MiniMaxH3SigmaShift - ComfyUI Built-in Node Documentation - ComfyUI

Sets the video and audio flow shift values for a MiniMax H3 model. The video shift controls the sampler’s sigma schedule, and both shift values are passed to the model’s internal transformer, which uses them to derive the audio schedule from the shared base grid.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The model to apply the sigma shift patch to. The node clones the model, so the original remains unchanged.	MODEL	Yes	-
`shift_video`	The video flow shift value. It drives the sampler’s sigma schedule. Default: 12.0.	FLOAT	Yes	0.01 to 100.0
`shift_audio`	The audio flow shift value. It is used by the model to derive the audio schedule. Default: 3.0.	FLOAT	Yes	0.01 to 100.0

Outputs

Output Name	Description	Data Type
`MODEL`	The cloned model with the video and audio sigma shift settings 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): 0f731585cc1a9c87a3e54341757c4cf4e490d1d4718ecf458bd2b9f4378af63f