ComfyUI Node
Face Composite
Composites refined face images back onto original video using bounding box coordinates. Handles frames without faces (bbox at 0,0 with original size) by passing through unchanged.
Face Composite
- original_images
- face_images
- face_bboxes
- composited_images
◄blend_modefeather►
◄feather_amount5►
CategoryWanAnimatePreprocess
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| original_images | IMAGE | Original video frames before face extraction | |
| face_images | IMAGE | Refined face images to composite back | |
| face_bboxes | BBOX | Face bounding boxes from Pose and Face Detection node | |
| blend_modeopt | COMBO | feather | How to blend refined faces back onto original |
| feather_amountopt | INT | 50–200 | Pixels to feather at edge (only for feather mode) |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| composited_images | IMAGE | — |