RecraftImageToImageNode - ComfyUI Built-in Node Documentation

This node modifies an existing image based on a text prompt and a strength parameter. It uses the Recraft V3 API to transform the input image according to the provided description while keeping some similarity to the original image, controlled by the strength setting.

Inputs

Parameter	Description	Data Type	Required	Range
`image`	The input image to be modified	IMAGE	Yes	-
`prompt`	Prompt for the image generation (default: empty string, max length: 1000 characters)	STRING	Yes	-
`n`	The number of images to generate (default: 1)	INT	Yes	1-6
`strength`	Defines the difference with the original image, should lie in [0, 1], where 0 means almost identical, and 1 means miserable similarity (default: 0.5)	FLOAT	Yes	0.0-1.0
`seed`	Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0)	INT	Yes	0-18446744073709551615
`recraft_style`	Optional style selection for the image generation. If not provided, defaults to `realistic_image`	STYLEV3	No	-
`negative_prompt`	An optional text description of undesired elements on an image (default: empty string)	STRING	No	-
`recraft_controls`	Optional additional controls over the generation via the Recraft Controls node	CONTROLS	No	-

Note: The seed parameter only triggers re-execution of the node but does not guarantee deterministic results. The strength parameter is rounded to 2 decimal places internally. The prompt is validated and must not exceed 1000 characters. An empty negative_prompt is treated as no negative prompt. If recraft_style is not provided, the node defaults to the realistic_image style. If you use a style_id from the Infinite Style Library, ensure it is not a Vector art style, as this may cause the node to receive SVG data instead of an image, resulting in an error. When the input image is a batch, each image in the batch is processed individually and all results are returned together.

Outputs

Output Name	Description	Data Type
`image`	The generated image(s) based on the input image and prompt	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): 1932e55d1dc392e6bd42a0bd29f5aaba44b65997b597648a927fba38a27c90ad

​Inputs

​Outputs

Inputs

Outputs