LatentOperationSharpen - ComfyUI Built-in Node Documentation - ComfyUI

The LatentOperationSharpen node creates a sharpening operation for latent representations using a Gaussian kernel. It normalizes the latent data, applies a custom sharpening kernel through convolution, and then restores the original luminance. This enhances the details and edges in the latent space representation.

Inputs

Parameter	Description	Data Type	Required	Range
`sharpen_radius`	The radius of the sharpening kernel, which controls the size of the area used for sharpening (default: 9)	INT	Yes	1-31
`sigma`	The standard deviation of the Gaussian kernel used to build the sharpening kernel (default: 1.0)	FLOAT	Yes	0.1-10.0
`alpha`	The sharpening intensity factor; higher values produce a stronger sharpening effect (default: 0.1)	FLOAT	Yes	0.0-5.0

All three inputs are advanced parameters and have default values, so the node can be used without changing them. This node is marked as experimental.

Outputs

Output Name	Description	Data Type
`operation`	Returns a sharpening operation that can be applied to latent data	LATENT_OPERATION

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): 8f49b7e47d35547a7169e9ec209328adbe084ee861ac26b9f26e4e644ac14d6d