The PolyexponentialScheduler node is designed to generate a sequence of noise levels (sigmas) based on a polyexponential noise schedule.
The PolyexponentialScheduler node is designed to generate a sequence of noise levels (sigmas) based on a polyexponential noise schedule. This schedule is a polynomial function in the logarithm of sigma, allowing for a flexible and customizable progression of noise levels throughout the diffusion process.
Inputs
Parameter
Description
Data Type
steps
Specifies the number of steps in the diffusion process, affecting the granularity of the generated noise levels.
INT
sigma_max
The maximum noise level, setting the upper bound of the noise schedule.
FLOAT
sigma_min
The minimum noise level, setting the lower bound of the noise schedule.
FLOAT
rho
A parameter that controls the shape of the polyexponential noise schedule, influencing how noise levels progress between the minimum and maximum values.
FLOAT
Outputs
Parameter
Description
Data Type
sigmas
The output is a sequence of noise levels (sigmas) tailored to the specified polyexponential noise 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