RecraftImageInpaintingNode - ComfyUI Built-in Node Documentation

This node modifies specific areas of an image based on a text prompt and a mask. It uses the Recraft API to intelligently edit only the masked regions while keeping the rest of the image unchanged.

Inputs

Parameter	Description	Data Type	Required	Range
`image`	The input image to be modified	IMAGE	Yes	-
`mask`	The mask defining which areas of the image should be modified	MASK	Yes	-
`prompt`	Prompt for the image generation (default: empty string, maximum length: 1000 characters)	STRING	Yes	-
`n`	The number of images to generate (default: 1, minimum: 1, maximum: 6)	INT	Yes	1-6
`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 parameter for the Recraft API. If not provided, defaults to “realistic_image” style	STYLEV3	No	-
`negative_prompt`	An optional text description of undesired elements on an image (default: empty string)	STRING	No	-

Note: The image and mask must be provided together for the inpainting operation to work. The mask will be automatically resized to match the image dimensions. The prompt is validated and has a maximum length of 1000 characters. If a style_id from the Infinite Style Library is used, ensure it is not a Vector art style, as this may cause the API to return SVG data instead of an image.

Outputs

Output Name	Description	Data Type
`image`	The modified image(s) generated based on the prompt and mask. Returns one image per input image multiplied by the `n` parameter	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): 64493a418224f4a01c6b6511581d31f92189852a32b41d9748629e57782bd511

​Inputs

​Outputs

Inputs

Outputs