FluxKontextMaxImageNode - ComfyUI Built-in Node Documentation - ComfyUI

Generates or edits an image with Flux.1 Kontext [max] through the BFL API, based on a prompt and an aspect ratio. With input_image connected the prompt describes the edit; without it the node generates a fresh image from the prompt alone. It exposes the same inputs as Flux.1 Kontext [pro] Image.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Prompt for the image generation. With an input image, specify what and how to edit.	STRING	Yes	-
`aspect_ratio`	Aspect ratio of the image; must be between 1:4 and 4:1 (default: `"16:9"`).	STRING	Yes	-
`guidance`	Guidance strength for the image generation process (default: 3.0).	FLOAT	Yes	0.1 to 99.0 (step 0.1)
`steps`	Number of steps for the image generation process (default: 50).	INT	Yes	1 to 150
`seed`	The random seed used for creating the noise (default: 1234).	INT	Yes	0 to 18446744073709551615
`prompt_upsampling`	Whether to perform upsampling on the prompt. If active, the prompt is modified automatically for more creative generation, but results are nondeterministic, so the same seed will not produce exactly the same result (default: `False`). This is an advanced setting.	BOOLEAN	Yes	True / False
`input_image`	Optional image to edit. When omitted, the prompt is validated to ensure it is not empty.	IMAGE	No	-

Note: The node sends the request to BFL and polls until the image is ready. Requests rejected by BFL’s content moderation fail instead of returning an image.

Outputs

Output Name	Description	Data Type
`IMAGE`	The generated or edited 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): 557f9e69de37ee89e161dffdaef7458ed026b884298594f2046454b6b8d3c415