PolyexponentialScheduler

sampling/custom_sampling/schedulers

PolyexponentialScheduler

Example

JSON Example

{
  "class_type": "PolyexponentialScheduler",
  "inputs": {
    "steps": 20,
    "sigma_max": 14.614642,
    "sigma_min": 0.0291675,
    "rho": 1
  }
}

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
steps	INT	required	min: 1, max: 10000	20
sigma_max	FLOAT	required	min: 0, max: 5000, step: 0.01	14.614642
sigma_min	FLOAT	required	min: 0, max: 5000, step: 0.01	0.0291675
rho	FLOAT	required	min: 0, max: 100, step: 0.01	1

Outputs

Index	Name	Type	Is List	Connection Reference
0	SIGMAS	SIGMAS	No	["{node_id}", 0]

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

Example

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

• SIGMAS (SIGMAS): ["5", 0]

Package: comfyui-extras