OptimalStepsScheduler - ComfyUI Built-in Node Documentation

The OptimalStepsScheduler node calculates noise schedule sigmas for diffusion models based on the selected model type and step configuration. It adjusts the total number of steps according to the denoise parameter and interpolates the noise levels to match the requested step count. The node returns a sequence of sigma values that determine the noise levels used during the diffusion sampling process.

Inputs

Parameter	Description	Data Type	Required	Range
`model_type`	The type of diffusion model to use for noise level calculation	COMBO	Yes	”FLUX" "Wan" "Chroma”
`steps`	The total number of sampling steps to calculate (default: 20)	INT	Yes	3-1000
`denoise`	Controls the denoising strength, which adjusts the effective number of steps (default: 1.0)	FLOAT	No	0.0-1.0

Note: When denoise is set to less than 1.0, the node calculates the effective steps as steps * denoise. If denoise is set to 0.0, the node returns an empty tensor.

Outputs

Output Name	Description	Data Type
`sigmas`	A sequence of sigma values representing the noise schedule for diffusion sampling	SIGMAS

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 19ad2b96d8256b1fd274f09d863215d4a4375f071829509d9f105d244cee3d28

​Inputs

​Outputs

Inputs

Outputs