MagnificImageUpscalerPreciseV2Node - ComfyUI Built-in Node Documentation

The Magnific Image Upscale (Precise V2) node performs high-fidelity image upscaling with precise control over sharpness, grain, and detail enhancement. It processes images through an external API, supporting up to a maximum output resolution of 10060×10060 pixels. The node offers different processing styles and can automatically downscale the input if the requested output would exceed the maximum allowed size.

Inputs

Parameter	Description	Data Type	Required	Range
`image`	The input image to be upscaled. Exactly one image is required. Minimum dimensions are 160x160 pixels. The aspect ratio must be between 1:3 and 3:1.	IMAGE	Yes	-
`scale_factor`	The desired upscaling multiplier.	STRING	Yes	`"2x"` `"4x"` `"8x"` `"16x"`
`flavor`	The processing style. “sublime” is for general use, “photo” is optimized for photographs, and “photo_denoiser” is for noisy photos.	STRING	Yes	`"sublime"` `"photo"` `"photo_denoiser"`
`sharpen`	Controls the intensity of image sharpening to increase edge definition and clarity. Higher values produce a sharper result. Default: 7.	INT	No	0 to 100
`smart_grain`	Adds intelligent grain or texture enhancement to prevent the upscaled image from looking too smooth or artificial. Default: 7.	INT	No	0 to 100
`ultra_detail`	Controls the amount of fine detail, textures, and micro-details added during the upscaling process. Default: 30.	INT	No	0 to 100
`auto_downscale`	When enabled, the node will automatically downscale the input image if the calculated output dimensions would exceed the maximum allowed resolution of 10060x10060 pixels. This helps prevent errors but may affect quality. Default: False.	BOOLEAN	No	-

Note: If auto_downscale is disabled and the requested output size (input dimensions × scale_factor) exceeds 10060x10060 pixels, the node will raise an error.

Outputs

Output Name	Description	Data Type
`image`	The resulting upscaled 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): 83559e99f86398b894c659996bdde48633a49f857a4769127fdf7ab6e80d6b0d

​Inputs

​Outputs

Inputs

Outputs