Unimatch Optical Flow

ControlNet Preprocessors/Optical Flow

Unimatch_OptFlowPreprocessor

Example

JSON Example

{
  "class_type": "Unimatch_OptFlowPreprocessor",
  "inputs": {
    "image": [
      "node_id",
      0
    ],
    "ckpt_name": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors",
    "backward_flow": false,
    "bidirectional_flow": 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
image	IMAGE	required	-	-
ckpt_name	ENUM 3 options gmflow-scale1-mixdata.pth gmflow-scale2-mixdata.pth gmflow-scale2-regrefine6-mixdata.pth URL: Checkpoint	required	-	"gmflow-scale2-regrefine6-mixdata.pth"
backward_flow	BOOLEAN	required	-	false
bidirectional_flow	BOOLEAN	required	-	false

Outputs

Index	Name	Type	Is List	Connection Reference
0	OPTICAL_FLOW	OPTICAL_FLOW	No	["{node_id}", 0]
1	PREVIEW_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 Unimatch_OptFlowPreprocessor node in your workflow, and output_index is the index from the table above.

Example

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

• OPTICAL_FLOW (OPTICAL_FLOW): ["5", 0]
• PREVIEW_IMAGE (IMAGE): ["5", 1]

Package: comfyui-controlnet-aux