SamplerDPMPP_2M_SDE - ComfyUI Built-in Node Documentation - ComfyUI

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

Parameter	Description	Data Type	Required	Range
`solver_type`	The type of differential equation solver to use for the sampling process (default: “midpoint”)	COMBO	Yes	`"midpoint"` `"heun"`
`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
`noise_device`	The device where noise calculations are performed. When set to “cpu”, the sampler uses CPU-based noise generation; when set to “gpu”, it uses GPU-based noise generation for potentially faster performance (default: “gpu”)	COMBO	Yes	`"gpu"` `"cpu"`

Note: eta, s_noise, and noise_device are marked as advanced parameters and appear in the advanced section of the node’s UI.

Outputs

Output Name	Description	Data Type
`sampler`	A configured sampler object ready for use in the sampling pipeline	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): 42f5f098fa7573ca8a1a6085b72675ee6cb0ae8e7865c5793a815a6ef2495f82