Skip to main content
This node is designed to generate a sampler for the DPM++ SDE (Stochastic Differential Equation) model. It adapts to both CPU and GPU execution environments, optimizing the sampler’s implementation based on the available hardware.

Inputs

ParameterDescriptionData Type
etaSpecifies the step size for the SDE solver, influencing the granularity of the sampling process.FLOAT
s_noiseDetermines the level of noise to be applied during the sampling process, affecting the diversity of the generated samples.FLOAT
rControls the ratio of noise reduction in the sampling process, impacting the clarity and quality of the generated samples.FLOAT
noise_deviceSelects the execution environment (CPU or GPU) for the sampler, optimizing performance based on available hardware.COMBO[STRING]

Outputs

ParameterDescriptionData Type
samplerThe generated sampler configured with the specified parameters, ready for use in sampling operations.SAMPLER
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub