FLUX.2 [pro]

Name: FLUX.2 [pro]
Brand: Black Forest Labs
Price: 0.015 USD
Availability: InStock

AI Image Editing Model

Image #9 Text-to-Image #8 Image-to-Image

Black Forest Labs' state-of-the-art image generation model with maximum quality and speed, supporting text-to-image and multi-reference image editing with up to 4MP output

Try Model Benchmark examples

2048 x 2048

Max Resolution

Supported Modes

Text to Image Image Edit

Active

Details

Model ID

flux.2-pro

Also known as: flux-2-pro

Creator

Black Forest Labs

Family

flux.2

Max Input Images

Ready to integrate?

Access flux.2-pro via our unified API.

Create Account

Available at 2 providers

Starting from

$0.015 /image via Replicate

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

See all providers

Provider Performance

Fastest generation through replicate at 14,131ms median latency with 100.0% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

replicate

p95: 38,175ms

fal

p95: 21,711ms

Success Rate

replicate

100.0%

17 / 17 requests

fal

100.0%

19 / 19 requests

Time to First Byte

replicate

13,710ms

p95: 28,363ms

fal

16,412ms

p95: 20,563ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	replicate	14,131ms	38,175ms	100.0%	13,710ms
2	fal	16,580ms	21,711ms	100.0%	16,412ms

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

Providers & Pricing (3)

FLUX.2 [pro] is available from 3 providers, with per-image pricing starting at $0.015 through fal.ai.

fal.ai

Text to Image

fal/flux.2-pro

Provider Model ID: fal-ai/flux-2-pro

Output

Megapixel

—

Pricing Notes (2)

• Resolution is rounded up to the next megapixel
• 1 megapixel = 1024x1024 pixels

View official pricing • As of Dec 28, 2025

fal.ai

Image Edit

fal/flux.2-pro-edit

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

Input

Megapixel

$0.015

Output

Megapixel

—

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 28, 2025

Replicate

Text to Image Image Edit

replicate/flux.2-pro

Provider Model ID: black-forest-labs/flux-2-pro

Input

Megapixel

$0.015

Output

Request

$0.015

Megapixel

$0.015

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 Jan 02, 2026

flux-2-pro API OpenAI-compatible

Integrate FLUX.2 [pro] into your workflow using Lumenfall’s OpenAI-compatible API to generate high-resolution 4MP images and perform complex multi-reference image edits. This unified endpoint provides programmatic access to Black Forest Labs' professional-grade media generation architecture for consistent production-quality output.

Base URL

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

Model

flux.2-pro

Code Examples

Text to Image

/v1/images/generations

curl -X POST \

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

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "flux.2-pro",

    "prompt": "",

    "size": "1024x1024"

}'

# Response:

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

import OpenAI from 'openai';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

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

});

const response = await client.images.generate({

  model: 'flux.2-pro',

  prompt: '',

  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.generate(

    model="flux.2-pro",

    prompt="",

    size="1024x1024"

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

print(response.data[0].url)

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-pro" \

  -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-pro',

  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-pro",

    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") `auto` `1K` 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

Output	`size`		`aspect_ratio` + `resolution`
Flexible
Auto	`"auto"`	—	Model chooses optimal dimensions
Custom 1–14142px per side	`"WxH"`	—	Any pixel dimensions within model constraints

1K 9 sizes

Output	`size`		`aspect_ratio` + `resolution`
1183 × 887	`"1183x887"`	or	`"4:3"` + `"1K"`
916 × 1145	`"916x1145"`	or	`"4:5"` + `"1K"`
1145 × 916	`"1145x916"`	or	`"5:4"` + `"1K"`
1024 × 1024	`"1024x1024"`	or	`"1:1"` + `"1K"`
887 × 1182	`"887x1182"`	or	`"3:4"` + `"1K"`
836 × 1254	`"836x1254"`	or	`"2:3"` + `"1K"`
1254 × 836	`"1254x836"`	or	`"3:2"` + `"1K"`
768 × 1365	`"768x1365"`	or	`"9:16"` + `"1K"`
1365 × 768	`"1365x768"`	or	`"16:9"` + `"1K"`

How these parameters work

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.	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

Parameter	Type	Description	Modes
`enable_safety_checker` fal	boolean	Whether to enable the safety checker.	T2I Edit
`height` replicate	integer	Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16 (if it's not, it will be rounded to nearest multiple of 16).	T2I Edit
`output_quality` replicate	integer	Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs	T2I Edit
`safety_tolerance`	string	The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. `1` `2` `3` `4` `5`	T2I Edit
`sync_mode` fal	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
`width` replicate	integer	Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16 (if it's not, it will be rounded to nearest multiple of 16).	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 [pro] Benchmarks

FLUX.2 [pro] currently holds the #9 position in global text-to-image rankings with a 1255 Elo and ranks #10 for image editing with an Elo of 1202. These scores place Black Forest Labs' flagship model within the top tier of all competitive media generation benchmarks.

Lumenfall Arena

Text-to-Image

1258 Elo

Lumenfall Arena

Image Editing

1208 Elo

Text-to-Image Landscape

Elo vs Cost

Elo vs Speed

8 without speed data omitted.

Image Editing Landscape

Elo vs Cost

Elo vs Speed

1 without speed data omitted.

Competition Results

Image Editing

Photorealism

View leaderboard

Man and Car in California

13 models

Image Editing

Source

Edit instruction

“Make a photo of the man driving the car down the California coastline”

FLUX.2 [pro] edited result for Night Sky Transformation

Original image before FLUX.2 [pro] editing

Before After

Night Sky Transformation

16 models

Image Editing

Edit instruction

“Change the scene to night: a deep, dark sky with subtle, glistening stars visible behind the mountain.”

