Flux Image Generation
API that can handle
your scale

Flux is a state-of-the-art image model by Black Forest Labs.
At fal you will find the fastest and most reliable Flux APIs for high-fidelity, accurate image generation.

Why choose fal as your Flux API Provider?#

  1. Fast

    fal provides the fastest and most reliable Flux APIs for high-fidelity, accurate image generation.

  2. Cheap

    Being fast and reliable doesn't mean expensive. fal provides the affordable API for you to use with no hidden costs.

  3. Reliable

    fal ensures your images will be generated, no matter the load.

  4. Scalable

    fal provides scalable APIs that allow you to generate thousands of images per second.

  5. Easy to use

    fal provides easy-to-use APIs that allow you to generate images with just a few lines of code, with first-class support for Python, JavaScript, Swift and more.

Fast. Cheap. Reliable.
Choose 3.

Flux models#

Flux is offered in a variety of different endpoints, each with its own unique capabilities and use cases.

FLUX1.1 [pro] ultraFLUX1.1 [pro] ultra is the newest version of FLUX1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.
text-to-image
high-res
realism
Train Flux LoRATrain styles, people and other subjects at blazing speeds.
training
lora
personalization
Train Flux LoRAs For PortraitsFLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.
training
lora
personalization
FLUX.1 [dev]FLUX.1 Image-to-Image is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
style transfer
FLUX.1 [dev]FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.
text-to-image
FLUX.1 [dev] with LoRAsSuper fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
text-to-image
lora
personalization
FLUX.1 [dev] Inpainting with LoRAsSuper fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
text-to-image
lora
personalization
FLUX.1 [schnell]FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use.
text-to-image
FLUX.1 SubjectSuper fast endpoint for the FLUX.1 [schnell] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.
text-to-image
personalization
customization
FLUX.1 [schnell] ReduxFLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
style transfer
FLUX.1 [dev] ReduxFLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
style transfer
lora
FLUX.1 [pro] ReduxFLUX.1 [pro] Redux is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
style transfer
FLUX1.1 [pro] ReduxFLUX1.1 [pro] Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
style transfer
FLUX1.1 [pro] ultra ReduxFLUX1.1 [pro] ultra Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
style transfer
high-res
FLUX.1 [pro] FillFLUX.1 [pro] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
editing
FLUX.1 [pro] CannyUtilize Flux.1 [pro] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.
image-to-image
controlnet
detection
editing
composition
FLUX.1 [pro] DepthGenerate high-quality images from depth maps using Flux.1 [pro] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.
image-to-image
depth
utility
composition
FLUX.1 [dev] Canny with LoRAsUtilize Flux.1 [dev] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.
image-to-image
controlnet
detection
lora
editing
composition
FLUX.1 [dev] Depth with LoRAsGenerate high-quality images from depth maps using Flux.1 [dev] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.
image-to-image
depth
lora
utility
composition
FLUX1.1 [pro]FLUX1.1 [pro] is an enhanced version of FLUX.1 [pro], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.
text-to-image
FLUX.1 [pro]FLUX.1 [pro] new is an accelerated version of FLUX.1 [pro], maintaining professional-grade image quality while delivering significantly faster generation speeds.
text-to-image
FLUX.1 [dev] Fill with LoRAsFLUX.1 [dev] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
image-to-image
editing
lora
FLUX.1 [dev] with LoRAsFLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.
image-to-image
lora
style transfer
FLUX.1 [dev] with Controlnets and LorasA versatile endpoint for the FLUX.1 [dev] model that supports multiple AI extensions including LoRA, ControlNet conditioning, and IP-Adapter integration, enabling comprehensive control over image generation through various guidance methods.
text-to-image
lora
controlnet
ip-adapter
FLUX.1 [dev] with Controlnets and LorasFLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.
image-to-image
lora
controlnet
ip-adapter
FLUX.1 [dev] with Controlnets and LorasFLUX General Image-to-Image is a versatile endpoint that transforms existing images with support for LoRA, ControlNet, and IP-Adapter extensions, enabling precise control over style transfer, modifications, and artistic variations through multiple guidance methods.
image-to-image
lora
controlnet
ip-adapter
FLUX.1 [dev] with Controlnets and LorasA specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.
image-to-image
lora
controlnet
ip-adapter
FLUX.1 [dev] with Controlnets and LorasA general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.
image-to-image
rf-inversion
editing
lora
PuLID FluxAn endpoint for personalized image generation using Flux as per given description.
image-to-image
personalization
style transfer
FLUX.1 [dev] Differential DiffusionFLUX.1 Differential Diffusion is a rapid endpoint that enables swift, granular control over image transformations through change maps, delivering fast and precise region-specific modifications while maintaining FLUX.1 [dev]'s high-quality output.
image-to-image
transformation

Articles about Flux#

Training FLUX Style LoRA on fal

Training FLUX Style LoRA on fal

FLUX has taken over the image generation space, but getting exactly the style you want can be difficult. This where style LoRAs can help. Training a style LoRA on Fal is easy, but there are some tips and tricks for getting the best results.

Oct 14, 2024
Announcing FLUX1.1 [pro] by BFL and FLUX [dev] speed improvements

Announcing FLUX1.1 [pro] by BFL and FLUX [dev] speed improvements

The FLUX1.1 [pro] model, codenamed "blueberry," was introduced in the Artificial Analysis image arena (https://artificialanalysis.ai/text-to-image/arena) last week. It currently boasts the highest overall Elo score among all image models, while at the same time being one of the fastest.

