CLIPSegDetectorProvider

ImpactPack/Util

CLIPSegDetectorProvider

Provides a detection function using CLIPSeg, which generates masks based on text prompts. To use this node, the CLIPSeg custom node must be installed.

Example

JSON Example

{
  "class_type": "CLIPSegDetectorProvider",
  "inputs": {
    "text": "example text",
    "blur": 7,
    "threshold": 0.4,
    "dilation_factor": 4
  }
}

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
text?	STRING	required	-	-
blur?	FLOAT	required	min: 0, max: 15, step: 0.1	7
threshold?	FLOAT	required	min: 0, max: 1, step: 0.05	0.4
dilation_factor?	INT	required	min: 0, max: 10, step: 1	4

Outputs

Index	Name	Type	Is List	Connection Reference
0	BBOX_DETECTOR	BBOX_DETECTOR	No	["{node_id}", 0]

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 CLIPSegDetectorProvider node in your workflow, and output_index is the index from the table above.

Example

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

• BBOX_DETECTOR (BBOX_DETECTOR): ["5", 0]

Package: comfyui-impact-pack