Skip to main content
Endpoint: POST https://fal.run/fal-ai/flux-pro/kontext/text-to-image Endpoint ID: fal-ai/flux-pro/kontext/text-to-image

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

Examples

A close-up artistic photograph of fresh blueberries on a white surface. The surface has a marbled, fluid texture with swirls of white and various shades of blue, creating an abstract, paint-like effect. The blueberries are scattered across the image, some sitting on the white areas and others nestle…
Generated image: A close-up artistic photograph of fresh blueberries on a white surface. The surf
A visually stunning image of the Turritopsis dohrnii jellyfish floating gracefully in clear water. Include a close-up of its unique, translucent body, showcasing the regeneration process. The background should have a serene underwater environment with soft lighting.
Generated image: A visually stunning image of the Turritopsis dohrnii jellyfish floating graceful
In the foreground is a pizza, in the background the word “Fal Pizzeria” is written in neon by a wood-fired pizza oven, next to the pizza pepper and mushrooms are artistically used to show freshness and freshness, a colorful and attractive color palette is used , dynamic image, food photography
Generated image: In the foreground is a pizza, in the background the word 'Fal Pizzeria' is writt

Capabilities

  • Text prompt input
  • Reproducible generation (seed)
  • CFG guidance scale
  • Synchronous mode
  • Batch generation
  • Aspect ratio control

API Reference

Input Schema

string
required
The prompt to generate an image from.
integer
The same seed and the same prompt given to the same version of the model will output the same image every time.
float
default:"3.5"
The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Default value: 3.5Range: 1 to 20
boolean
default:"false"
If True, the media will be returned as a data URI and the output data won’t be available in the request history.
integer
default:"1"
The number of images to generate. Default value: 1Range: 1 to 4
OutputFormatEnum
default:"jpeg"
The format of the generated image. Default value: "jpeg"Possible values: jpeg, png
SafetyToleranceEnum
default:"2"
The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. Default value: "2"Possible values: 1, 2, 3, 4, 5, 6
boolean
default:"false"
Whether to enhance the prompt for better results.
AspectRatioEnum
default:"1:1"
The aspect ratio of the generated image. Default value: "1:1"Possible values: 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21

Output Schema

list<registry__image__fast_sdxl__models__Image>
required
The generated image files info.
Timings
required
integer
required
Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.
list<boolean>
required
Whether the generated images contain NSFW concepts.
string
required
The prompt used for generating the image.

Input Example

Output Example

Limitations

  • guidance_scale range: 1 to 20
  • num_images range: 1 to 4
  • output_format restricted to: jpeg, png
  • safety_tolerance restricted to: 1, 2, 3, 4, 5, 6