---
license: other
license_name: corridor-key-licence-2.0
license_link: LICENSE
pipeline_tag: image-segmentation
tags:
  - video-matting
  - green-screen
  - blue-screen
  - chroma-key
  - vfx
---

# CorridorKey 2.0

Machine-learning green screen and blue screen keying at native resolution, by
[Corridor Digital](https://www.corridordigital.com). Given a clip, CorridorKey
predicts a matte and a clean foreground for every frame, with optional hints
to tell it which subject to key. It is HDR-capable and can write scene-linear
OpenEXR sequences.

> **Want CorridorKey inside your compositing or editing software?** The
> CorridorKey plugin at **[corridorkey.com](https://corridorkey.com)** brings
> this model into media software packages as a one-time purchase.

## How to use

These weights are loaded by the CorridorKey 2.0 inference engine:
**https://github.com/nikopueringer/CorridorKey2.0**

```
git clone https://github.com/nikopueringer/CorridorKey2.0
cd CorridorKey2.0
pip install -r requirements.txt
python scripts/download_weights.py
python infer.py --input shot.mp4 --output_dir out
```

`scripts/download_weights.py` downloads the files in this repository along
with the three foundation models listed below. See the GitHub README for
inference modes, hints, HDR/EXR output, and low-VRAM settings.

## Files

| File | Contents |
|---|---|
| `corridorkey_v2.safetensors` | CorridorKey 2.0 model weights (2.66 GB) |
| `foundation_stats.safetensors` | Normalization statistics for the foundation-model features |

## Requirements

- NVIDIA GPU, RTX 30-series or newer, with at least 4 GB of VRAM for footage
  up to 1440p, or 6 GB for 4K
- CUDA-enabled PyTorch (tested with 2.9.1) and `ffmpeg`

## Foundation models

CorridorKey runs on features from three frozen foundation models. They are not
included in this repository; the download script fetches them from their
original publishers, under their own licenses:

| Model | Publisher | License |
|---|---|---|
| [C-RADIOv4-SO400M](https://huggingface.co/nvidia/C-RADIOv4-SO400M) | NVIDIA | NVIDIA Open Model License |
| [MoGe-2 ViT-B](https://huggingface.co/Ruicheng/moge-2-vitb-normal) | Microsoft | MIT |
| [RVM small](https://github.com/google-deepmind/representations4d) | Google DeepMind | CC-BY 4.0 |

## Training data

All training data for CorridorKey 2.0 was generated in-house at Corridor
Digital using 3D rendering.

## License

Use CorridorKey for whatever you'd like, including processing footage for
commercial projects. What you make with it is yours.

- You may not sell this model, or charge for access to it, and you may not
  offer it as a paid API or inference service.
- You may build on the code and model, but what you release must be freely
  accessible, stay under this same license, and keep the CorridorKey name.
  Donationware and pay-what-you-want are fine.
- Organizations with more than US $20 million in annual revenue need to
  purchase a seat of the CorridorKey plugin for each person using this model.
  See [corridorkey.com](https://corridorkey.com).
- If you run a commercial software package and want to integrate CorridorKey,
  email contact@corridordigital.com.

The full terms are in [LICENSE](LICENSE), a variation of
[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) with
additional terms.