> ## 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-5.5-pro

> Seedream 5.5 Pro text-to-image, image editing, and transparent image generation API.

Use `seedream-5-5-pro` with the synchronous image generation endpoint. Choose a tab for text-to-image generation, reference-image editing, or transparent image output.

> [!WARNING]
>
> To request transparent output, set `background` to `transparent` and `output_format` to `png`. A request without `background: "transparent"` returns an opaque image.

> [tab] Text to image
>
> ## Create an image
>
> `POST /v1/images/generations`
>
> ```bash cURL theme={null}
> curl --request POST \
>   --url https://www.anyfast.ai/v1/images/generations \
>   --header 'Authorization: Bearer YOUR_API_KEY' \
>   --header 'Content-Type: application/json' \
>   --data '{
>     "model": "seedream-5-5-pro",
>     "prompt": "A lifelike editorial photograph of a ceramic teapot on a wooden table, soft morning window light, fine glaze and wood textures",
>     "size": "1K",
>     "response_format": "url",
>     "output_format": "png",
>     "watermark": false
>   }'
> ```
>
> **model** `string` *required*
>
> Use `seedream-5-5-pro`.
>
> **prompt** `string` *required*
>
> Text prompt for image generation. Describe the subject, composition, style, lighting, materials, and any text to render.
>
> **size** `string`
>
> Accepts `1K`, `1.5K`, and `2K`. The example uses `1K`, which returned `1248x832`.
>
> **response\_format** `string`
>
> Return the generated image as a URL or Base64 data.
>
> **output\_format** `string`
>
> Use `png` or `jpeg`. Both formats were accepted. Use `png` when you need an alpha channel.
>
> **watermark** `boolean`
>
> Whether to add an AI-generated watermark.
>
> ### Create response
>
> ```json 200 theme={null}
> {
>   "model": "dola-seedream-5-5-261028",
>   "created": 1794382953,
>   "data": [
>     {
>       "url": "https://example.com/generated-image.png",
>       "size": "1248x832",
>       "output_format": "png",
>       "background": "opaque"
>     }
>   ],
>   "usage": {
>     "input_images": 0,
>     "generated_images": 1,
>     "output_tokens": 4056,
>     "total_tokens": 4056
>   }
> }
> ```

> [tab] Image editing
>
> ## Edit an image
>
> `POST /v1/images/generations`
>
> ```bash cURL theme={null}
> curl --request POST \
>   --url https://www.anyfast.ai/v1/images/generations \
>   --header 'Authorization: Bearer YOUR_API_KEY' \
>   --header 'Content-Type: application/json' \
>   --data '{
>     "model": "seedream-5-5-pro",
>     "prompt": "Change the blue scarf to forest green. Preserve the subject, pose, background, lighting, and all other details.",
>     "image": "https://example.com/source-image.png",
>     "size": "1K",
>     "response_format": "url",
>     "output_format": "png",
>     "watermark": false
>   }'
> ```
>
> **model** `string` *required*
>
> Use `seedream-5-5-pro`.
>
> **prompt** `string` *required*
>
> Editing instruction. Specify the requested change and the details that should remain unchanged.
>
> **image** `string` *required*
>
> Source image URL for editing.
>
> **size** `string`
>
> Accepts `1K`, `1.5K`, and `2K`. The example uses `1K`, which returned `1248x832`.
>
> **response\_format** `string`
>
> Return the generated image as a URL or Base64 data.
>
> **output\_format** `string`
>
> Use `png` or `jpeg`. Both formats were accepted. Use `png` when you need an alpha channel.
>
> **watermark** `boolean`
>
> Whether to add an AI-generated watermark.
>
> To continue a multi-turn edit, pass the latest output image as the next request's `image` and describe the next focused change.
>
> ### Create response
>
> ```json 200 theme={null}
> {
>   "model": "dola-seedream-5-5-261028",
>   "created": 1794383042,
>   "data": [
>     {
>       "url": "https://example.com/edited-image.png",
>       "size": "1248x832",
>       "output_format": "png",
>       "background": "opaque"
>     }
>   ],
>   "usage": {
>     "input_images": 1,
>     "generated_images": 1,
>     "output_tokens": 4056,
>     "total_tokens": 4056
>   }
> }
> ```

