Black Forest LabsMediumUltra

FLUX Kontext Max

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts.

190 credits

per image

Top-tier Kontext editing performance, above FLUX Kontext Pro

Improved typography and text rendering in edited images

Natural language instruction-based editing

Aspect ratio auto-match to the input image

Consistent character and style preservation across edits

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "black-forest-labs/flux-kontext-max",
  "input": {
    "prompt": "Make the letters 3D, floating in space on a city street",
    "input_image": "https://replicate.delivery/xezq/XfwWjHJ7HfrmXE6ukuLVEpXWfeQ3PQeRI5mApuLXRxST7XMmC/tmpc91tlq20.png",
    "aspect_ratio": "match_input_image"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Text description of what you want to generate, or the instruction on how to edit the given image
`input_image`	string	No	-	Image to use as reference. Must be jpeg, png, gif, or webp
`aspect_ratio`	string	No	match_input_image	Aspect ratio of the generated image. match_input_image matches the input image's ratio match_input_image1:116:99:164:33:43:22:34:55:421:99:212:11:2
`output_format`	string	No	png	Output format for the generated image jpgpng
`safety_tolerance`	integer	No	2	Safety tolerance, 0 is most strict and 6 is most permissive. Max 2 when input images are used
`prompt_upsampling`	boolean	No	false	Automatic prompt improvement
`seed`	integer	No	-	Random seed. Set for reproducible generation

How to Provide File Input

There are 3 ways to provide files for the input_image parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=black-forest-labs/flux-kontext-max" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:input_image=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "black-forest-labs/flux-kontext-max",
  "input": {
    "prompt": "your prompt here",
    "input_image": "https://example.com/image.jpg"
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

3D Typography Edit

Transform 2D text in a photo into a floating 3D effect

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "black-forest-labs/flux-kontext-max",
  "input": {
    "prompt": "Make the letters 3D, floating in space on a city street",
    "input_image": "https://replicate.delivery/xezq/XfwWjHJ7HfrmXE6ukuLVEpXWfeQ3PQeRI5mApuLXRxST7XMmC/tmpc91tlq20.png",
    "aspect_ratio": "match_input_image"
  }
}'