LaplaceScheduler - ComfyUI Built-in Node Documentation

The LaplaceScheduler node generates a sequence of sigma values following a Laplace distribution for use in diffusion sampling. It creates a schedule of noise levels that gradually decrease from a maximum to minimum value, using Laplace distribution parameters to control the progression. This scheduler is commonly used in custom sampling workflows to define the noise schedule for diffusion models.

Inputs

Parameter	Description	Data Type	Required	Range
`steps`	Number of sampling steps in the schedule (default: 20)	INT	Yes	1 to 10000
`sigma_max`	Maximum sigma value at the start of the schedule (default: 14.614642)	FLOAT	Yes	0.0 to 5000.0
`sigma_min`	Minimum sigma value at the end of the schedule (default: 0.0291675)	FLOAT	Yes	0.0 to 5000.0
`mu`	Mean parameter for the Laplace distribution (default: 0.0)	FLOAT	Yes	-10.0 to 10.0
`beta`	Scale parameter for the Laplace distribution (default: 0.5)	FLOAT	Yes	0.0 to 10.0

Note: sigma_max, sigma_min, mu, and beta are advanced parameters.

Outputs

Output Name	Description	Data Type
`SIGMAS`	A sequence of sigma values following a Laplace distribution schedule	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): 8e5ca00f4797f863a2cf8b9b115ec27beb7f65981cbb04eb036150402fc19389

​Inputs

​Outputs

Inputs

Outputs