Skip to main content
The SamplerSASolver node implements a custom sampling algorithm for diffusion models. It uses a predictor-corrector approach with configurable order settings and stochastic differential equation (SDE) parameters to generate samples from the input model.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe diffusion model to use for samplingMODELYes-
etaControls the step size scaling factor (default: 1.0)FLOATNo0.0 - 10.0
sde_start_percentThe starting percentage for SDE sampling (default: 0.2)FLOATNo0.0 - 1.0
sde_end_percentThe ending percentage for SDE sampling (default: 0.8)FLOATNo0.0 - 1.0
s_noiseControls the amount of noise added during sampling (default: 1.0)FLOATNo0.0 - 100.0
predictor_orderThe order of the predictor component in the solver (default: 3)INTNo1 - 6
corrector_orderThe order of the corrector component in the solver (default: 4)INTNo0 - 6
use_peceEnables or disables the PECE (Predict-Evaluate-Correct-Evaluate) methodBOOLEANNo-
simple_order_2Enables or disables simplified second-order calculationsBOOLEANNo-

Outputs

Output NameDescriptionData Type
samplerA configured sampler object that can be used with diffusion modelsSAMPLER
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): f1491a63377d4d8a5c44cb7109afba09678ef9c048786f9086a5437aacb17753