Skip to main content
This node is designed to generate a sampler for the DPMPP_2M_SDE model, allowing for the creation of samples based on specified solver types, noise levels, and computational device preferences. It abstracts the complexities of sampler configuration, providing a streamlined interface for generating samples with customized settings.

Inputs

ParameterDescriptionData Type
solver_typeSpecifies the solver type to be used in the sampling process, offering options between ‘midpoint’ and ‘heun’. This choice influences the numerical integration method applied during sampling.COMBO[STRING]
etaDetermines the step size in the numerical integration, affecting the granularity of the sampling process. A higher value indicates a larger step size.FLOAT
s_noiseControls the level of noise introduced during the sampling process, influencing the variability of the generated samples.FLOAT
noise_deviceIndicates the computational device (‘gpu’ or ‘cpu’) on which the noise generation process is executed, affecting performance and efficiency.COMBO[STRING]

Outputs

ParameterDescriptionData Type
samplerThe output is a sampler configured according to the specified parameters, ready for generating samples.SAMPLER
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub