Flux3ImageNode - ComfyUI Built-in Node Documentation

Flux 3 Image generates an image with FLUX 3 from a prompt, or edits and combines reference images. Write what you want as an instruction, then connect up to 10 reference images and refer to them in the prompt as image 1, image 2, and so on. The prompt is interpreted and expanded before generation, and the result is rendered at the aspect ratio and resolution you choose.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	What to generate, or the edit to make. The prompt is interpreted and expanded before generation. Refer to connected reference images as image 1, image 2, and so on. (default: "")	STRING	Yes	1 to 15000 characters
`images`	Growable slot for reference images; connect up to 10 in total. Each image must be at least 256x256 pixels, and its aspect ratio cannot be more extreme than 64:1.	IMAGE	No	0 to 10 images
`bounding_boxes`	Optional boxes from the Create Bounding Boxes node that place objects or text in the output. Positions are relative to the canvas, so give the node the output’s aspect ratio.	ARRAY	No	-
`aspect_ratio`	Aspect ratio of the generated image. “auto” follows the first reference image, or picks a ratio from the prompt. (default: “auto”)	COMBO	Yes	`"auto"` `"21:9"` `"2:1"` `"16:9"` `"3:2"` `"7:5"` `"4:3"` `"5:4"` `"1:1"` `"4:5"` `"3:4"` `"5:7"` `"2:3"` `"9:16"` `"1:2"` `"9:21"`
`resolution`	Output size at the chosen aspect ratio: 0.75K is about 0.6 megapixels, 1K 1 MP, 1.5K 2.4 MP, 2K 4.2 MP, 4K 16.8 MP. (default: “2K”)	COMBO	Yes	`"0.75K"` `"1K"` `"1.5K"` `"2K"` `"4K"`
`grounding`	Let the model research the prompt with web and image search before generating. (default: True)	BOOLEAN	Yes	True False
`safety_tolerance`	Moderation tolerance, 0 is the strictest. (default: 4)	INT	Yes	0 to 4
`seed`	Seed to determine if node should re-run; FLUX 3 picks its own seed, so actual results are nondeterministic regardless of this value. (default: 42)	INT	Yes	0 to 4294967295

safety_tolerance is an advanced input, and seed includes Control After Generate controls in the UI. Reference images are uploaded before the request is sent. A single slot can carry a batch, and every frame of every batch counts towards the limit of 10 images. bounding_boxes rows are appended to the prompt, so the prompt and the box descriptions must be 15000 characters or fewer together. The displayed price depends on resolution:

0.05863 at 0.75K,

0.06864 at 1K,

0.1001 at 1.5K,

0.143 at 2K and $0.86801 at 4K.

Outputs

Output Name	Description	Data Type
`IMAGE`	The generated image, downloaded from the FLUX 3 result.	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): f32a90887227f9ce9e6ed04a76cde452a70f36fb97d8c36d7c55140855c1f593

​Inputs

​Outputs

Inputs

Outputs