SAMDetector (segmented)

ImpactPack/Detector

SAMDetectorSegmented

Example

JSON Example

{
  "class_type": "SAMDetectorSegmented",
  "inputs": {
    "sam_model": [
      "node_id",
      0
    ],
    "segs": [
      "node_id",
      0
    ],
    "image": [
      "node_id",
      0
    ],
    "detection_hint": "center-1",
    "dilation": 0,
    "threshold": 0.93,
    "bbox_expansion": 0,
    "mask_hint_threshold": 0.7,
    "mask_hint_use_negative": "False"
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

Name	Type	Status	Constraints	Default
sam_model?	SAM_MODEL	required	-	-
segs?	SEGS	required	-	-
image?	IMAGE	required	-	-
detection_hint?	ENUM 9 options center-1 horizontal-2 vertical-2 rect-4 diamond-4 mask-area mask-points mask-point-bbox none	required	-	-
dilation?	INT	required	min: -512, max: 512, step: 1	0
threshold	FLOAT	required	min: 0, max: 1, step: 0.01	0.93
bbox_expansion?	INT	required	min: 0, max: 1000, step: 1	0
mask_hint_threshold?	FLOAT	required	min: 0, max: 1, step: 0.01	0.7
mask_hint_use_negative?	ENUM 3 options False Small Outter	required	-	-

Outputs

Index	Name	Type	Is List	Connection Reference
0	combined_mask	MASK	No	["{node_id}", 0]
1	batch_masks	MASK	No	["{node_id}", 1]

How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this SAMDetectorSegmented node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

• combined_mask (MASK): ["5", 0]
• batch_masks (MASK): ["5", 1]

Package: comfyui-impact-pack