Documentation Index
Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
Use this file to discover all available pages before exploring further.
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Overview
Detects faces in an image and identifies 468 facial landmarks (key points) on each face using MediaPipe’s BlazeFace and FaceMesh models. It also calculates ARKit-52 blendshape coefficients for facial expression analysis. The node can process multiple images in a batch and outputs both the landmark data and bounding boxes for each detected face.Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
face_detection_model | FACE_DETECTION_MODEL | Yes | The MediaPipe face detection model to use for landmark detection. | |
image | IMAGE | Yes | The input image or batch of images to detect faces in. | |
detector_variant | COMBO | Yes | "short""full""both" | Face detector range. "short" is tuned for close-up faces (within ~2 m of the camera); "full" covers farther/smaller faces (up to ~5 m) but is slower. "both" runs both detectors and keeps whichever found more faces per frame (~2x detection cost). Default: "short". |
num_faces | INT | Yes | 0 to 16 | Maximum number of faces to return per frame. 0 means no cap (return all detected). Default: 1. |
min_confidence | FLOAT | No | 0.00 to 1.00 | BlazeFace score threshold. Lower values help catch small or occluded faces. Default: 0.5. |
missing_frame_fallback | COMBO | No | "empty""previous""interpolate" | Per-frame behavior when detection fails in a batch. "empty" leaves the frame faceless. "previous" copies the most recent successful detection. "interpolate" lerps landmarks/bbox/blendshapes between bracketing successful frames. Multi-face: pairs faces across frames by greedy bbox-centre NN. Default: "empty". |
Outputs
| Output Name | Data Type | Description |
|---|---|---|
face_landmarks | FACE_LANDMARKS | A structured output containing per-frame face detection results, including 468 facial landmarks, ARKit-52 blendshape coefficients, transformation matrices, and connection sets for mesh visualization. |
bboxes | BOUNDING_BOX | A list of bounding boxes for each detected face, with coordinates (x, y, width, height), label “face”, and confidence score. One list per input frame. |
Source fingerprint (SHA-256):
f60ed6201288a59d65d62cc98c12f227a353870c36decea8da81a063cfdf2bba