ComfyUI Node
Video Actor Extract
A ComfyUI node in video/actor with 9 inputs and 3 outputs.
Video Actor Extract
- images
- actor_info_json
- output_dir
- actor_count
◄model_pathyolov8n.pt►
◄seg_model_pathyolov8n-seg.pt►
◄video_path►
◄max_actors10►
◄face_threshold0.60►
◄min_track_length5►
◄skip_every_n1►
◄bg_colortransparent►
Categoryvideo/actor
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| images | IMAGE | — | |
| model_pathopt | STRING | yolov8n.pt | — |
| seg_model_pathopt | STRING | yolov8n-seg.pt | YOLOv8-seg model for person segmentation |
| video_pathopt | STRING | Optional: original video path for metadata. If empty, metadata is estimated. | |
| max_actorsopt | INT | 101–50 | — |
| face_thresholdopt | FLOAT | 0.600.1–0.99 | — |
| min_track_lengthopt | INT | 51–100 | — |
| skip_every_nopt | INT | 11–30 | Process every Nth frame. 1=all frames, 2=every other frame, etc. Higher values are faster but less precise. |
| bg_coloropt | COMBO | transparent | 5 options: transparent, green, blue, black, white |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| actor_info_json | STRING | — |
| output_dir | STRING | — |
| actor_count | INT | — |