Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The BetaSamplingScheduler node generates a sequence of noise levels (sigmas) for the sampling process using a beta scheduling algorithm. It takes a model and configuration parameters to create a customized noise schedule that controls the denoising process during image generation. This scheduler allows fine-tuning of the noise reduction trajectory through alpha and beta parameters.

Inputs

ParameterData TypeInput TypeDefaultRangeDescription
modelMODELRequired--The model used for sampling, which provides the model sampling object
stepsINTRequired201-10000The number of sampling steps to generate sigmas for
alphaFLOATRequired0.60.0-50.0Alpha parameter for the beta scheduler, controlling the scheduling curve
betaFLOATRequired0.60.0-50.0Beta parameter for the beta scheduler, controlling the scheduling curve

Outputs

Output NameData TypeDescription
SIGMASSIGMASA sequence of noise levels (sigmas) used for the sampling process