> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Seedream 5.0 Pro

> Use ByteDance Seedream 5.0 Pro through AnyFast for text-to-image generation, image editing, and multi-image reference.

Seedream 5.0 Pro is ByteDance's high-precision image generation and editing model, available through the AnyFast API. Use model ID `doubao-seedream-5-0-pro-260628`.

<Info>For specific content requests, select the **Special-Ns** resource group.</Info>

<Warning>Seedream 5.0 Pro does not support grouped image generation, web search, or streaming. Do not send `sequential_image_generation`, `sequential_image_generation_options`, `tools`, or `stream`.</Warning>

## Key capabilities

* **Text to image** — Generate a high-precision image from text
* **Image to image** — Edit references and combine content from multiple images
* **Interactive editing** — Use natural language, marked regions, points, bounding boxes, arrows, and annotations
* **Multilingual text** — Generate text in Russian, Arabic, Filipino, Thai, Turkish, Korean, Malay, Spanish, Portuguese, Indonesian, French, German, Vietnamese, Japanese, and other supported languages
* **Output control** — Configure size, response format, image format, and watermark

<Tabs>
  <Tab title="Text to image">
    ## Quick example

    <CodeGroup>
      ```bash cURL theme={null}
      curl https://www.anyfast.ai/v1/images/generations \
        -H "Authorization: Bearer <token>" \
        -H "Content-Type: application/json" \
        -d '{
          "model": "doubao-seedream-5-0-pro-260628",
          "prompt": "A high-end product hero image for a smart speaker, precise lighting, clean editorial layout",
          "size": "2K",
          "output_format": "png",
          "watermark": false
        }'
      ```

      ```python Python theme={null}
      import requests

      response = requests.post(
          "https://www.anyfast.ai/v1/images/generations",
          headers={
              "Authorization": "Bearer YOUR_API_KEY",
              "Content-Type": "application/json",
          },
          json={
              "model": "doubao-seedream-5-0-pro-260628",
              "prompt": "A high-end product hero image for a smart speaker, precise lighting, clean editorial layout",
              "size": "2K",
              "output_format": "png",
              "watermark": False,
          },
      )

      print(response.json())
      ```
    </CodeGroup>

    | Parameter                      | Type    | Required | Description                                                                             |
    | ------------------------------ | ------- | -------- | --------------------------------------------------------------------------------------- |
    | `model`                        | string  | Yes      | Must be `doubao-seedream-5-0-pro-260628`                                                |
    | `prompt`                       | string  | Yes      | Image generation prompt. Keep it concise enough that important details are not diluted. |
    | `size`                         | string  | No       | `1K`, `2K`, or explicit pixels such as `2048x1024`                                      |
    | `response_format`              | string  | No       | `url` or `b64_json`; default `url`                                                      |
    | `output_format`                | string  | No       | `png` or `jpeg`; default `jpeg`                                                         |
    | `watermark`                    | boolean | No       | Whether to add an AI-generated watermark                                                |
    | `optimize_prompt_options.mode` | string  | No       | Use `standard`                                                                          |
  </Tab>

  <Tab title="Image to image">
    ## Quick example

    ```bash cURL theme={null}
    curl https://www.anyfast.ai/v1/images/generations \
      -H "Authorization: Bearer <token>" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "doubao-seedream-5-0-pro-260628",
        "prompt": "Add a ceramic coffee cup to the marked area and preserve the original composition",
        "image": "https://example.com/marked-reference.png",
        "size": "2K",
        "output_format": "png",
        "watermark": false
      }'
    ```

    Use `<point>` or `<bbox>` tags in the prompt for coordinate-based editing. `image` accepts a URL, Base64 data URI, or an array of up to 10 references.

    ```json Coordinate-based edit theme={null}
    {
      "model": "doubao-seedream-5-0-pro-260628",
      "prompt": "Place the subject from image 1 <bbox>179 283 796 986</bbox> into image 2 <bbox>118 331 933 871</bbox>.",
      "image": [
        "https://example.com/source.png",
        "https://example.com/target.png"
      ],
      "size": "2K",
      "output_format": "png"
    }
    ```

    | Parameter                      | Type            | Required | Description                                                                                                       |
    | ------------------------------ | --------------- | -------- | ----------------------------------------------------------------------------------------------------------------- |
    | `model`                        | string          | Yes      | Must be `doubao-seedream-5-0-pro-260628`                                                                          |
    | `prompt`                       | string          | Yes      | Image editing or reference-generation instruction. Keep it concise enough that important details are not diluted. |
    | `image`                        | string or array | Yes      | URL, Base64 data URI, or up to 10 references                                                                      |
    | `size`                         | string          | No       | `1K`, `2K`, or explicit pixels                                                                                    |
    | `response_format`              | string          | No       | `url` or `b64_json`                                                                                               |
    | `output_format`                | string          | No       | `png` or `jpeg`                                                                                                   |
    | `watermark`                    | boolean         | No       | Whether to add an AI-generated watermark                                                                          |
    | `optimize_prompt_options.mode` | string          | No       | Prompt optimization mode. Use `standard`; fast mode is not supported.                                             |

    ## Input limits

    Supported formats are `jpeg`, `png`, `webp`, `bmp`, `tiff`, `gif`, `heic`, and `heif`. Each image must be no larger than 30 MB, have an aspect ratio in `[1/16, 16]`, dimensions of at least 14 px, and no more than 36,000,000 total pixels.
  </Tab>
</Tabs>

## Size notes

Use `1K` or `2K` resolution tiers and describe the desired aspect ratio in the prompt, or pass an explicit `widthxheight` value such as `2048x1024`. Explicit dimensions must have a total pixel count from `1280x720` through `2048x2048x1.1025` and an aspect ratio in `[1/16, 16]`.

<Note>When `response_format` is `url`, the returned URL is temporary. Save the generated image promptly.</Note>

<Card title="API Reference" icon="code" href="/api-reference/model-api/bytedance/doubao-seedream-5-0-pro-260628">View both Seedream 5.0 Pro workflows.</Card>

<script src="/public/feedback.js" />