flux-kontext-apps/multi-image-kontext-max

An experimental FLUX Kontext model that can combine two input images

Capabilities

Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`input_image_1` *	string (uri)	First input image. Must be jpeg, png, gif, or webp.	`—`	—
`input_image_2` *	string (uri)	Second input image. Must be jpeg, png, gif, or webp.	`—`	—
`prompt` *	string	Text description of how to combine or transform the two input images	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.	`"match_input_image"`	match_input_image 1:1 16:9 9:16 4:3 3:4 3:2 2:3 4:5 5:4 21:9 9:21 2:1 1:2
`output_format`	string	Output format for the generated image	`"png"`	jpg png
`safety_tolerance`	integer	Safety tolerance, 0 is most strict and 2 is most permissive. 2 is currently the maximum allowed.	`2`	min: 0, max: 2
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

input_image_1 required string

First input image. Must be jpeg, png, gif, or webp.

input_image_2 required string

Second input image. Must be jpeg, png, gif, or webp.

prompt required string

Text description of how to combine or transform the two input images

aspect_ratio string

Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.

Default: "match_input_image"

match_input_image 1:1 16:9 9:16 4:3 3:4 3:2 2:3 4:5 5:4 21:9 9:21 2:1 1:2

output_format string

Output format for the generated image

Default: "png"

jpg png

safety_tolerance integer

Safety tolerance, 0 is most strict and 2 is most permissive. 2 is currently the maximum allowed.

Default: 2 min: 0, max: 2

seed integer

Random seed. Set for reproducible generation

Version: aa37e77197b9 Updated: 2/26/2026 222.6K runs