Flux Dev API

Dev
Image To Image
Redux

Endpoint: POST https://fal.run/fal-ai/flux/dev Endpoint ID: fal-ai/flux/dev

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux/dev",
    arguments={
        "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word \"FLUX\" is painted over it in big, white brush strokes with visible texture."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

portrait | wide angle shot of eyes off to one side of frame, lucid dream-like woman, looking off in distance ::8 style | daydreampunk with glowing skin and eyes, styled in headdress, beautiful, she is dripping in neon lights, very colorful blue, green, purple, bioluminescent, glowing ::8 background …

Generated image: portrait | wide angle shot of eyes off to one side of frame, lucid dream-like wo

a girl walking through a field, in the style of ethereal trees, dark yellow and azure, majestic, sweeping seascapes, photorealistic representation, graceful balance, wimmelbilder, orange

Generated image: a girl walking through a field, in the style of ethereal trees, dark yellow and

Microscopic photograph of mites caught in a drop of water, green colored sparks raining from above across a gradient background, brightly shining sparks, emitting green light, shallow depth of field volumetric lighting, cinematic, intricate detail, ultra-realistic

Generated image: Microscopic photograph of mites caught in a drop of water, green colored sparks

Input Schema

prompt

string

required

The prompt to generate an image from.

image_size

ImageSize | Enum

default:"landscape_4_3"

The size of the generated image. Default value: landscape_4_3Possible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

num_inference_steps

integer

default:"28"

The number of inference steps to perform. Default value: 28Range: 1 to 50

seed

integer

The same seed and the same prompt given to the same version of the model will output the same image every time.

guidance_scale

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

sync_mode

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.

num_images

integer

default:"1"

The number of images to generate. Default value: 1Range: 1 to 4

enable_safety_checker

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

output_format

OutputFormatEnum

default:"jpeg"

The format of the generated image. Default value: "jpeg"Possible values: jpeg, png

acceleration

AccelerationEnum

default:"none"

The speed of the generation. The higher the speed, the faster the generation. Default value: "none"Possible values: none, regular, high

Output Schema

images

list<Image>

required

The generated image files info.

timings

Timings

required

seed

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.

has_nsfw_concepts

list<boolean>

required

Whether the generated images contain NSFW concepts.

prompt

string

required

The prompt used for generating the image.

Input Example

{
  "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word \"FLUX\" is painted over it in big, white brush strokes with visible texture.",
  "image_size": "landscape_4_3",
  "num_inference_steps": 28,
  "guidance_scale": 3.5,
  "sync_mode": false,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "acceleration": "none"
}

Output Example

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

Endpoint: POST https://fal.run/fal-ai/flux/dev/image-to-image Endpoint ID: fal-ai/flux/dev/image-to-image

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux/dev/image-to-image",
    arguments={
        "image_url": "https://fal.media/files/koala/Chls9L2ZnvuipUTEwlnJC.png",
        "prompt": "A cat dressed as a wizard with a background of a mystic forest."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

a cat dressed as a wizard with a background of a mystic forest.

Generated image: a cat dressed as a wizard with a background of a mystic forest.

woman, in cyberpunk city, purple, green, neon

Generated image: woman, in cyberpunk city, purple, green, neon

cartoon tiger, anime style

Generated image: cartoon tiger, anime style

Input Schema

image_url

string

required

The URL of the image to generate an image from.

strength

float

default:"0.95"

The strength of the initial image. Higher strength values are better for this model. Default value: 0.95Range: 0.01 to 1

num_inference_steps

integer

default:"40"

The number of inference steps to perform. Default value: 40Range: 10 to 50

prompt

string

required

The prompt to generate an image from.

seed

integer

The same seed and the same prompt given to the same version of the model will output the same image every time.

guidance_scale

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

sync_mode

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.

num_images

integer

default:"1"

The number of images to generate. Default value: 1Range: 1 to 4

enable_safety_checker

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

output_format

OutputFormatEnum

default:"jpeg"

The format of the generated image. Default value: "jpeg"Possible values: jpeg, png

acceleration

AccelerationEnum

default:"none"

The speed of the generation. The higher the speed, the faster the generation. Default value: "none"Possible values: none, regular, high

Output Schema

images

list<Image>

required

The generated image files info.

timings

Timings

required

seed

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.

has_nsfw_concepts

list<boolean>

required

Whether the generated images contain NSFW concepts.

prompt

string

required

The prompt used for generating the image.

