Official

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

An experimental FLUX Kontext model that can combine two input images

  • Public
  • 69.2K runs
  • Commercial use
Iterate in playground
  • Prediction

    flux-kontext-apps/multi-image-kontext-max
    ID
    y9khwmsxxsrme0cq3hh8b1rpbc
    Status
    Succeeded
    Source
    Web
    Total duration
    Created
    by @flux-kontext-apps

    Input

    prompt
    Put Elsa and Mona Lisa dancing together at a deep house rave
    aspect_ratio
    3:2
    input_image_1
    input_image_1
    input_image_2
    input_image_2

    Output

    output
    Generated in
  • Prediction

    flux-kontext-apps/multi-image-kontext-max
    ID
    ke0dxqbyhsrmc0cq3hns9fxzrm
    Status
    Succeeded
    Source
    Web
    Total duration
    Created

    Input

    prompt
    Put the woman and the na'vi together at a garden party, the friends pose in the evening light
    aspect_ratio
    3:4
    input_image_1
    input_image_1
    input_image_2
    input_image_2

    Output

    output
    Generated in
  • Prediction

    flux-kontext-apps/multi-image-kontext-max
    ID
    0sn3zm2ya5rma0cq3hq9w9vk2w
    Status
    Succeeded
    Source
    Web
    Total duration
    Created
    by @flux-kontext-apps

    Input

    prompt
    A photo of the reimagined vase in the colorful aurora style
    aspect_ratio
    3:2
    input_image_1
    input_image_1
    input_image_2
    input_image_2

    Output

    output
    Generated in
  • Prediction

    flux-kontext-apps/multi-image-kontext-max
    ID
    t1t7eg9nssrm80cq3ht97f6xgm
    Status
    Succeeded
    Source
    Web
    Total duration
    Created
    by @flux-kontext-apps

    Input

    prompt
    Add the handwriting to the car scene, the text says "Look at this car!"
    aspect_ratio
    3:2
    input_image_1
    input_image_1
    input_image_2
    input_image_2

    Output

    output
    Generated in
  • Prediction

    flux-kontext-apps/multi-image-kontext-max
    ID
    n06kn3k221rmc0cq3j0rpat0rc
    Status
    Succeeded
    Source
    Web
    Total duration
    Created
    by @flux-kontext-apps

    Input

    prompt
    Put the woman into a white t-shirt with the text on it
    aspect_ratio
    1:1
    input_image_1
    input_image_1
    input_image_2
    input_image_2

    Output

    output
    Generated in

Want to make some of these yourself?

Run this model