> [tab] Transparent background
>
> ## Generate a transparent image
>
> `POST /v1/images/generations`
>
> ```bash cURL theme={null}
> curl --request POST \
>   --url https://www.anyfast.ai/v1/images/generations \
>   --header 'Authorization: Bearer YOUR_API_KEY' \
>   --header 'Content-Type: application/json' \
>   --data '{
>     "model": "seedream-5-5-pro",
>     "prompt": "A detailed snowy owl in flight, isolated asset, transparent background outside the owl, preserve fine feather edges",
>     "size": "1K",
>     "response_format": "url",
>     "output_format": "png",
>     "background": "transparent",
>     "watermark": false
>   }'
> ```
>
> **model** `string` *required*
>
> Use `seedream-5-5-pro`.
>
> **prompt** `string` *required*
>
> Describe the image and request a transparent background outside the subject.
>
> **size** `string`
>
> Accepts `1K`, `1.5K`, and `2K`. The example uses `1K`, which returned `1248x832`.
>
> **response\_format** `string`
>
> Return the generated image as a URL or Base64 data.
>
> **output\_format** `string` *required*
>
> Use `png` to retain the full and partial transparency in the RGBA output.
>
> **background** `string` *required*
>
> Set to `transparent` for transparent RGBA output. The response reports `opaque` or `transparent`.
>
> ### Create response
>
> ```json 200 theme={null}
> {
>   "model": "dola-seedream-5-5-261028",
>   "created": 1794383006,
>   "data": [
>     {
>       "url": "https://example.com/transparent-image.png",
>       "size": "1248x832",
>       "output_format": "png",
>       "background": "transparent"
>     }
>   ],
>   "usage": {
>     "input_images": 0,
>     "generated_images": 1,
>     "output_tokens": 4056,
>     "total_tokens": 4056
>   }
> }
> ```

## Headers

**Authorization** `string` *required*

Bearer authentication. Use `Bearer YOUR_API_KEY`.

**Content-Type** `string` *required* (default: application/json)

Request body format.

## Response fields

**model** `string`

Model identifier reported in the response. This request returned `dola-seedream-5-5-261028`.

**created** `integer`

Creation time as a Unix timestamp in seconds.

**data** `object[]`

Generated image results.

**data\[].url** `string`

Temporary image URL when `response_format` is `url`.

**data\[].b64\_json** `string`

Base64 image data when `response_format` is `b64_json`.

**data\[].size** `string`

Generated image dimensions.

**data\[].output\_format** `string`

Generated image format.

**data\[].background** `string`

Background mode reported for the generated image: `opaque` or `transparent`.

**usage.generated\_images** `integer`

Number of generated images.

**usage.input\_images** `integer`

Number of input images, when applicable.

**usage.output\_tokens** `integer`

Output token count.

**usage.total\_tokens** `integer`

Total token count.

## Error responses

Error responses use an `error` object with `code`, `message`, and `type` fields.

**error** `object`

Error information.

**error.code** `string`

Machine-readable error code.

**error.message** `string`

Human-readable error message.

**error.type** `string`

Error category.

> [tab] 400
>
> Invalid request or unsupported parameter value.
>
> ```json theme={null}
> { "error": { "code": "invalid_request_error", "message": "Invalid request parameter", "type": "invalid_request_error" } }
> ```

> [tab] 401
>
> Missing or invalid API key.
>
> ```json theme={null}
> { "error": { "code": "unauthorized", "message": "Invalid API key", "type": "authentication_error" } }
> ```

> [tab] 429
>
> Rate limit exceeded.
>
> ```json theme={null}
> { "error": { "code": "rate_limit_exceeded", "message": "Rate limit exceeded", "type": "rate_limit_error" } }
> ```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.