vision.face
vision
Detect face landmarks (478 points) or bounding boxes using MediaPipe
Inlets
video
Video input
| Message | Description |
|---|---|
bang | Toggle enabled state |
boolean | Set enabled state directly |
number | 0 disables, non-zero enables |
Outlets
| Message | Description |
|---|---|
| Face landmarks (478 pts), optional blendshapes, or bounding boxes (detect mode) |
Tags
mediapipefacelandmarkblendshapedetectionmlvisionmesh