Models
fal
FLUX.2 [dev] Turbo

fal

llms.txt

FLUX.2 [dev] Turbo

AI Image Editing Model

Mode:

All Text to Image Image Edit

Image #3 Text-to-Image

Distilled version of Black Forest Labs' FLUX.2 [dev] outperforming it at a cheaper price. Developed by fal.ai.

FLUX.2 [dev] Turbo generated image of A hyper-realistic, macro close-up of a weathered leather craftsmans's workben...

FLUX.2 [dev] Turbo generated image of A hyper-realistic close-up portrait of an elderly artisan woodworker in a sun...

Try Model Benchmark examples

2048 x 2048

Max Resolution

Supported Modes

Text to Image Image Edit

Active

Details

Model ID

flux.2-dev-turbo

Creator

fal

Family

flux.2

Released

December 2025

Max Input Images

Ready to integrate?

Access flux.2-dev-turbo via our unified API.

Create Account

Available at 1 provider

Starting from

$0.0080 /image via fal.ai

Prices shown are in USD · Some prices estimated from per-megapixel or per-token pricing

Full pricing details

Provider Performance

Fastest generation through fal at 2,476ms median latency with 92.0% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

fal

p95: 13,297ms

Success Rate

fal

92.0%

23 / 25 requests

Time to First Byte

fal

1,887ms

p95: 13,070ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	fal	2,476ms	13,297ms	92.0%	1,887ms

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (1)

FLUX.2 [dev] Turbo is available exclusively through fal.ai, starting at $0.008/image.

fal.ai

Image Edit

fal/flux.2-dev-turbo-edit

Provider Model ID: fal-ai/flux-2/turbo/edit

Input

Megapixel

$0.0080

Output

Megapixel

$0.0080

Pricing Notes (4)

• Resolution is rounded up to the next megapixel, separately for each reference image and the generated image
• 1 megapixel = 1024x1024 pixels
• Each reference image is counted separately (minimum 1 MP each)
• Images exceeding 4 megapixels are resized to 4 megapixels

View official pricing • As of Dec 29, 2025

FLUX.2 [dev] Turbo API OpenAI-compatible

Integrate text-to-image generation and complex image editing into any application using the Lumenfall OpenAI-compatible API to access FLUX.2 [dev] Turbo. This endpoint enables programmatic creation of high-fidelity visual media through a single unified integration point.

Base URL

https://api.lumenfall.ai/openai/v1

Model

flux.2-dev-turbo

Code Examples

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=flux.2-dev-turbo" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'flux.2-dev-turbo',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="flux.2-dev-turbo",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Edit instruction for the image	T2I Edit
`seed`	integer	Random seed for reproducibility	T2I Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2I Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2I Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2I Edit

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP. Up to 4 images per request.	T2I Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	T2I Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	T2I Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	T2I Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	T2I Edit

Additional Parameters

Provider-specific passthrough fields, available only when the request is routed to the listed provider.

Parameter	Type	Description	Modes
Universal
`cfg_scale`	number	Classifier-free guidance scale — higher values stick more closely to the prompt	T2I Edit
`prompt_enhancement`	string	Whether an LLM rewrites/expands the prompt before generation (off, on) `off` `on`	T2I Edit
fal
`enable_safety_checker`	boolean	If set to true, the safety checker will be enabled.	T2I Edit
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	T2I Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

FLUX.2 [dev] Turbo Benchmarks

FLUX.2 [dev] Turbo holds the fourth position globally in text-to-image generation with an Elo rating of 1272. This distilled model by fal.ai consistently outperforms the original FLUX.2 [dev] across speed and quality metrics in competitive human-preference environments.

