fal-ai/flux-pro/kontext

FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

Open in Sandbox

Input

Prompt*

Type # to reference inputs.

Image URL*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif

Additional Settings

Customize your input with more control.

Result

Idle

foZaaLzgc--Vlcy3XwrNQ_c51f2cc166534c5997dcc0b072e41e09.jpg

What would you like to do next?

Download

{
  "seed": 123456,
  "images": [
    {
      "url": "https://fal.media/files/elephant/foZaaLzgc--Vlcy3XwrNQ_c51f2cc166534c5997dcc0b072e41e09.jpg",
      "width": 1248,
      "height": 832,
      "content_type": "image/jpeg"
    }
  ],
  "prompt": "Change the car color to red",
  "timings": {},
  "has_nsfw_concepts": [
    false
  ]
}

Your request will cost $0.04 per image.

Readme

FLUX.1 Kontext [pro] - Advanced Image-to-Image Generation and Editing

Transform your images with intelligent editing using FLUX.1 Kontext [pro], a powerful 12-billion parameter multimodal flow transformer designed for in-context image generation and editing. Seamlessly modify existing images with simple text instructions while preserving character consistency and visual quality.

Overview

FLUX.1 Kontext [pro] delivers exceptional image editing and generation capabilities through its multimodal architecture. Built to understand both text and visual context, it excels at intelligent image modifications, character preservation, and complex scene transformations without requiring fine-tuning or complex workflows.

Key Capabilities

In-context image editing with simple text instructions
Character consistency preservation across multiple edits
Local and global editing capabilities in one unified model
Text-to-image generation with state-of-the-art prompt following
Typography handling for text editing within images
Commercial-ready output quality with fast inference

Popular Use Cases

Creative Image Editing Modify existing images with natural language instructions. Change styles, swap objects, adjust lighting, or transform scenes while maintaining visual coherence.

Character Consistency Preserve unique characters, objects, or styles across different scenes and environments without any fine-tuning required.

Typography and Text Editing Seamlessly edit text within images - change signs, labels, posters, or any text elements with precision.

Style Transfer and Remixing Transform images from one artistic style to another - oil painting to pencil sketch, modern poster to surreal collage.

Getting Started

Getting up and running with FLUX.1 Kontext [pro] takes just a few minutes. Here's how to begin:

Get your API key at https://fal.ai/login
Install the client library for your preferred language
Make your first API call

For JavaScript/TypeScript:

javascript
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

const result = await fal.subscribe("fal-ai/flux-pro/kontext", {
  input: {
    prompt: "Change the red car to blue while keeping everything else the same",
    image_url: "https://your-image-url.com/image.jpg"
  }
});

For Python:

python
from fal_client import FalClient

client = FalClient("YOUR_FAL_KEY")
result = client.subscribe("fal-ai/flux-pro/kontext", {
    "prompt": "Change the red car to blue while keeping everything else the same",
    "image_url": "https://your-image-url.com/image.jpg"
})

Technical Specifications

Model Architecture

12 billion parameter multimodal flow transformer
In-context image generation and editing capabilities
Handles both text and reference images as inputs
Supports targeted local edits and complex scene transformations

Input Capabilities

Image input: jpg, jpeg, png, webp, gif, avif formats
Text prompts: Natural language editing instructions
Multimodal processing: Simultaneous text and image understanding

Performance

Fast inference optimized for iterative editing
Up to 8x faster than competing state-of-the-art models
Minimal latency for real-time creative workflows
99.9% uptime guarantee

Best Practices

Achieve optimal results with these proven approaches:

Write Clear Edit Instructions

Be specific about what you want to change and what should remain the same. Instead of "make it better," try "change the background to a sunset while keeping the person's pose and clothing identical."

Leverage Character Consistency

Use Kontext's strength in preserving characters across edits. You can modify lighting, backgrounds, or scenes while maintaining the same person, object, or style.

Handle Text Editing Precisely

When editing text in images, specify exactly what text to change and what it should become: "Change 'SALE' to 'SOLD OUT' on the storefront sign."

Build upon previous edits through multiple turns while maintaining visual consistency and character identity.

Advanced Features

Local and Global Editing

Targeted edits: Modify specific regions or objects
Scene transformations: Change entire backgrounds or contexts
Style preservation: Maintain artistic consistency during modifications

Multi-turn Editing

Refine images through successive edits while preserving quality and character consistency across multiple editing sessions.

Context Understanding

The model reads both image context and text instructions to ensure edits make logical and visual sense.

API Reference

The FLUX.1 Kontext [pro] API accepts the following core parameters:

typescript
interface FluxKontextParameters {
  prompt: string;              // Your editing instruction
  image_url: string;          // Input image to edit
  guidance_scale?: number;     // Prompt adherence strength
  num_inference_steps?: number; // Generation steps
  seed?: number;              // For reproducible results
}

Pricing and Usage

Your request will cost $0.04 per image. Our transparent, per-image pricing makes it cost-effective for both experimentation and production use:

Fixed $0.04 cost per image edit
No hidden fees or minimum commitments
Commercial usage rights included
Volume discounts available for enterprise users

View detailed pricing or contact sales for enterprise solutions.

Support and Resources

We're here to help you succeed with FLUX.1 Kontext [pro]:

Documentation: Complete API reference at https://docs.fal.ai/
Community: Join our Discord for support and creative showcases
Examples: Browse our GitHub repository for sample implementations
Support: Enterprise support available for production deployments

Ready to transform your images with intelligent editing? Sign up now at https://fal.ai and start creating with FLUX.1 Kontext [pro].

