ModelSamplingContinuousV - ComfyUI Built-in Node Documentation - ComfyUI

The ModelSamplingContinuousV node adjusts a model’s sampling behavior by applying continuous V-prediction sampling. It creates a clone of the input model and configures it with custom minimum and maximum sigma values for finer control over the sampling process.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The input model to be modified with continuous V-prediction sampling	MODEL	Yes	-
`sampling`	The sampling method to apply; currently V-prediction is the only available option (default: `"v_prediction"`)	COMBO	Yes	`"v_prediction"`
`sigma_max`	The maximum sigma value for sampling (advanced parameter, default: 500.0)	FLOAT	Yes	0.0 - 1000.0
`sigma_min`	The minimum sigma value for sampling (advanced parameter, default: 0.03)	FLOAT	Yes	0.0 - 1000.0

Outputs

Output Name	Description	Data Type
`model`	The modified model with continuous V-prediction sampling applied	MODEL

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): 8549be9dd2375374c20da7c74a756a90285716db0e52fed8a1a2b753cd6d75fe