FreSca - ComfyUI Built-in Node Documentation

The FreSca node applies frequency-dependent scaling to the guidance during the sampling process. It separates the guidance signal into low-frequency and high-frequency components using Fourier filtering, then applies different scaling factors to each frequency range before recombining them. This allows for more nuanced control over how guidance affects different aspects of the generated output.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The model to apply frequency scaling to	MODEL	Yes	-
`scale_low`	Scaling factor for low-frequency components (default: 1.0)	FLOAT	No	0 - 10
`scale_high`	Scaling factor for high-frequency components (default: 1.25)	FLOAT	No	0 - 10
`freq_cutoff`	Number of frequency indices around center to consider as low-frequency (default: 20)	INT	No	1 - 10000

Outputs

Output Name	Description	Data Type
`model`	The modified model with frequency-dependent scaling applied to its guidance function	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): 2ff3517619d856db68a9091ae7c87af8c56a23420fa2176b089bf9700475a7a9

​Inputs

​Outputs

Inputs

Outputs