Get Started with FLUX Kontext Pro

Readme

FLUX.1 Kontext [pro] - Advanced Image-to-Image Generation and Editing

Overview

Key Capabilities

In-context image editing with simple text instructions
Character consistency preservation across multiple edits
Local and global editing capabilities in one unified model
Text-to-image generation with state-of-the-art prompt following
Typography handling for text editing within images
Commercial-ready output quality with fast inference

Popular Use Cases

Creative Image Editing Modify existing images with natural language instructions. Change styles, swap objects, adjust lighting, or transform scenes while maintaining visual coherence.

Character Consistency Preserve unique characters, objects, or styles across different scenes and environments without any fine-tuning required.

Typography and Text Editing Seamlessly edit text within images - change signs, labels, posters, or any text elements with precision.

Style Transfer and Remixing Transform images from one artistic style to another - oil painting to pencil sketch, modern poster to surreal collage.

Getting Started

Getting up and running with FLUX.1 Kontext [pro] takes just a few minutes. Here's how to begin:

Get your API key at https://fal.ai/login
Install the client library for your preferred language
Make your first API call

For JavaScript/TypeScript:

javascript
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

const result = await fal.subscribe("fal-ai/flux-pro/kontext", {
  input: {
    prompt: "Change the red car to blue while keeping everything else the same",
    image_url: "https://your-image-url.com/image.jpg"
  }
});

For Python:

python
from fal_client import FalClient

client = FalClient("YOUR_FAL_KEY")
result = client.subscribe("fal-ai/flux-pro/kontext", {
    "prompt": "Change the red car to blue while keeping everything else the same",
    "image_url": "https://your-image-url.com/image.jpg"
})

Technical Specifications

Model Architecture

12 billion parameter multimodal flow transformer
In-context image generation and editing capabilities
Handles both text and reference images as inputs
Supports targeted local edits and complex scene transformations

Input Capabilities

Image input: jpg, jpeg, png, webp, gif, avif formats
Text prompts: Natural language editing instructions
Multimodal processing: Simultaneous text and image understanding

Performance

Fast inference optimized for iterative editing
Up to 8x faster than competing state-of-the-art models
Minimal latency for real-time creative workflows
99.9% uptime guarantee

Best Practices

Achieve optimal results with these proven approaches:

Write Clear Edit Instructions

Be specific about what you want to change and what should remain the same. Instead of "make it better," try "change the background to a sunset while keeping the person's pose and clothing identical."

Leverage Character Consistency

Use Kontext's strength in preserving characters across edits. You can modify lighting, backgrounds, or scenes while maintaining the same person, object, or style.

Handle Text Editing Precisely

When editing text in images, specify exactly what text to change and what it should become: "Change 'SALE' to 'SOLD OUT' on the storefront sign."

Build upon previous edits through multiple turns while maintaining visual consistency and character identity.

Advanced Features

Local and Global Editing

Targeted edits: Modify specific regions or objects
Scene transformations: Change entire backgrounds or contexts
Style preservation: Maintain artistic consistency during modifications

Multi-turn Editing

Refine images through successive edits while preserving quality and character consistency across multiple editing sessions.

Context Understanding

The model reads both image context and text instructions to ensure edits make logical and visual sense.

API Reference

The FLUX.1 Kontext [pro] API accepts the following core parameters:

typescript
interface FluxKontextParameters {
  prompt: string;              // Your editing instruction
  image_url: string;          // Input image to edit
  guidance_scale?: number;     // Prompt adherence strength
  num_inference_steps?: number; // Generation steps
  seed?: number;              // For reproducible results
}

Pricing and Usage

Your request will cost $0.04 per image. Our transparent, per-image pricing makes it cost-effective for both experimentation and production use:

Fixed $0.04 cost per image edit
No hidden fees or minimum commitments
Commercial usage rights included
Volume discounts available for enterprise users

View detailed pricing or contact sales for enterprise solutions.

Support and Resources

We're here to help you succeed with FLUX.1 Kontext [pro]:

Documentation: Complete API reference at https://docs.fal.ai/
Community: Join our Discord for support and creative showcases
Examples: Browse our GitHub repository for sample implementations
Support: Enterprise support available for production deployments

Ready to transform your images with intelligent editing? Sign up now at https://fal.ai and start creating with FLUX.1 Kontext [pro].

Get Started with FLUX Kontext Pro

fal-ai/flux-pro/kontext

Input

Result

What would you like to do next?

Readme

FLUX.1 Kontext [pro] - Advanced Image-to-Image Generation and Editing

Overview

Key Capabilities

Popular Use Cases

Getting Started

Technical Specifications

Model Architecture

Input Capabilities

Performance

Best Practices

Write Clear Edit Instructions

Leverage Character Consistency

Handle Text Editing Precisely

Iterative Refinement

Advanced Features

Local and Global Editing

Multi-turn Editing

Context Understanding

API Reference

Pricing and Usage

Support and Resources

Readme

FLUX.1 Kontext [pro] - Advanced Image-to-Image Generation and Editing

Overview

Key Capabilities

Popular Use Cases

Getting Started

Technical Specifications

Model Architecture

Input Capabilities

Performance

Best Practices

Write Clear Edit Instructions

Leverage Character Consistency

Handle Text Editing Precisely

Iterative Refinement

Advanced Features

Local and Global Editing

Multi-turn Editing

Context Understanding

API Reference

Pricing and Usage

Support and Resources