ComfyUI Node
SAM2Matting Video
Treats the complete ordered IMAGE batch as one video, seeds the selected frame with a white-foreground mask, and propagates a single temporal predictor state in both directions. Returns only the ordered alpha batch to avoid caching duplicate full-resolution RGB and preview batches.
SAM2Matting Video
- model
- images
- initial_mask
- alpha
◄mask_frame0►
◄mask_threshold0.50►
◄memory_modebalanced►
CategorySAM2Matting/video
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| model | SAM2MATTING_VIDEO_MODEL | — | |
| images | IMAGE | — | |
| initial_mask | MASK | — | |
| mask_frame | INT | 00–2147483647 | — |
| mask_threshold | FLOAT | 0.500–1 | — |
| memory_mode | COMBO | balanced | 3 options: balanced, low_vram, maximum_speed |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| alpha | MASK | — |