Input Example

{
  "image_url": "https://fal.media/files/koala/Chls9L2ZnvuipUTEwlnJC.png",
  "strength": 0.95,
  "num_inference_steps": 40,
  "prompt": "A cat dressed as a wizard with a background of a mystic forest.",
  "guidance_scale": 3.5,
  "sync_mode": false,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "acceleration": "none"
}

Output Example

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

Endpoint: POST https://fal.run/fal-ai/flux/dev/redux Endpoint ID: fal-ai/flux/dev/redux

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux/dev/redux",
    arguments={
        "image_url": "https://fal.media/files/kangaroo/acQvq-Kmo2lajkgvcEHdv.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

image_url

string

required

The URL of the image to generate an image from.

image_size

ImageSize | Enum

default:"landscape_4_3"

The size of the generated image. Default value: landscape_4_3Possible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

num_inference_steps

integer

default:"28"

The number of inference steps to perform. Default value: 28Range: 1 to 50

seed

integer

The same seed and the same prompt given to the same version of the model will output the same image every time.

guidance_scale

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

sync_mode

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.

num_images

integer

default:"1"

The number of images to generate. Default value: 1Range: 1 to 4

enable_safety_checker

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

output_format

OutputFormatEnum

default:"jpeg"

The format of the generated image. Default value: "jpeg"Possible values: jpeg, png

acceleration

AccelerationEnum

default:"none"

The speed of the generation. The higher the speed, the faster the generation. Default value: "none"Possible values: none, regular, high

Output Schema

images

list<Image>

required

The generated image files info.

timings

Timings

required

seed

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.

has_nsfw_concepts

list<boolean>

required

Whether the generated images contain NSFW concepts.

prompt

string

required

The prompt used for generating the image.

Input Example

{
  "image_url": "https://fal.media/files/kangaroo/acQvq-Kmo2lajkgvcEHdv.png",
  "image_size": "landscape_4_3",
  "num_inference_steps": 28,
  "guidance_scale": 3.5,
  "sync_mode": false,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "acceleration": "none"
}

Output Example

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "prompt": ""
}

FLUX.1 [dev] - High-Performance Image Generation API

Transform your creative vision into stunning images with FLUX.1 [dev], a state-of-the-art text-to-image generation model powered by a 12 billion parameter flow transformer. Built for both speed and quality, FLUX.1 [dev] delivers professional-grade results suitable for personal and commercial use.

Key Benefits

Create production-ready images faster and with greater control. FLUX.1 [dev] enables you to:

Generate high-fidelity images from natural language descriptions
Achieve consistent results across multiple generations
Scale from prototype to production with enterprise-grade reliability
Access both personal and commercial licensing options
Deploy anywhere with flexible API integration
Use streaming capabilities for real-time generation

Popular Use Cases

Content Creation Generate marketing visuals, social media assets, and blog illustrations at scale. Perfect for agencies and content teams who need consistent, high-quality imagery. Product Development
Create concept art, UI mockups, and design variations for rapid prototyping. Ideal for designers exploring visual directions. E-commerce Generate product lifestyle images, seasonal campaigns, and A/B testing visuals to boost conversion rates. Entertainment Produce game assets, storyboard illustrations, and creative concept art for media projects.

