Imagen 3

This documentation is valid for the following list of our models:

• imagen-3.0-generate-002

Model Overview

Google's latest text-to-image AI model, designed to generate high-quality, photorealistic images from text descriptions with improved detail, lighting, and fewer artifacts. It boasts enhanced natural language understanding and better text rendering.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Authorizations

access-token

Body

application/json

modelundefined · enumRequiredPossible values:

promptstring · max: 400Required

The text prompt describing the content, style, or composition of the image to be generated.

convert_base64_to_urlbooleanOptional

If True, the URL to the image will be returned; otherwise, the file will be provided in base64 format.

Default: false

num_imagesinteger · max: 4Optional

The number of images to generate.

Default: 1

seedinteger · max: 4294967295Optional

The same seed and the same prompt given to the same version of the model will output the same image every time.

enhance_promptbooleanOptional

Optional parameter to use an LLM-based prompt rewriting feature for higher-quality images that better match the original prompt. Disabling it may affect image quality and prompt alignment.

Default: true

aspect_ratiostring · enumOptional

The aspect ratio of the generated image.

Default: 1:1Possible values:

person_generationstring · enumOptional

Allow generation of people.

Default: allow_adultPossible values:

safety_settingstring · enumOptional

Adds a filter level to safety filtering.

Default: block_medium_and_abovePossible values:

add_watermarkbooleanOptional

Add an invisible watermark to the generated images.

Default: false

Responses

201

Successfully generated image

application/json

post

JavaScriptPythoncURLHTTP

async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'imagen-3.0-generate-002',
      prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.',
    }),
  });

  const data = await response.json();
  console.log(JSON.stringify(data, null, 2));
}

main();

201

Successfully generated image

{
  "status": "text",
  "prompt": [
    "text"
  ],
  "model": "text",
  "model_owner": "text",
  "tags": {
    "ANY_ADDITIONAL_PROPERTY": null
  },
  "num_returns": 1,
  "args": {
    "model": "text",
    "prompt": "text",
    "n": 1,
    "steps": 1,
    "size": "text"
  },
  "subjobs": [],
  "output": {
    "choices": [
      {
        "image_base64": "text"
      }
    ]
  }
}

Quick Example

Let's generate an image of the specified size using a simple prompt.

Python

import requests
import json  # for getting a structured output with indentation

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "prompt": "Racoon eating ice-cream",
            "model": "imagen-3.0-generate-002",
            "convert_base64_to_url": True,
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()

JS

async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
    method: 'POST',
    headers: {
      // Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'imagen-3.0-generate-002',
      prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.',
      convert_base64_to_url: true
    }),
  });

  const data = await response.json();
  console.log(data);
}

main();

Note that prompt enhancement is enabled by default. The model will also return the enhanced prompt in the response. If you prefer not to use this feature, set the parameter enhance_prompt to False.

Response

{
  data: [
    {
      mime_type: 'image/png',
      url: 'https://cdn.aimlapi.com/generations/guepard/1756970940506-11b77754-ca2a-4995-a260-d75adfb9885c.png',
      prompt: 'A playful raccoon with a mischievous grin is indulging in a scoop of creamy, strawberry ice cream. Its black mask and fluffy tail are prominent features as it delicately licks the cool treat with its pink tongue. The raccoon is perched on a park bench, the soft daylight illuminating its fur and the vibrant color of the ice cream. The background is a slightly blurred, idyllic summer scene with a few scattered trees and a lush green lawn. The overall image captures a moment of unexpected delight, with the raccoon enjoying a sweet summer treat in a natural and relaxing setting. This picture captures the charming side of this often misunderstood animal, showcasing its playful curiosity and enjoyment of simple pleasures. The image has a soft, nostalgic quality, using natural light and a shallow depth of field to focus on the raccoon and its ice-cream.'
    }
  ]
}

Default aspect ratio is 1:1, so we obtained the following 1024x1024 image by running this code example:

In reality, raccoons shouldn’t be given ice cream or chocolate—it’s harmful to their metabolism. But in the AI world, raccoons party like there’s no tomorrow.