Models / Black Forest Labs
Image

FLUX.2 [pro]

Advanced production-grade image generation with multi-reference editing

About model

FLUX.2 [pro] has 32K-token context window. On Together AI it costs $0.03 per image.

FLUX.2 [pro] is Black Forest Labs' production model for image generation and editing, built for high quality at speed. The FLUX.2 family, released on November 25, 2025, pairs a Mistral-3 24B vision-language model with a rectified flow transformer and handles text-to-image generation and image editing in one architecture. FLUX.2 [pro] generates and edits images at up to 4 megapixels and accepts multiple reference images in one request, which keeps a character, product or style consistent across outputs. It also follows structured JSON prompts, matches colors given as hex codes and renders legible text for infographics and interface mockups. Available on Together AI.

‍

Close-up of a potter's hands shaping clay on a wheel
Hands
A potter's hands in wet clay, down to the fingernails.
Prompt
Close-up photograph of a potter's hands shaping wet clay on a spinning wheel, clay on the fingers, natural window light, shallow depth of field
A stack of knitted wool sweaters in autumn colours on a wooden chair
Fabrics
Cable-knit wool with the stitches visible.
Prompt
A neatly folded stack of knitted wool sweaters in autumn colours on a wooden chair, visible yarn texture, soft window light, photograph
A portrait of a young woman with freckles laughing in warm light
Faces
Freckles, flyaway hair and a natural smile.
Prompt
Natural light portrait of a young woman with freckles laughing, wind in her hair, shallow depth of field, 50mm lens
Generated with FLUX.2 [pro] on Together AI. Images are unedited.
Max Resolution

4MP

Generation and editing at up to 4 megapixels

Structured Prompts

JSON

Follows structured JSON prompts and hex color codes

Vision-Language Model

24B

Mistral-3 model paired with a rectified flow transformer

Model key capabilities
  • Multi-Reference Editing: Combines several reference images in one request and keeps characters, products and styles consistent
  • Exact Color Control: Matches brand colors given as hex codes in the prompt
  • Text and Detail: Legible typography for infographics and interface mockups, with sharper textures and more stable lighting
  • Production-Ready Infrastructure: 99.9% SLA, available on Together AI serverless infrastructure
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    black-forest-labs/FLUX.2-pro

    curl -X POST "https://api.together.ai/v1/images/generations" \
      -H "Authorization: Bearer $TOGETHER_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "black-forest-labs/FLUX.2-pro",
        "prompt": "A serene mountain landscape at sunset with a lake reflection"
      }'
    from together import Together
    
    client = Together()
    
    response = client.images.generate(
        model="black-forest-labs/FLUX.2-pro",
        prompt="A serene mountain landscape at sunset with a lake reflection",
    )
    
    print(response.data[0].url)
    import Together from 'together-ai';
    
    const together = new Together();
    
    const response = await together.images.generate({
      model: "black-forest-labs/FLUX.2-pro",
      prompt: "A serene mountain landscape at sunset with a lake reflection",
    });
    
    console.log(response.data[0].url);
  • Model card

    Architecture Overview:
    • Next-generation image model with enhanced multi-reference support
    • Up to 4MP output resolution capability
    • 32K prompt token capacity for detailed creative direction

    Multi-Reference System:
    • API: Up to 8 reference images (9 MP total input)
    • Playground: Up to 10 reference images
    • Advanced character, product & style consistency

    Performance Characteristics:
    • Photorealistic rendering with professional-grade detail
    • Hex-code color accuracy for brand guidelines
    • Enhanced prompt following and world knowledge
    • Improved text rendering for typography and UI mockups

    ‍

  • Prompting

    Together AI API Access:
    • Access FLUX.2 [pro] via Together AI APIs using the endpoint black-forest-labs/FLUX.2-pro
    • Authenticate using your Together AI API key in request headers
    • Send an image generation request with a text prompt, and set width and height from 256 to 1920 pixels
    • For editing, pass image URLs in reference_images and refer to them by number in the prompt, such as the jacket from image 2
    • For exact colors, write the word color or hex followed by the code, for example color #2E4057. Structured JSON prompts are also accepted
    • Available on Together AI serverless infrastructure

  • Applications & use cases

    Marketing and Advertising:
    • Run campaigns with the same character across many assets
    • Place a product in new contexts with lighting that adapts to the scene
    • Match brand colors exactly with hex codes

    E-Commerce and Product Visualization:
    • Generate product photography at scale
    • Create lifestyle shots and variants from reference images

    Design and UI:
    • Produce interface mockups with readable text
    • Generate infographics from a detailed written specification

  • Model provider
    Black Forest Labs
  • Type
    Image
  • Main use cases
    Image Generation
  • Deployment
  • Context length
    32K
  • Price

    $0.03 / image

  • Input modalities
    Text
    Image
  • Output modalities
    Image