Explore

FLUX IMAGE MODELS

Flux model collection


The Flux model collection on WaveSpeedAI features high-performance text-to-image and image-to-image generation with rich stylistic control and structural fidelity. Enhanced by WaveSpeed’s optimized inference engine, Flux models run up to 6x faster than standard endpoints, delivering consistent quality with minimal latency. Ideal for creative workflows requiring fast iteration, LoRA support, and fine-grained visual modification.

wavespeed-ai/flux-dev-lora

wavespeed-ai/flux-dev-lora

$0.015

Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs

wavespeed-ai/flux-dev-lora-ultra-fast

wavespeed-ai/flux-dev-lora-ultra-fast

$0.006

Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs, ultra fast !

wavespeed-ai/flux-dev

wavespeed-ai/flux-dev

$0.012

Flux-dev text to image model, 12 billion parameter rectified flow transformer

wavespeed-ai/flux-schnell

wavespeed-ai/flux-schnell

$0.003

FLUX.1 [schnell] is fastest image generation model tailored for local development and personal use, a 12 billion parameter rectified flow transformer

wavespeed-ai/flux-schnell-lora

wavespeed-ai/flux-schnell-lora

$0.005

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.

wavespeed-ai/flux-dev-ultra-fast

wavespeed-ai/flux-dev-ultra-fast

$0.005

Flux-dev text to image model, 12 billion parameter rectified flow transformer, ultra fast!

wavespeed-ai/flux-pro-redux

wavespeed-ai/flux-pro-redux

$0.025

FLUX.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.

wavespeed-ai/flux-redux-dev

wavespeed-ai/flux-redux-dev

$0.025

Open-weight image variation model. Create new versions while preserving key elements of your original.

wavespeed-ai/flux-kontext-pro

wavespeed-ai/flux-kontext-pro

$0.04

A state-of-the-art image editing model, Flux Kontext, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash.

wavespeed-ai/flux-kontext-pro/multi

wavespeed-ai/flux-kontext-pro/multi

$0.04

Experimental version of FLUX.1 Kontext [pro] with multi image handling capabilities

wavespeed-ai/flux-kontext-max

wavespeed-ai/flux-kontext-max

$0.08

A state-of-the-art image editing model, Flux Kontext, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash.

wavespeed-ai/flux-kontext-max/multi

wavespeed-ai/flux-kontext-max/multi

$0.08

Experimental version of FLUX.1 Kontext [max] with multi image handling capabilities

wavespeed-ai/flux-kontext-max/text-to-image

wavespeed-ai/flux-kontext-max/text-to-image

$0.08

FLUX.1 Kontext [max] text-to-image is a new premium model brings maximum performance across all aspects – greatly improved prompt adherence.

wavespeed-ai/flux-kontext-pro/text-to-image

wavespeed-ai/flux-kontext-pro/text-to-image

$0.04

The FLUX.1 Kontext [pro] text-to-image delivers state-of-the-art image generation results with unprecedented prompt following, photorealistic rendering, and flawless typography.

wavespeed-ai/flux-dev-fill

wavespeed-ai/flux-dev-fill

$0.035

FLUX.1 [dev] Fill 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.

wavespeed-ai/flux-control-lora-canny

wavespeed-ai/flux-control-lora-canny

$0.03

FLUX Control LoRA Canny is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a Canny edge map.

wavespeed-ai/flux-control-lora-depth

wavespeed-ai/flux-control-lora-depth

$0.03

FLUX Control LoRA Depth is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a depth map.