Technical Overview

FLUX.1 [dev] is built on advanced flow transformer architecture that enables:

Performance: 12B parameters optimized for rapid inference
Flexibility: Support for multiple generation approaches including streaming
Quality: Enhanced image coherence and composition
Licensing: Suitable for both personal and commercial use

Getting Started

Getting up and running with FLUX.1 [dev] is straightforward. Here’s how to begin:

Get your API key at https://fal.ai/login
Install the client library:

# For JavaScript/TypeScript
npm install --save @fal-ai/client

# For Python
pip install fal-client

Make your first API call:

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

const result = await fal.subscribe("fal-ai/flux/dev", {
  input: {
    prompt: "A serene mountain landscape at sunset, photorealistic style"
  }
});

Streaming Support

FLUX.1 [dev] supports streaming requests for real-time generation:

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

const stream = await fal.stream("fal-ai/flux/dev", {
  input: {
    prompt: "Your detailed prompt here"
  }
});

for await (const event of stream) {
  console.log(event);
}

const result = await stream.done();

Best Practices

For optimal results when using FLUX.1 [dev]:

Keep prompts clear and specific while maintaining natural language
Start with default parameters and adjust based on results
Consider using negative prompts to refine unwanted elements
Monitor usage for cost-effective scaling
Take advantage of streaming for interactive applications

Advanced Features

Image Style Control

Fine-tune the artistic direction of your generations through comprehensive style parameters. Adjust attributes like composition, lighting, and artistic influence while maintaining consistent quality.

API Parameters

The model supports various configuration options:

CFG Scale: Control prompt adherence (default: 3.5)
Safety Checker: Enable content safety filtering
Output Format: Choose between PNG and other formats
Number of Images: Generate multiple variations
Speed Settings: Optimize for generation speed

Batch Processing

Generate multiple variations efficiently with built-in batching support. Perfect for creating asset collections or exploring creative variations.

Integration Support

Our comprehensive SDK support makes integration seamless across your technology stack:

REST API for platform-agnostic integration
Native SDKs for Python and JavaScript/TypeScript
Streaming capabilities for real-time applications
Detailed documentation and code examples
Enterprise support options available

Pricing and Usage

Your request will cost $0.025 per megapixel. Images are billed by rounding up to the nearest megapixel. Our transparent, usage-based pricing scales with your needs:

Cost-effective: $0.025 per megapixel
Commercial usage rights included
No subscription fees or minimum commitments
Transparent billing with clear pricing structure

View detailed pricing or contact sales for enterprise solutions.

Licensing

FLUX.1 [dev] is suitable for both personal and commercial use through fal.ai’s platform. The model provides flexible licensing options that support various use cases from individual projects to enterprise deployments.

Migration Guide

Moving from other platforms? Our migration tools and documentation help ensure a smooth transition to FLUX.1 [dev]. Contact our support team for personalized migration assistance and best practices.

Getting Help

We’re here to support your success with FLUX.1 [dev]:

Documentation: Comprehensive guides at https://docs.fal.ai
Support: Technical assistance via support@fal.ai
Community: Join our Discord for tips and discussions
Updates: Regular model improvements and feature additions

Ready to transform your creative vision into reality? Get started at https://fal.ai/models/fal-ai/flux/dev.

FLUX.1 [schnell] — Image Generation
FLUX.1 [dev] Redux — Image Generation

Limitations

image_size restricted to: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
num_inference_steps range: 1 to 50
guidance_scale range: 1 to 20
num_images range: 1 to 4
output_format restricted to: jpeg, png
acceleration restricted to: none, regular, high
Content moderation via safety checker
strength range: 0.01 to 1
num_inference_steps range: 10 to 50

Video Generation

Image Generation

Audio

Vision

3D

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​FLUX.1 [dev] - High-Performance Image Generation API

​Key Benefits

​Popular Use Cases

​Technical Overview

​Getting Started

​Streaming Support

​Best Practices

​Advanced Features

​Image Style Control

​API Parameters

​Batch Processing

​Integration Support

​Pricing and Usage

​Licensing

​Migration Guide

​Getting Help

​Related

​Limitations

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

FLUX.1 [dev] - High-Performance Image Generation API

Key Benefits

Popular Use Cases

Technical Overview

Getting Started

Streaming Support

Best Practices

Advanced Features

Image Style Control

API Parameters

Batch Processing

Integration Support

Pricing and Usage

Licensing

Migration Guide

Getting Help

Related

Limitations