Batch CLIPSeg

KJNodes/masking

BatchCLIPSeg

Segments an image or batch of images using CLIPSeg.

Example

JSON Example

{
  "class_type": "BatchCLIPSeg",
  "inputs": {
    "images": [
      "node_id",
      0
    ],
    "text": "example text",
    "threshold": 0.5,
    "binary_mask": true,
    "combine_mask": false,
    "use_cuda": true
  }
}

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
images	IMAGE	required	-	-
text	STRING	required	-	-
threshold	FLOAT	required	min: 0, max: 10, step: 0.001	0.5
binary_mask	BOOLEAN	required	-	true
combine_mask	BOOLEAN	required	-	false
use_cuda	BOOLEAN	required	-	true
blur_sigma	FLOAT	optional	min: 0, max: 100, step: 0.1	0
opt_model	CLIPSEGMODEL	optional	-	-
prev_mask	MASK	optional	-	-
image_bg_level	FLOAT	optional	min: 0, max: 1, step: 0.01	0.5
invert	BOOLEAN	optional	-	false

Outputs

Index	Name	Type	Is List	Connection Reference
0	Mask	MASK	No	["{node_id}", 0]
1	Image	IMAGE	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 BatchCLIPSeg 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]
• Image (IMAGE): ["5", 1]

Package: comfyui-kjnodes