SEGS Classify

ImpactPack/HuggingFace

ImpactSEGSClassify

Example

JSON Example

{
  "class_type": "ImpactSEGSClassify",
  "inputs": {
    "classifier": [
      "node_id",
      0
    ],
    "segs": [
      "node_id",
      0
    ],
    "preset_expr": "#Female > #Male",
    "manual_expr": ""
  }
}

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
classifier	TRANSFORMERS_CLASSIFIER	required	-	-
segs	SEGS	required	-	-
preset_expr	ENUM 7 options #Female > #Male #Female < #Male female > 0.5 male > 0.5 Age16to25 > 0.1 Age50to69 > 0.1 Manual expr	required	-	-
manual_expr	STRING	required	-	-
ref_image_opt	IMAGE	optional	-	-

Outputs

Index	Name	Type	Is List	Connection Reference
0	filtered_SEGS	SEGS	No	["{node_id}", 0]
1	remained_SEGS	SEGS	No	["{node_id}", 1]
2	detected_labels	STRING	Yes	["{node_id}", 2]

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

Example

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

• filtered_SEGS (SEGS): ["5", 0]
• remained_SEGS (SEGS): ["5", 1]
• detected_labels (STRING): ["5", 2]

Package: comfyui-impact-pack