Upscale an image with Magnific
This asynchronous endpoint enables image upscaling using advanced AI algorithms. Upon submission, it returns a unique task_id
which can be used to track the progress of the upscaling process. For real-time production use, include the optional webhook_url
parameter to receive an automated notification once the task has been completed. This allows for seamless integration and efficient task management without the need for continuous polling.
Important
For a comprehensive guide on this service, including use cases and detailed functionality, check out our Image Upscaler Guide.
Request
Authorizations
Your Freepik API key. Required for authentication. Learn how to obtain an API key
Headers
The Content-Type
header must be set to application/json
to indicate that the payload is formatted as JSON.
If a different Content-Type
is provided, the payload will be ignored, and the request will proceed without
processing the body.
Body
Base64 image to upscale The resulted image can't exceed maximum allowed size of 25.3 million pixels.
Webhook URL to receive the upscaled image once it's ready
Configure scale factor of the image. For higher scales, the image will take longer to process
2x
, 4x
, 8x
, 16x
Styles to optimize the upscale process
standard
, soft_portraits
, hard_portraits
, art_n_illustration
, videogame_assets
, nature_n_landscapes
, films_n_photography
, 3d_renders
, science_fiction_n_horror
Prompt to guide the upscale process. Reusing the same prompt for AI-generated images will improve the results
Increase or decrease AI's creativity.
Valid values range [-10, 10]
, default 0
.
-10 < x < 10
Increase or decrease the level of definition and detail.
Valid values range [-10, 10]
, default 0
.
-10 < x < 10
Adjust the level of resemblance to the original image.
Valid values range [-10, 10]
, default 0
.
-10 < x < 10
Control the strength of the prompt and intricacy per square pixel.
Valid values range [-10, 10]
, default 0
.
-10 < x < 10
Magnific model engines
automatic
, magnific_illusio
, magnific_sharpy
, magnific_sparkle
Response
Was this page helpful?