SamplerCustom

sampling/custom_sampling

SamplerCustom

Example

JSON Example

{
  "class_type": "SamplerCustom",
  "inputs": {
    "model": [
      "node_id",
      0
    ],
    "add_noise": true,
    "noise_seed": 0,
    "cfg": 8,
    "positive": [
      "node_id",
      0
    ],
    "negative": [
      "node_id",
      0
    ],
    "sampler": [
      "node_id",
      0
    ],
    "sigmas": [
      "node_id",
      0
    ],
    "latent_image": [
      "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
model	MODEL	required	-	-
add_noise	BOOLEAN	required	-	true
noise_seed	INT	required	min: 0, max: 1.84e+19	0
cfg	FLOAT	required	min: 0, max: 100, step: 0.1	8
positive	CONDITIONING	required	-	-
negative	CONDITIONING	required	-	-
sampler	SAMPLER	required	-	-
sigmas	SIGMAS	required	-	-
latent_image	LATENT	required	-	-

Outputs

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

Example

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

• output (LATENT): ["5", 0]
• denoised_output (LATENT): ["5", 1]

Package: comfyui-extras