Guided video keying with clean subject extraction control.

Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning — you still choose inputs, prompts, and settings.

Open preloaded workflow on RunComfy

Open preloaded workflow on RunComfy (browser)

Why RunComfy first
- Fewer missing-node surprises — run the graph in a managed environment before you mirror it locally.
- Quick GPU tryout — useful if your local VRAM or install time is the bottleneck.
- Matches the published JSON — the zip follows the same runnable workflow you can open on RunComfy.

When downloading for local ComfyUI makes sense — you want full control over models on disk, batch scripting, or offline runs.

How to use (local ComfyUI)
1. Load inputs (images/video/audio) in the marked loader nodes.
2. Set prompts, resolution, and seeds; start with a short test run.
3. Export from the Save / Write nodes shown in the graph.

Expectations — First run may pull large weights; cloud runs may require a free RunComfy account.

Overview

This guided workflow helps you extract clean video foregrounds with precise control. Designed for editors and compositors, it refines coarse masks into smooth mattes. You can accurately separate subjects from complex scenes without edge artifacts. Built for live-action editing, it enhances compositing clarity and saves cleanup time. Perfect for creators seeking production-ready keying results with adjustable matting responsiveness.

Important nodes:

Key nodes in Comfyui CorridorKey ComfyUI workflow

CorridorKey (#28)

This is the centerpiece that transforms a rough guide into a production-ready matte and foreground. Treat the guide mask as the main steering signal: if it is too tight you may clip hair and motion blur, and if it is too loose the key can creep into the background. Keep your input color space consistent across the plate and mask, and rely on the QC output to judge edge integrity before exporting. When refining tricky shots, iterate on the coarse mask rather than over-tweaking downstream steps.

ImageToMask (#31)

This node extracts a single-channel matte from the mask clip. Match its channel selector to how your mask is encoded, for example red for solid-red graphics or the appropriate channel for color-coded mattes. If your mask is grayscale, select the luminance-appropriate channel so white represents subject and black represents background. A clean binary or near-binary input here greatly improves CorridorKey’s stability.

Notes

CorridorKey ComfyUI Workflow | Guided Keying and Matting Control — see RunComfy page for the latest node requirements.