MagnificImageStyleTransferNode - ComfyUI Built-in Node Documentation

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

This node applies the visual style from a reference image to your input image. It uses an external AI service to process the images, allowing you to control the strength of the style transfer and the preservation of the original image’s structure.

Inputs

Parameter	Data Type	Required	Range	Description
`image`	IMAGE	Yes	-	The image to apply style transfer to.
`reference_image`	IMAGE	Yes	-	The reference image to extract style from.
`prompt`	STRING	No	-	An optional text prompt to guide the style transfer.
`style_strength`	INT	No	0 to 100	Percentage of style strength (default: 100).
`structure_strength`	INT	No	0 to 100	Maintains the structure of the original image (default: 50).
`flavor`	COMBO	No	”faithful" "gen_z" "psychedelia" "detaily" "clear" "donotstyle" "donotstyle_sharp”	Style transfer flavor.
`engine`	COMBO	No	”balanced" "definio" "illusio" "3d_cartoon" "colorful_anime" "caricature" "real" "super_real" "softy”	Processing engine selection.
`portrait_mode`	COMBO	No	”disabled" "enabled”	Enable portrait mode for facial enhancements.
`portrait_style`	COMBO	No	”standard" "pop" "super_pop”	Visual style applied to portrait images. This input is only available when `portrait_mode` is set to “enabled”.
`portrait_beautifier`	COMBO	No	”none" "beautify_face" "beautify_face_max”	Facial beautification intensity on portraits. This input is only available when `portrait_mode` is set to “enabled”.
`fixed_generation`	BOOLEAN	No	-	When disabled, expect each generation to introduce a degree of randomness, leading to more diverse outcomes (default: True).

Constraints:

Exactly one image and one reference_image are required.
Both images must have an aspect ratio between 1:3 and 3:1.
Both images must have a minimum height and width of 160 pixels.
The portrait_style and portrait_beautifier parameters are only active and required when portrait_mode is set to “enabled”.

Outputs

Output Name	Data Type	Description
`image`	IMAGE	The resulting image after style transfer has been applied.

​Inputs

​Outputs

Inputs

Outputs