Reframe
Reframe intelligently adjusts image aspect ratios using AI-powered content analysis. The model analyzes your image and automatically decides whether to expand (outpaint/zoom-out) or crop (zoom-in) to reach the target aspect ratio while preserving important content.
- Model Name:
reframe - Lifecycle: experimental
- Processing Time: 12 seconds
- Maximum Resolution: ~1MP (see full list below)
- Credits: 1
Request
Reframe images by submitting the source image and target aspect ratio to the universal /v1/run endpoint:
Request Parameters
imageRequiredimage URL | base64
Source image to reframe to a new aspect ratio. The AI analyzes the image content and intelligently decides whether to expand or crop based on subject position, content density, and edge details.
Output resolution is limited to ~1MP. If your image is already at or above this size, it will be downsampled so that, after reframing, the final result fits within the 1MP limit.
Base64 images must include the proper prefix (e.g., data:image/jpg;base64,<YOUR_BASE64>)
aspect_ratioRequired'21:9' | '1:1' | '4:3' | '3:2' | '2:3' | '5:4' | '4:5' | '3:4' | '16:9' | '9:16'
Target aspect ratio for the reframed image. The AI determines whether expansion or cropping is more appropriate based on the current image content and dimensions.
num_imagesinteger
Number of images to generate in a single run. Image generation has a random element, so generating multiple images increases the chances of getting a good result.
Default: 1
Range: 1 to 4
seedinteger
Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results.
Default: 42
Range: 0 to 2^32 - 1
output_format'png' | 'jpeg'
Specifies the output image format.
-png: Delivers the highest quality image, ideal for use cases such as content creation where quality is paramount.
-jpeg: Provides a faster response with a slightly compressed image, more suitable for real-time applications.
Default: png
return_base64boolean
When set to true, the API will return the generated image as a base64-encoded string instead of a CDN URL. The base64 string will be prefixed according to the output_format (e.g., data:image/png;base64,... or data:image/jpeg;base64,...).
This option offers enhanced privacy as user-generated outputs are not stored on our servers when return_base64 is enabled.
Default: false
Response Polling
After submitting your request, poll the status endpoint using the returned prediction ID. See API Fundamentals for complete polling details.
Successful Response
When your reframe operation completes successfully, the status endpoint will return:
The output array contains URLs to your reframed images, adjusted to the target aspect ratio.
Runtime Errors
Reframe shares the common runtime errors in Error Handling.
In addition, Reframe may return:
| Error | Description |
|---|---|
InputValidationError | Image already matches target aspect ratio |
Related Guides
For detailed implementation guidance and best practices:
- Image Preprocessing Best Practices - Optimize your source images for reframing operations