TopazImageEnhance - ComfyUI Built-in Node Documentation - ComfyUI

The Topaz Image Enhance node provides industry-standard upscaling and image enhancement. It processes a single input image using a cloud-based AI model to improve quality, detail, and resolution. The node offers fine-grained control over the enhancement process, including options for creative guidance, subject focus, and facial preservation.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The AI model to use for image enhancement.	COMBO	Yes	`"Reimagine"`
`image`	The input image to be enhanced. Only one image is supported.	IMAGE	Yes	-
`prompt`	Optional text prompt for creative upscaling guidance (default: empty).	STRING	No	-
`subject_detection`	Controls which part of the image the enhancement focuses on (default: “All”).	COMBO	No	`"All"` `"Foreground"` `"Background"`
`face_enhancement`	Enhance faces (if present) during processing (default: True).	BOOLEAN	No	-
`face_enhancement_creativity`	Set the creativity level for face enhancement (default: 0.0).	FLOAT	No	0.0 - 1.0
`face_enhancement_strength`	Controls how sharp enhanced faces are relative to the background (default: 1.0).	FLOAT	No	0.0 - 1.0
`crop_to_fill`	By default, the image is letterboxed when the output aspect ratio differs. Enable to crop the image to fill the output dimensions (default: False).	BOOLEAN	No	-
`output_width`	Zero value means to calculate automatically (usually it will be original size or output_height if specified) (default: 0).	INT	No	0 - 32000
`output_height`	Zero value means to output in the same height as original or output width (default: 0).	INT	No	0 - 32000
`creativity`	Controls the overall creativity level of the enhancement (default: 3).	INT	No	1 - 9
`face_preservation`	Preserve subjects’ facial identity (default: True).	BOOLEAN	No	-
`color_preservation`	Preserve the original colors (default: True).	BOOLEAN	No	-

Note: This node can only process a single input image. Providing a batch of multiple images will result in an error.

Outputs

Output Name	Description	Data Type
`image`	The enhanced output image.	IMAGE

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): 1a0e708cdea9ec4f92f7f3aaabbdeea06a8fdab2f91a45ad2dea15f2bc2e8fa3