Ideogram - Expand image
This endpoint allows you to expand an image using the Ideogram 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
left, right, top and bottom define the aspect ratio of the result,
not its pixel dimensions. The canvas is built as
input_width + left + right by input_height + top + bottom, and the model
then renders it at approximately 1 megapixel, picking the closest match
from its own fixed list of supported resolutions (all multiples of 32). The
pixel values you send are therefore not preserved:
| Requested canvas | Actual output |
|---|---|
| 896x1172 | 832x1088 |
| 1396x672 | 1472x704 |
| 896x896 | 1024x1024 |
| 4992x4768 | 1024x960 |
As the last row shows, a very large expansion does not produce a larger image: it only changes the shape. If you need specific output dimensions, resize the result yourself after generation.
left, right, top and bottom are all required. At least one of them
must be greater than 0, otherwise the request returns a 400; the other
three may be 0.
Authorizations
Your Magnific API key. Required for authentication. Learn how to obtain an API key
Body
Base64 image to expand
Number of pixels to expand on the left side
0 <= x <= 2048Number of pixels to expand on the right side
0 <= x <= 2048Number of pixels to expand on the top side
0 <= x <= 2048Number of pixels to expand on the bottom side
0 <= x <= 2048Optional 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.
"https://www.example.com/webhook"
Optional text prompt describing the desired expanded content. If not provided, the AI model will auto-generate a prompt based on the image.
Optional seed for reproducibility
0 <= x <= 2147483647Response
OK - The task exists and the status is returned