SamplerDPMPP_SDE - ComfyUI Built-in Node Documentation - ComfyUI

SamplerDPMPP_SDE creates a DPM++ SDE (Stochastic Differential Equation) sampler for use in the sampling process. This sampler provides a stochastic sampling method with configurable noise parameters and device selection. It returns a sampler object that can be used in the sampling pipeline.

Inputs

Parameter	Description	Data Type	Required	Range
`eta`	Controls the stochasticity of the sampling process (default: 1.0)	FLOAT	Yes	0.0 - 100.0
`s_noise`	Controls the amount of noise added during sampling (default: 1.0)	FLOAT	Yes	0.0 - 100.0
`r`	A parameter that influences the sampling behavior (default: 0.5)	FLOAT	Yes	0.0 - 100.0
`noise_device`	Selects the device where noise calculations are performed. When set to “cpu”, the `dpmpp_sde` sampler is created; when set to “gpu”, the `dpmpp_sde_gpu` sampler is created (default: “gpu”)	COMBO	Yes	”gpu" "cpu”

Note: All inputs are marked as advanced parameters. The noise_device selection changes which sampler variant is created: “cpu” maps to dpmpp_sde and “gpu” maps to dpmpp_sde_gpu.

Outputs

Output Name	Description	Data Type
`sampler`	Returns a configured DPM++ SDE sampler object for use in sampling pipelines	SAMPLER

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): 56949712f245abfcc48c09d7d14a1a7778e80ba58535e538484c382d7e0d02c6