Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.together.ai/llms.txt

Use this file to discover all available pages before exploring further.

Some image models support editing or transforming an existing image. The parameter you use depends on the model:
ParameterTypeModelsDescription
image_urlstringFLUX.1 Kontext (pro/max), FLUX.2 (pro/flex)A single image URL to edit or transform
reference_imagesstring[]FLUX.2 (pro/dev/flex), Gemini 3 Pro Image, Flash Image 2.5An array of image URLs to guide generation
reference_images is recommended for FLUX.2 and Google models because it supports multiple input images. FLUX.2 [pro] and [flex] also accept image_url for single-image edits, but FLUX.2 [dev], Gemini 3 Pro Image, and Flash Image 2.5 only support reference_images.

​
Use image_url (Kontext models)

from together import Together

client = Together()

response = client.images.generate(
    model="black-forest-labs/FLUX.1-kontext-pro",
    width=1024,
    height=768,
    prompt="Transform this into a watercolor painting",
    image_url="https://cdn.pixabay.com/photo/2020/05/20/08/27/cat-5195431_1280.jpg",
)
Example output: Reference image: reference_image.png

​
Use reference_images (FLUX.2 and Google models)

from together import Together

client = Together()

response = client.images.generate(
    model="black-forest-labs/FLUX.2-pro",
    width=1024,
    height=768,
    prompt="Replace the color of the car to blue",
    reference_images=[
        "https://images.pexels.com/photos/3729464/pexels-photo-3729464.jpeg"
    ],
)
For more details on multi-image editing, image indexing, and color control with FLUX.2, see the FLUX.2 Quickstart.