SamplerSEEDS2 - ComfyUI Built-in Node Documentation - ComfyUI

This node provides a configurable sampler for image generation. It implements the SEEDS-2 algorithm, which is a stochastic differential equation (SDE) solver. By adjusting its parameters, you can configure it to behave like several specific samplers, including seeds_2, exp_heun_2_x0, and exp_heun_2_x0_sde.

Inputs

Parameter	Description	Data Type	Required	Range
`solver_type`	Selects the underlying solver algorithm for the sampler.	COMBO	Yes	”phi_1" "phi_2”
`eta`	Stochastic strength (default: 1.0).	FLOAT	No	0.0 - 100.0
`s_noise`	SDE noise multiplier (default: 1.0).	FLOAT	No	0.0 - 100.0
`r`	Relative step size for the intermediate stage (c2 node) (default: 0.5).	FLOAT	No	0.01 - 1.0

Note: The node description defines the following sampler presets:

seeds_2: default settings
exp_heun_2_x0: solver_type = “phi_2”, r = 1.0, eta = 0.0
exp_heun_2_x0_sde: solver_type = “phi_2”, r = 1.0, eta = 1.0, s_noise = 1.0

Outputs

Output Name	Description	Data Type
`sampler`	A configured sampler object that can be passed to other sampling nodes.	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): f48744a706a49ef93d41845bf8c308af971853f6150afd00ded45f0317ffc4f9