideoMaMa uv run hf download stabilityai/stable-video-diffusion-img2vid-xt \ --local-dir VideoMaMaInferenceModule/checkpoints/stable-video-diffusion-img2vid-xt \ --include "feature_extractor/*" "image_encoder/*" "vae/*" "model_index.json" ``` ## Key CLI Commands ```bash # Run inference on prepared clips uv run python main.py run_inference --device cuda uv run python main.py run_inference --device cpu uv run python main.py run_inference --device mps # Apple Silicon # List available clips/shots uv run python main.py list # Interactive setup wizard uv run python main.py wizard uv run python main.py wizard --win_path /path/to/ClipsForInference ``` ## Docker (Linux + NVIDIA GPU) ```bash # Build docker build -t corridorkey:latest . # Run inference docker run --rm -it --gpus all \ -e OPENCV_IO_ENABLE_OPENEXR=1 \ -v "$(pwd)/ClipsForInference:/app/ClipsForInference" \ -v "$(pwd)/Output:/app/Output" \ -v "$(pwd)/CorridorKeyModule/checkpoints:/app/CorridorKeyModule/checkpoints" \ corridorkey:latest run_inference --device cuda # Docker Compose docker compose build docker compose --profile gpu run --rm corridorkey run_inference --device cuda docker compose --profile gpu run --rm corridorkey list # Pin to specific GPU on multi-GPU systems NVIDIA_VISIBLE_DEVICES=0 docker compose --profile gpu run --rm corridorkey run_inference --device cuda ``` ## Directory Structure ``` CorridorKey/ ├── ClipsForInference/ # Input shots go here │ └── my_shot/ │ ├── frames/