FLUX.2 [max]

Professional-grade image generation with unmatched editing consistency and grounded generation

About model

FLUX.2 [max] is the most capable variant of FLUX.2 for professional-grade image generation and editing. Delivering top-tier quality with highest editing consistency across tasks, it features the strongest prompt following and faithful representation of various styles, with grounded generation capabilities that integrate real-time web context for visualizing trending products, current events, and latest styles.

Quality Tier

Max

Highest quality in FLUX.2 family

Grounded Gen

Web

Real-time web context integration

Grade Output

Pro

Marketplace-ready quality

Model key capabilities

Highest Editing Consistency: Professional retexturing, character consistency, spatial reasoning
Grounded Generation: Real-time web context for trending products, current events, latest styles
Character Consistency: Preserves facial features, proportions, expressions across complex edits
Strongest Prompt Following: Faithful representation of various styles with precise control

Quickstart guides

Image

Quickstart: FLUX.2

Image

Image Generation with Flux2

Image

Images Docs

API usage

cURL
Python
Typescript

Endpoint:

black-forest-labs/FLUX.2-max

curl -X POST "https://api.together.xyz/v1/images/generations" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "black-forest-labs/FLUX.2-max",
    "prompt": "Draw an anime style version of this image.",
    "width": 1024,
    "height": 768,
    "steps": 28,
    "n": 1,
    "response_format": "url",
    "image_url": "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
  }'

from together import Together

client = Together()

imageCompletion = client.images.generate(
    model="black-forest-labs/FLUX.2-max",
    width=1024,
    height=768,
    steps=28,
    prompt="Draw an anime style version of this image.",
    image_url="https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png",
)

print(imageCompletion.data[0].url)

import Together from "together-ai";

const together = new Together();

async function main() {
  const response = await together.images.create({
    model: "black-forest-labs/FLUX.2-max",
    width: 1024,
    height: 1024,
    steps: 28,
    prompt: "Draw an anime style version of this image.",
    image_url: "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png",
  });

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

main();

Model card
Architecture Overview:
• Most capable variant in the FLUX.2 family optimized for professional-grade image generation and editing.
• Supports grounded generation with real-time web context integration for up-to-date visual content creation.
• Advanced editing consistency across retexturing, character consistency, spatial reasoning, and style transfer tasks.
• Strongest prompt following capabilities in the FLUX.2 lineup with faithful style representation.

Training Methodology:
• Trained for maximum performance across diverse image generation and editing scenarios.
• Specialized training for consistent character preservation across varying scenes, angles, and environments.
• Enhanced style fidelity training enabling faithful reproduction of artistic styles and visual aesthetics.
• Real-time grounding capabilities trained to integrate current web context into generated imagery.

Performance Characteristics:
• Highest editing consistency in FLUX.2 family across all editing tasks including retexturing and character consistency.
• Superior prompt adherence compared to FLUX.2 [pro] and [flex] variants for complex, detailed instructions.
• Grounded generation uniquely supports real-time information without manual reference sourcing.
• Professional-grade output quality suitable for marketplace-ready product photos and commercial applications.
• Consistent character preservation maintains facial features, proportions, and expressions across multiple images and edits.
‍
Applications & use cases
Product Marketing & E-Commerce:
• Creating marketplace-ready product photos with polished, consistent, professional appearance.
• Consistent product visualization across multiple angles, lighting conditions, and backgrounds.
• Retexturing products with different materials, colors, and finishes while preserving shape and geometry.

Character & Brand Consistency:
• Maintaining character consistency across images, scenes, styles, and complex edits.
• Preserving facial features, proportions, expressions, and visual identity across changing environments.
• Brand mascot and character design with consistent representation across marketing materials.

Grounded & Real-Time Generation:
• Visualizing trending products, current events, or latest styles without manual reference sourcing.
• Integrating real-time web information directly into generated imagery.
• Creating timely, contextually relevant visual content based on current trends and data.

Creative & Design:
• Logo design and brand identity creation with precise control and style fidelity.
• Cinematic visuals and filmmaking concept art with professional-grade quality.
• Iterative editing workflows with consistent results across multiple refinements.

Retexturing & Material Design:
• Redesigning surfaces and materials with precision while preserving geometry and lighting.
• Consistent, high-quality material changes for products, objects, and environments.
• Architectural and interior design visualization with various material options.

Advanced Editing:
• Spatial reasoning for complex scene composition and object placement.
• Text rendering and typography integration within generated images.
• Style transfer with faithful representation of various artistic and photographic styles.
‍

Related models

Model specifications

Model data

Model provider
Black Forest Labs
Type
Image
Main use cases
Image-to-Image
Deployment
Serverless
Endpoint
black-forest-labs/FLUX.2-max
Price
$0.070 / MP
Input modalities
Text
Output modalities
Image

Released
December 15, 2025
External link
Provider docs
Category
Image

Run in Playground

Quickstart docs

Deploy model

FLUX.2 [max]

About model

API usage

Model card

Applications & use cases