SamplerER_SDE - ComfyUI Built-in Node Documentation

The SamplerER_SDE node provides specialized sampling methods for diffusion models, offering different solver types including ER-SDE, Reverse-time SDE, and ODE approaches. It allows control over the stochastic behavior and computational stages of the sampling process. The node automatically adjusts parameters based on the selected solver type to ensure proper functionality.

Inputs

Parameter	Description	Data Type	Required	Range
`solver_type`	The type of solver to use for sampling. Determines the mathematical approach for the diffusion process.	COMBO	Yes	”ER-SDE" "Reverse-time SDE" "ODE”
`max_stage`	The maximum number of stages for the sampling process (default: 3). Controls the computational complexity and quality.	INT	No	1-3
`eta`	Stochastic strength of reverse-time SDE (default: 1.0). When eta=0, it reduces to deterministic ODE. This setting doesn’t apply to ER-SDE solver type.	FLOAT	No	0.0-100.0
`s_noise`	Noise scaling factor for the sampling process (default: 1.0). Controls the amount of noise applied during sampling.	FLOAT	No	0.0-100.0

Parameter Constraints:

When solver_type is set to “ODE” or when using “Reverse-time SDE” with eta=0, both eta and s_noise are automatically set to 0 regardless of user input values.
The eta parameter only affects “Reverse-time SDE” solver type and has no effect on “ER-SDE” solver type.

Outputs

Output Name	Description	Data Type
`sampler`	A configured sampler object that can be used in the sampling pipeline with the specified solver settings.	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): 7a822bd28a41e616dea9feb1826d5bc1594fe0ba7429a7de21c602fe9f84ff10

​Inputs

​Outputs

Inputs

Outputs