Models / Black Forest Labs
Image

FLUX.1 Krea [dev]

Advanced photorealistic image generation with distinctive aesthetics

About model

FLUX.1 Krea [dev] is a breakthrough open‑weights text‑to‑image model that delivers exceptional photorealism with distinctive aesthetics. Developed through collaboration between Black Forest Labs & Krea AI, it overcomes the common "AI look" problem to generate diverse, visually compelling images that surprise users with their realism & artistic quality.

  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    black-forest-labs/FLUX.1-krea-dev

    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.1-krea-dev",
        "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.1-krea-dev",
        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.1-krea-dev",
        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:
    • Distilled open‑weights version of Krea 1
    • Compatible with FLUX.1 [dev] architecture & ecosystem
    • Optimized for photorealistic image generation

    Training Methodology:
    • Trained specifically to generate realistic & diverse images
    • Addresses oversaturated & oversmooth texture issues
    • Enhanced for exceptional realism & image quality

    Performance Characteristics:
    • ELO rating of 1011 in human preference assessments
    • Outperforms previous open FLUX text‑to‑image models
    • On par with closed solutions like FLUX1.1 [pro]
    • Best open weights FLUX model for text‑to‑image generation

  • Applications & use cases

    Creative & Artistic Applications:
    • Professional photography & visual content creation
    • Marketing & advertising campaign visuals
    • Social media content generation
    • Artistic & creative projects

    Commercial & Business Solutions:
    • E‑commerce product visualization
    • Brand identity & marketing materials
    • Website & digital asset creation
    • Custom visual content for businesses

    Development & Customization:
    • Base model for downstream fine‑tuning
    • Custom model development projects
    • Research & experimentation in image generation
    • Integration into creative workflows & applications

Related models
  • Model provider
    Black Forest Labs
  • Type
    Image
  • Main use cases
    Image Generation
  • Deployment
    Serverless
  • Price

    $0.025 / MP

  • Input modalities
    Text
  • Output modalities
    Image