< img height="1" width="1" style="display:none;" alt="" src="https://px.ads.linkedin.com/collect/?pid=3131724&fmt=gif" />
Last updated:

    Text to Image

    Task Overview

    Text to Image tasks generate images from text descriptions (prompts), suitable for image generation models such as Stable Diffusion and FLUX.

    API Usage

    curl https://<instance-address>/v1/images/generations \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer <access-token>" \
      -d '{
        "model": "<model-name>",
        "prompt": "a beautiful mountain landscape at sunset, photorealistic",
        "n": 1,
        "size": "1024x1024"
      }'
    

    Response Format

    {
      "created": 1234567890,
      "data": [
        {
          "url": "https://...",
          "b64_json": "..."
        }
      ]
    }
    

    The response contains the generated image as a URL or Base64-encoded content (depending on the response_format parameter in the request).

    Python Example

    from openai import OpenAI
    
    client = OpenAI(
        base_url="https://<instance-address>/v1",
        api_key="<access-token>"
    )
    
    response = client.images.generate(
        model="<model-name>",
        prompt="a beautiful mountain landscape at sunset, photorealistic",
        n=1,
        size="1024x1024"
    )
    print(response.data[0].url)
    

    Common Parameters

    Parameter Type Description
    prompt string Image description text
    n int Number of images to generate; default 1
    size string Image dimensions, e.g., 512x512, 1024x1024
    response_format string Return format: url or b64_json