Create image from text - Magnific One
Generate images with Magnific One, Magnific's image model with art direction built in: from a prompt, it develops the composition, style, lighting and visual treatment before rendering.
Modes:
- quality (default): one finished image, with selectable quality and resolution (up to 4k)
- draft: a contact sheet of quick variations, returned as 8 or 16 individual images — explore directions, then render the chosen one in quality mode
Key Features:
- Art direction from a short prompt
- Optional style reference images (up to 10), in both modes
- 10 aspect ratios, from 21:9 to 9:16
Output: the task's generated array holds one image URL in quality mode, or 8 or 16 URLs (one per individual image) in draft mode.
Credits: a quality request is billed once, at the price of its quality and resolution. A draft request is billed once for the whole sheet, at the medium / 2k price, never per image. Reference images do not change the price.
The request is processed asynchronously: the endpoint returns a task id immediately. Retrieve the result by polling the task endpoint or by providing an optional webhook_url.
Request
- Base URL: https://api.magnific.com
- URL: https://api.magnific.com/v1/ai/magnific-one
- Auth: API key in header x-magnific-api-key
Request body
Example request
{
"prompt": "A lighthouse on a cliff at dusk",
"mode": "quality",
"aspect_ratio": "1:1",
"quality": "high",
"resolution": "2k",
"tiles": 8,
"reference_images": [
"https://example.com/reference.jpg"
],
"webhook_url": "https://www.example.com/webhook"
}Response
OK - The request has succeeded and the Magnific One process has started.
Example response
{
"data": {
"generated": [
"https://openapi-generator.tech",
"https://openapi-generator.tech"
],
"task_id": "046b6c7f-0b8a-43b9-b35d-6489e6daee91",
"status": "CREATED"
}
}Changes
No recorded changes to this operation across all 1 revision of this API.