MeshGraphormer Hand Refiner With External Detector

ControlNet Preprocessors/Normal and Depth Estimators

MeshGraphormer+ImpactDetector-DepthMapPreprocessor

Example

JSON Example

{
  "class_type": "MeshGraphormer+ImpactDetector-DepthMapPreprocessor",
  "inputs": {
    "image": [
      "node_id",
      0
    ],
    "bbox_detector": [
      "node_id",
      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
image	IMAGE	required	-	-
bbox_detector	BBOX_DETECTOR	required	-	-
bbox_threshold	FLOAT	optional	min: 0.1, max: 1, step: 0.01	0.5
bbox_dilation	INT	optional	min: -512, max: 512, step: 1	10
bbox_crop_factor	FLOAT	optional	min: 1, max: 10, step: 0.01	3
drop_size	INT	optional	min: 1, max: 16384, step: 1	10
mask_bbox_padding	INT	optional	min: 0, max: 100, step: 1	30
mask_type	ENUM 3 options based_on_depth tight_bboxes original	optional	-	"based_on_depth"
mask_expand	INT	optional	min: -16384, max: 16384, step: 1	5
rand_seed	INT	optional	min: 0, max: 1.84e+19, step: 1	88
resolution	INT	optional	min: 64, max: 16384, step: 64	512

Outputs

Index	Name	Type	Is List	Connection Reference
0	IMAGE	IMAGE	No	["{node_id}", 0]
1	INPAINTING_MASK	MASK	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 MeshGraphormer+ImpactDetector-DepthMapPreprocessor node in your workflow, and output_index is the index from the table above.

Example

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

• IMAGE (IMAGE): ["5", 0]
• INPAINTING_MASK (MASK): ["5", 1]

Package: comfyui-controlnet-aux