Models / Google
Image

Google Imagen 4.0 Preview

Create stunning images with Google's latest AI

About model

Google Imagen 4.0 Preview offers advanced image generation with up to 2K resolution output, featuring SynthID watermarking for AI content identification. Optimized for creativity with enhanced colors, styles, and text rendering capabilities.

Quickstart guides
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    google/imagen-4.0-preview

    curl -X POST "https://api.together.xyz/v1/images/generations" \
      -H "Authorization: Bearer $TOGETHER_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "google/imagen-4.0-preview",
        "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="google/imagen-4.0-preview",
        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: "google/imagen-4.0-preview",
        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:
    • Advanced diffusion-based model architecture
    • Supports up to 2K resolution generation
    • 10x faster generation mode available

    Key Features:
    • SynthID invisible watermarking
    • Enhanced text rendering capabilities
    • Improved color and style diversity

  • Applications & use cases

    Use Cases:
    • Creative design and rapid prototyping
    • Marketing and advertising visuals
    • Blog and social media content
    • Concept visualization for products
    • Educational materials and illustrations

Related models
  • Model provider
    Google
  • Type
    Image
  • Main use cases
    Image Generation
  • Deployment
    Serverless
  • Input price

    $0.04 / MP

  • Input modalities
    Text
  • Output modalities
    Image