Models / Pruna AI
Image

P-Image-Ideogram

Fast text-to-image with precise typography and layout control

About model

On Together AI, P-Image-Ideogram costs $0.00225 per image.

P-Image-Ideogram is a text-to-image model from Pruna AI, built in collaboration with Ideogram for fast, production-grade generation where in-image text, layout, and branding must be precise. Adjustable thinking levels trade generation speed and cost against quality from the same model, and images generate at 1K or 2K across aspect-ratio presets or custom dimensions. Beyond natural-language prompts, the model accepts structured JSON prompts following the Ideogram 4.0 caption schema, giving tighter control over layout, color palettes, bounding boxes, and typography. Available on Together AI.

‍

Max Resolution

2K

1K or 2K output with presets or custom dimensions

Thinking Levels

Tunable

Balance speed and cost against quality per request

Structured Prompting

JSON

Control layout, color palettes, bounding boxes, and typography

Model key capabilities
  • Precise Typography: Renders readable, correctly spelled text as part of the design
  • Adjustable Thinking: Lower levels for fast drafts, higher levels for detailed prompts and crisp text
  • Structured Layout Control: JSON prompts following the Ideogram 4.0 caption schema for exact composition
  • Available on Together AI: Serverless access through the Together AI API
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    prunaai/p-image-ideogram

    curl -X POST "https://api.together.ai/v1/images/generations" \
      -H "Authorization: Bearer $TOGETHER_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "prunaai/p-image-ideogram",
        "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="prunaai/p-image-ideogram",
        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: "prunaai/p-image-ideogram",
        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:
    • Text-to-image model in Pruna AI's P-Image family, built in collaboration with Ideogram
    • Text input with image output at 1K or 2K
    • Aspect-ratio presets plus custom dimensions up to 2560 pixels

    Training Methodology:
    • Trained on structured captions with a consistent field order, matching the Ideogram 4.0 JSON prompting schema

    Performance Characteristics:
    • Pruna optimizes the P-Image family for fast inference in high-volume production workloads
    • Higher thinking levels improve prompt adherence and typography on detailed prompts

    ‍

  • Prompting

    Together AI API Access:
    • Access P-Image-Ideogram via Together AI APIs using the endpoint prunaai/p-image-ideogram
    • Authenticate using your Together AI API key in request headers
    • Choose a thinking level and an image size of 1K or 2K
    • Put exact wording in quotation marks and describe font, size, color, and position for best typography
    • Use structured JSON prompts for strict control over layout and composition
    • Available on Together AI with serverless access

    ‍

  • Applications & use cases

    Marketing & Brand Design:
    • Create posters, ads, and social graphics with correctly spelled headlines
    • Hold brand color palettes and layouts with structured prompts
    • Generate campaign variants at high volume

    Editorial & Publishing:
    • Produce magazine openers and covers with sharp mastheads
    • Design podcast and series artwork with integrated titles
    • Lay out typography-heavy compositions precisely

    Product & Creative Teams:
    • Embed fast image generation into creative tools and pipelines
    • Draft quickly at low thinking levels, then finalize at high
    • Generate product, people, and brand imagery from text

    ‍

  • Model provider
    Pruna AI
  • Type
    Image
  • Main use cases
    Image Generation
  • Resolution/Duration
    1K-2K
  • Deployment
  • Price

    $0.00225 / image

  • Input modalities
    Text
  • Output modalities
    Image
  • Category
    Image