Annotate detections
View API docs →Render bounding boxes and labels onto an image. Accepts the JSON output of any of the detection tools (faces / barcodes / QR / contours / etc.) and produces a visual overlay.
POST
/api/image-annotate-detections·cap 25.0 MiB·2 cost unit(s)More Image manipulation
See all →Auto-orient image
Rotate an image based on its EXIF orientation tag and clear the tag.
Blur faces (privacy)
Detect faces in an image and blur each one in place.
Chroma key (green-screen)
Replace a colour key (typically green or blue) with transparency.
Crop image
Crop an image to a rectangular region.
Deskew (auto-straighten)
Detect and correct skew on a scanned document.
Image add text
Add text to an image with configurable font, size, position, and colour.
Image background removal
Remove a uniform background from an image (colour-based).
Image crop to circle
Crop an image to a circle (transparent corners).
Image face crop
Detect a face and return a tightly-cropped headshot.
Image flip / mirror
Flip an image horizontally, vertically, or both.
Image padding
Add a coloured border / padding around an image.
Image perspective
Detect a rectangular subject in an image and rectify its perspective.
Image perspective warp
Apply a 4-point perspective warp to an image.
Image trim
Crop away uniform-colour borders / padding from an image.
Image watermark
Stamp a text watermark across an image.
Optimize SVG
Minify an SVG: strip metadata, redundant attributes, unused defs, comments.
Overlay images
Composite one image on top of another.
Replace background
Remove a uniform background and replace it with a chosen colour.
Rotate image
Rotate an image by an arbitrary angle.
Strip EXIF (JPEG)
Remove all EXIF and IPTC metadata from an image.
Undistort (lens correction)
Correct lens distortion (barrel / pincushion) in an image.