Lumenfall Arena

Text-to-Image

1279 Elo

Lumenfall Arena

#23

Image Editing

1058 Elo

Image Editing Landscape

Elo vs Cost

1 model without pricing omitted

Elo vs Speed

6 models waiting for enough speed data

Competition Results

Uncategorized

#10

Pose & Character Mashup

14 models

Image Editing

Source

Edit instruction

“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”

Top Matchups

See how FLUX.2 [dev] Turbo performs head-to-head against other AI models, ranked by community votes in blind comparisons.

vs Stable Diffusion 3.5 Large

Challenge: Apollo 11: Journey to Tranquility

67% W · 0% L · 33% T

vs Seedream 4.5

Challenge: Isometric Miniature Diorama Scenes

0% W · 67% L · 33% T

vs FLUX.2 [klein] 4B

Challenge: The Halloween Invitation

0% W · 100% L

vs Grok Imagine Image

Challenge: Modern Clean Menu

0% W · 100% L

vs GPT Image 1 Mini

Challenge: Candid Street Photography

0% W · 100% L

Gallery

View all 1 images

FLUX.2 [dev] Turbo FAQ

How much does FLUX.2 [dev] Turbo cost?

FLUX.2 [dev] Turbo starts at $0.008 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use FLUX.2 [dev] Turbo via API?

You can use FLUX.2 [dev] Turbo through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "flux.2-dev-turbo". Code examples are available in Python, JavaScript, and cURL.

Which providers offer FLUX.2 [dev] Turbo?

FLUX.2 [dev] Turbo is available through fal.ai on Lumenfall. Lumenfall automatically routes requests to the best available provider.

What is the maximum resolution for FLUX.2 [dev] Turbo?

FLUX.2 [dev] Turbo supports images up to 2048x2048 resolution.

Overview

FLUX.2 [dev] Turbo is an accelerated image generation model developed by fal.ai, designed to provide high-fidelity outputs with significantly lower latency than the base FLUX.2 [dev] model. It uses architectural distillation to achieve high performance at a lower cost, maintaining the composition and detail of the original Black Forest Labs weights while requiring fewer sampling steps. This open-weights model is released under a non-commercial license and is optimized for workflows where generation speed and cost-efficiency are prioritized over maximum sampling depth.

Strengths

Generation Velocity: Significant reduction in inference time compared to the standard FLUX.2 [dev], capable of producing high-resolution images in a fraction of the steps.
Anatomical and Text Fidelity: Retains the core architectural strengths of the FLUX family, specifically in rendering legible text and accurate human anatomy (such as hands and limbs).
Instruction Following: High responsiveness to complex, multi-subject prompts involving specific spatial arrangements or lighting conditions.
Operational Efficiency: Lower compute requirements and a reduced price point ($0.008 starting price) make it suitable for high-volume prototyping or iterative design processes.

Limitations

Non-Commercial License: The model is restricted to research and personal use; it cannot be integrated into commercial products or used for profit-generating workflows.
Detail Ceiling: Due to the distillation process, it may occasionally lack the extreme fine-grain texture or subtle lighting nuances found in the full FLUX.2 [dev] model during multi-step high-CFG generations.
Reduced Flexibility: This turbo variant is specifically tuned for a lower step count, which may make it less responsive to manual sampling adjustments compared to its non-distilled counterpart.

Technical Background

FLUX.2 [dev] Turbo is part of the FLUX.2 family, utilizing a distilled version of the original diffusion transformer (DiT) architecture. By applying adversarial or sequence-level distillation techniques, fal.ai optimized the original Black Forest Labs weights to converge in fewer iterations without sacrificing the structural integrity of the generated output. The model accepts both text and image inputs, allowing for versatile image-to-image and text-to-image workflows.

Best For

Iterative Design: Rapidly testing different prompt variations or character concepts without the wait times associated with standard diffusion models.
Prototyping: Building proof-of-concept creative tools where speed-of-feedback is critical for user experience.
Research and Personal Projects: High-quality image generation for non-commercial academic research or hobbyist exploration.

FLUX.2 [dev] Turbo is available through Lumenfall’s unified API and playground, allowing developers to integrate fast, state-of-the-art image generation into their research environments with minimal configuration.

Try FLUX.2 [dev] Turbo in Playground

Generate images with custom prompts — no API key needed.

Open Playground