Smart Cropping

Overview

The Image Editing API allows you to automatically crop an image to put the focus on its main subject.

To perform such a smart crop set the parameters:

• removeBackground to false

• outputSize to the desired result size and aspect ratio, for example 2000x2000

• padding to add some breathing room around the subject, for example 10%

• (optional) segmentation.prompt to focus on a specific element of the image, for example product

(original image)	(result image)

If you want to give it a try, here's the code to reproduce the example above:

curl --request POST \
  --url https://image-api.photoroom.com/v2/edit \
  --header 'x-api-key: YOUR_API_KEY_HERE' \
  --form imageFile=@/path/to/image.png \
  --form removeBackground=false \
  --form outputSize=2000x2000 \
  --form padding=10% \
  --form segmentation.prompt=product \
  --output result-smart-crop.png

Try it now!

Examples

(original image)	(result image)

Faceless / Headless Crop

Some marketplaces require on-model imagery to be anonymized: the model's face must be cropped out, just below the nose, so the listing doesn't rely on a recognizable likeness.

To produce a faceless crop, set the parameters:

• removeBackground to false to keep the original background and apply only the crop

• referenceBox to subjectBox to frame the crop relative to the model

• segmentation.mode to ignoreSalientObject so the prompts drive the crop region instead of the most prominent object

• segmentation.prompt to garment,chin,lip,mouth, the parts to keep

• segmentation.negativePrompt to head,nose,eye,forehead, the parts to exclude

• padding to 25px to add a little breathing room around the subject

(original image)	(result image)

If you want to give it a try, here's the code to reproduce the example above:

curl --request POST \
  --url https://image-api.photoroom.com/v2/edit \
  --header 'x-api-key: YOUR_API_KEY_HERE' \
  --form imageFile=@/path/to/image.jpg \
  --form removeBackground=false \
  --form referenceBox=subjectBox \
  --form segmentation.mode=ignoreSalientObject \
  --form 'segmentation.prompt=garment,chin,lip,mouth' \
  --form 'segmentation.negativePrompt=head,nose,eye,forehead' \
  --form padding=25px \
  --output result-faceless-crop.png

Try it now!

Tip: You can chain this with subsequent Image Editing API calls to remove the background, add realistic shadows, or apply further enhancements.