Oct 3, 2024
Announcing Flux by Black Forest Labs: The Next Leap in Text-to-Image Models

Announcing Flux by Black Forest Labs: The Next Leap in Text-to-Image Models

Flux, the largest SOTA open source text-to-image model to date, developed by Black Forest Labs — the original team behind Stable Diffusion is now available on fal. Flux pushes the boundaries of creativity and performance with an impressive 12B parameters, delivering aesthetics reminiscent of Midjourney.

Aug 1, 2024

Flux prompt examples#

Examples are generated using the Flux models. You can customize them by clicking on the "Customize it" button.

image of a cat in the style of TOK

image of a cat in the style of TOK

loras
num_inference_steps: 28
guidance_scale: 3.5
image_size: 512x512
Customize it
a trtcrd of a person on a computer, on the computer you see a meme being made with an ancient looking trollface, "the shitposter" arcana, in the style of TOK a trtcrd, tarot style

a trtcrd of a person on a computer, on the computer you see a meme being made with an ancient looking trollface, "the shitposter" arcana, in the style of TOK a trtcrd, tarot style

loras
num_inference_steps: 28
guidance_scale: 3.5
image_size: 1024x768
Customize it
generated withfal-ai/flux-lora
girl of the future using a food vendor machine, futuristic design, electronic artwork, manga character, techno-noir, animated drawing, vintage futurism, pan futurism, dystopian cyberpunk, neon-lit urban landscape, dark and gritty, high-tech, graffiti, futuristic gadgets, cinematic, detailed cityscape, moody lighting, ultra-detailed, urban landscape, high-tech implants, augmented reality

girl of the future using a food vendor machine, futuristic design, electronic artwork, manga character, techno-noir, animated drawing, vintage futurism, pan futurism, dystopian cyberpunk, neon-lit urban landscape, dark and gritty, high-tech, graffiti, futuristic gadgets, cinematic, detailed cityscape, moody lighting, ultra-detailed, urban landscape, high-tech implants, augmented reality

num_inference_steps: 8
seed: 2284939846
image_size: 768x1024
Customize it
generated withfal-ai/flux/schnell
Close-up of LEGO chef minifigure cooking for homeless. Focus on LEGO hands using utensils, showing culinary skill. Warm kitchen lighting, late morning atmosphere. Canon EOS R5, 50mm f/1.4 lens. Capture intricate cooking techniques. Background hints at charitable setting. Inspired by Paul Bocuse and Massimo Bottura's styles. Freeze-frame moment of food preparation. Convey compassion and altruism through scene details.

Close-up of LEGO chef minifigure cooking for homeless. Focus on LEGO hands using utensils, showing culinary skill. Warm kitchen lighting, late morning atmosphere. Canon EOS R5, 50mm f/1.4 lens. Capture intricate cooking techniques. Background hints at charitable setting. Inspired by Paul Bocuse and Massimo Bottura's styles. Freeze-frame moment of food preparation. Convey compassion and altruism through scene details.

num_inference_steps: 6
seed: 2219464023
image_size: 1024x1024
Customize it
generated withfal-ai/flux/schnell
A solar system with vibrant-colored planets and exotic atmospheres, depicted in a science fiction style. HD, 8k, vivid colors, HDR effect, color palette, illustration, photo, 3D render, vibrant, portrait photography.

A solar system with vibrant-colored planets and exotic atmospheres, depicted in a science fiction style. HD, 8k, vivid colors, HDR effect, color palette, illustration, photo, 3D render, vibrant, portrait photography.

num_inference_steps: 50
guidance_scale: 3
seed: 1390878983
image_size: 1024x768
Customize it
generated withfal-ai/flux/dev
A steampunk cityscape at sunset, with towering clockwork structures, airships floating between buildings, and steam billowing from intricate brass pipes

A steampunk cityscape at sunset, with towering clockwork structures, airships floating between buildings, and steam billowing from intricate brass pipes

num_inference_steps: 35
guidance_scale: 4
seed: 3270195566
image_size: 1024x768
Customize it
generated withfal-ai/flux-pro/new
A anime/cartoony character Headshot, Must me details and really well made yet looks human made

A anime/cartoony character Headshot, Must me details and really well made yet looks human made

seed: 33247972
image_size: 1024x1024
Customize it
generated withfal-ai/flux-pro/v1.1
beautiful house indoor

beautiful house indoor

controlnets
num_inference_steps: 28
guidance_scale: 3.5
seed: 1234
Customize it
generated withfal-ai/flux-general
girl in the street green neon lights

girl in the street green neon lights

controlnet_unions
num_inference_steps: 28
guidance_scale: 3.5
seed: 1234
image_size: 1024x768
Customize it
generated withfal-ai/flux-general
orange alien

orange alien

num_inference_steps: 40
guidance_scale: 4.5
seed: 1234
image_size: 1024x768
Customize it
colorful dress, woman

colorful dress, woman

controlnet_unions
num_inference_steps: 28
guidance_scale: 3.5
seed: 1234
image_size: 1024x768
Customize it
generated withfal-ai/flux-general
An ancient tree of life, its branches forming constellations against a starry night sky, with mystical creatures nestled among its roots

An ancient tree of life, its branches forming constellations against a starry night sky, with mystical creatures nestled among its roots

num_inference_steps: 28
guidance_scale: 3.5
seed: 404514731
image_size: 768x1024
Customize it
generated withfal-ai/flux-pro/new