Skip to main content
The SamplerDPMPP_3M_SDE node creates a DPM++ 3M SDE sampler for use in the sampling process. This sampler uses a third-order multistep stochastic differential equation method with configurable noise parameters. The node allows you to choose whether noise calculations are performed on the GPU or CPU.

Inputs

ParameterDescriptionData TypeRequiredRange
etaControls the stochasticity of the sampling process (default: 1.0)FLOATYes0.0 - 100.0
s_noiseControls the amount of noise added during sampling (default: 1.0)FLOATYes0.0 - 100.0
noise_deviceSelects the device for noise calculations, either GPU or CPU (default: “gpu”)COMBOYes”gpu"
"cpu”

Outputs

Output NameDescriptionData Type
samplerReturns a configured sampler object for use in sampling workflowsSAMPLER
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): d25f8f69211ebca5aca8d1925d53f90a1bee3f883239635bffc107b5fdae8b36