---
title: "Seedream V4.5 - Expand image"
method: POST
path: "/v1/ai/image-expand/seedream-v4-5"
tags: ["image-expand"]
---

# Seedream V4.5 - Expand image

`POST /v1/ai/image-expand/seedream-v4-5`

## Request

- Base URL: `https://api.magnific.com`
- URL: `https://api.magnific.com/v1/ai/image-expand/seedream-v4-5`
- Auth: API key in header `x-magnific-api-key`

This endpoint allows you to expand an image using the Seedream V4.5 AI model. The image will be expanded based on the provided pixel values for each side.
If no prompt is provided, the model will auto-generate one based on the image content.

### Output size

The requested canvas is `input_width + left + right` by
`input_height + top + bottom`, and this model constrains it in two ways:

1. **Each side is rounded up to the next multiple of 16.**
2. **The canvas must contain between 3,686,400 and 16,777,216 pixels.** A
   smaller canvas is scaled **up** to reach the lower bound, and a larger one
   is scaled down to the upper bound. Since the lower bound is close to 3.7
   megapixels, a small input with a small expansion is upscaled — a 896x672
   image expanded by 100px on each edge asks for a 1096x872 canvas and comes
   back at 2160x1728, close to twice the requested dimensions (measured).

If you need the output to stay close to the pixel values you requested, use
`POST /v1/ai/image-expand/flux-pro`, which only deviates by the rounding to 16
while the result stays under 1.6 megapixels. For exact dimensions, resize the
result yourself after generation.

`left`, `right`, `top` and `bottom` are all required, and at least one of them
must be greater than `0`.

## Request body

- ImageExpandSeedreamV45Request
  - `webhook_url` string, uri: Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field.
  - `image` string, required: Image to expand. Accepts an HTTPS URL or a Base64-encoded image (max 10MB).
  - `prompt` string: Optional text prompt describing the desired expanded content. If not provided, the AI model will auto-generate a prompt based on the image.
  - `left` integer, required: Number of pixels to expand on the left side
  - `right` integer, required: Number of pixels to expand on the right side
  - `top` integer, required: Number of pixels to expand on the top side
  - `bottom` integer, required: Number of pixels to expand on the bottom side
  - `seed` integer: Optional seed for reproducibility

## Response `200`

OK - The task exists and the status is returned

- InlineObject4
  - `data` TaskDetail1, required
    - `task_id` string, uuid, required: Task identifier
    - `status` 'CREATED' | 'IN_PROGRESS' | 'COMPLETED' | 'FAILED', required: Task status
    - `generated` string[], required

## Other responses

- `400`: Bad Request - The server could not understand the request due to invalid syntax.
- `401`: Unauthorized - The client must authenticate itself to get the requested response.
- `500`: Internal Server Error - The server has encountered a situation it doesn't know how to handle.
- `503`: Service Unavailable

---

[API](https://skmtc.dev/magnific/apis/magnific-api.md) · [All operations](https://skmtc.dev/magnific/apis/magnific-api/llms.txt) · [OpenAPI document](https://skmtc.dev/magnific/apis/magnific-api/revisions/60711fb082c7?raw)