Seedream 3.0

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

• bytedance/seedream-3.0

Model Overview

This bilingual (Chinese-English) image generation model supports arbitrary image dimensions — as long as the product of width and height remains within a generous limit (up to 2K). It offers faster response times, improved rendering of small text and layouts, stronger visual aesthetics and structural consistency, and high fidelity in fine details.

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

Body

promptstringRequired

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

modelundefined · enumRequiredPossible values:

response_formatstring · enumOptional

The format in which the generated images are returned.

Default: urlPossible values:

sizestringOptional

The total image area (height x width) must be between 262,144 and 4,194,304 pixels.

Example: 1024x1024

seedintegerOptional

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

guidance_scalenumber · min: 1 · max: 10Optional

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

watermarkbooleanOptional

Add an invisible watermark to the generated images.

Default: false

Responses

201

Successfully generated image

application/json

Responseany

post

HTTPcURLJavaScriptPython

POST /v1/images/generations HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer <YOUR_AIMLAPI_KEY>
Content-Type: application/json
Accept: */*
Content-Length: 139

{
  "prompt": "text",
  "model": "bytedance/seedream-3.0",
  "response_format": "url",
  "size": "1024x1024",
  "seed": 1,
  "guidance_scale": 1,
  "watermark": false
}

201

Successfully generated image

No content

Quick Example

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

Python

import requests


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": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.",
            "model": "bytedance/seedream-3.0",
            "size": "1888x301",
            "watermark": False
        }
    )

    # response.raise_for_status()
    data = response.json()

    print("Generation:", data)


if __name__ == "__main__":
    main()

JS

async function main() {
  try {
    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({
        prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.',
        model: 'bytedance/seedream-3.0',
        size: '555x543',
        watermark: false
      }),
    });

    if (!response.ok) {
      throw new Error(`HTTP error! Status: ${response.status}`);
    }

    const data = await response.json();
    console.log('Generation:', data);

  } catch (error) {
    console.error('Error:', error);
  }
}

main();

Response

Generation: {'created': 1751616711, 'data': [{'url': 'https://ark-content-generation-v2-ap-southeast-1.tos-ap-southeast-1.volces.com/seedream-3-0-t2i/02175161671039622600af416b2ca58c9c8a1e1bf93fac0335693.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYjg3ZjNlOGM0YzQyNGE1MmI2MDFiOTM3Y2IwMTY3OTE%2F20250704%2Fap-southeast-1%2Ftos%2Frequest&X-Tos-Date=20250704T081151Z&X-Tos-Expires=86400&X-Tos-Signature=76ad6d2e0eb218521b9ce0bfdc98eaf2aa683e9a0d3840624fb4d413a1fd360e&X-Tos-SignedHeaders=host&x-tos-process=image%2Fwatermark%2Cimage_YXNzZXRzL3dhdGVybWFyay5wbmc_eC10b3MtcHJvY2Vzcz1pbWFnZS9yZXNpemUsUF81'}]}

We obtained the following 1888x301 image by running this code example:

'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.'

Here’s an example of a 555×543 image generated using the same prompt:

'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.'