🔧 Apply CLIPSeg

essentials/segmentation

ApplyCLIPSeg+

Example

JSON Example

{
  "class_type": "ApplyCLIPSeg+",
  "inputs": {
    "clip_seg": [
      "node_id",
      0
    ],
    "image": [
      "node_id",
      0
    ],
    "prompt": "",
    "threshold": 0.4,
    "smooth": 9,
    "dilate": 0,
    "blur": 0
  }
}

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
clip_seg	CLIP_SEG	required	-	-
image	IMAGE	required	-	-
prompt	STRING	required	-	""
threshold	FLOAT	required	min: 0, max: 1, step: 0.05	0.4
smooth	INT	required	min: 0, max: 32, step: 1	9
dilate	INT	required	min: -32, max: 32, step: 1	0
blur	INT	required	min: 0, max: 64, step: 1	0

Outputs

Index	Name	Type	Is List	Connection Reference
0	MASK	MASK	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 ApplyCLIPSeg+ node in your workflow, and output_index is the index from the table above.

Example

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

• MASK (MASK): ["5", 0]

Package: comfyui-essentials