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 SamplerDPMPP_2M_SDE node creates a DPM++ 2M SDE sampler for diffusion models. This sampler uses second-order differential equation solvers with stochastic differential equations to generate samples. It provides different solver types and noise handling options to control the sampling process.

Inputs

ParameterData TypeRequiredRangeDescription
solver_typeSTRINGYes"midpoint"
"heun"
The type of differential equation solver to use for the sampling process
etaFLOATYes0.0 - 100.0Controls the stochasticity of the sampling process (default: 1.0)
s_noiseFLOATYes0.0 - 100.0Controls the amount of noise added during sampling (default: 1.0)
noise_deviceSTRINGYes"gpu"
"cpu"
The device where noise calculations are performed

Outputs

Output NameData TypeDescription
samplerSAMPLERA configured sampler object ready for use in the sampling pipeline