FLUX.2 [pro] edited result for Neutral Expression to Genuine Smile

Before After

#13

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

FLUX.2 [pro] edited result for Bald man challenge

Before After

#12

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

#13

Golden Hour Stroll

13 models

Image Editing

Source

Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Text-to-Image

Text Rendering

View leaderboard

Vintage Cafe Logo

21 models

Text-to-Image

Prompt

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

#12

Modern Clean Menu

19 models

Text-to-Image

Prompt

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

#13

Apollo 11: Journey to Tranquility

19 models

Text-to-Image

Prompt

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

Image Editing

Anime

View leaderboard

Studio Ghibli Anime Style

14 models

Image Editing

Source

Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Image Editing

Portrait

View leaderboard

Before After

#13

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

Before After

#12

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Text-to-Image

Photorealism

View leaderboard

#16

Candid Street Photography

24 models

Text-to-Image

Prompt

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

Text-to-Image

Product, Branding & Commercial

View leaderboard

Vintage Cafe Logo

21 models

Text-to-Image

Prompt

Text-to-Image

Portrait

View leaderboard

#10

Fantasy Warrior

21 models

Text-to-Image

Prompt

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

Uncategorized

Heroic Super Hero Portrait

21 models

Text-to-Image

Prompt

“Hyper-photorealistic full-body portrait of a female superhero standing triumphantly on a New York skyscraper rooftop at golden sunset, wearing a classic modest superhero costume with flowing cape, chest emblem, gloves, and boots in red and blue colors, practical design, short hair, strong determined heroic expression looking into the distance, powerful confident stance with hands on hips and cape billowing dramatically in the wind, detailed urban cityscape background, warm natural sunlight with sharp shadows and fabric highlights, ultra-sharp textures on suit, hair, and concrete, 8K masterpiece, empowering family-friendly style.”

Over-the-top cartoon caricature

13 models

Image Editing

Source

Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

#21

Geometric Composition

22 models

Text-to-Image

Prompt

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

#15

Adorable Baby Animals in Sunny Meadow

25 models

Text-to-Image

Prompt

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

Fantasy Warrior

14 models

Text-to-Image

Prompt

3 attempts – showing best result

Top Matchups

See how FLUX.2 [pro] 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

20% W · 80% L

vs Nano Banana

Challenge: Neutral Expression to Genuine Smile

20% W · 80% L

vs Nano Banana

Challenge: Heroic Super Hero Portrait

25% W · 25% L · 50% T

vs Grok Imagine Image

Challenge: Modern Clean Menu

25% W · 75% L

vs Nano Banana Pro

Challenge: Bald man challenge

0% W · 100% L

FLUX.2 [pro] is best for

See all Use Cases

The model excels in commercial applications, ranking #2 out of 19 for product and branding with a 70% win rate, and preserves high fidelity in portraiture with a 75% win rate. While it performs strongly in anime generation at rank #4, it shows moderate competitive performance in specialized text rendering where it ranks #11.

#2 of 21

Product, Branding & Commercial

Gen · 68.2% win rate

#5 of 14

Anime

Edit · 63.0% win rate

Gallery

View all 20 images

FLUX.2 [pro] FAQ

How much does FLUX.2 [pro] cost?

FLUX.2 [pro] starts at $0.015 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

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

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

Which providers offer FLUX.2 [pro]?

FLUX.2 [pro] is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

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

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

Overview

FLUX.2 [pro] is the flagship high-performance image generation model developed by Black Forest Labs. It is designed to produce high-fidelity visuals up to 4 megapixels while maintaining a balance between aesthetic quality and inference speed. A distinguishing feature of this iteration is its native support for multi-reference image editing, allowing users to guide generation using existing visual assets alongside text prompts.

Strengths

High-Resolution Output: Capable of generating detailed images up to 4MP, providing significantly more pixel-level data than standard 1MP models for large-format applications.
Multi-Reference Consistency: Excels at “image-to-image” and reference-based workflows, using multiple source images to maintain consistency in style, character, or composition during the editing process.
Complex Prompt Adherence: Demonstrates high precision in following intricate text instructions, particularly when handling spatial relationships between objects and specific lighting conditions.
Text Rendering Accuracy: Inherits the family’s capability for rendering legible, correctly spelled text within generated images, even in complex fonts or curved layouts.

Limitations

Computational Cost: As the “pro” tier model, it carries a higher price point per generation ($0.015) compared to the “schnell” or “dev” variants, making it less ideal for high-volume rapid prototyping.
Latency Tradeoff: While optimized for speed relative to its output size, the sheer volume of pixels (4MP) results in longer generation times than lower-resolution, distilled models.
Hardware Requirements: Due to its scale and state-of-the-art weights, it is generally restricted to managed API environments rather than consumer-grade local hardware.

Technical Background

FLUX.2 [pro] is built on a scaled diffusion transformer architecture, a refinement of the original Flow-based models developed by the core team behind Stable Diffusion. The training approach focuses on maximizing the signal-to-noise ratio at high resolutions, utilizing a “pro” weight set that has been fine-tuned for photorealism and professional-grade color accuracy. It utilizes advanced latent space compression to handle the 4MP output without proportional increases in VRAM usage.

Best For

This model is best suited for professional design workflows, advertising photography, and high-end digital art where resolution and prompt fidelity are non-negotiable. It is particularly effective for brand-consistent content creation where multiple reference images must define the output’s look and feel. FLUX.2 [pro] is available for testing and deployment through Lumenfall’s unified API and interactive playground, allowing developers to integrate its high-resolution capabilities into their applications with minimal overhead.

Try FLUX.2 [pro] in Playground

Generate images with custom prompts — no API key needed.

Open Playground