Meta has just unveiled a beta version of an image segmentation tool that will be useful not only for amateur photo editors, but also for scientists, journalists, advertisers, and everyone else.

Meta’s Segment Anything Model (SAM) analyzes an image and uses an AI-based algorithm to split it into different parts. This goes beyond something like Google’s Magic Eraser, as SAM splits up the entire image, pixel by pixel, to create accurate segmentation models. This means you can identify and remove any object from a photo, from an annoying person in the background to something tiny in the foreground.

The model was trained on a dataset of over a billion images and image parts, the largest ever for this type of editing tool. There’s a demo you can try out for yourself and a full version available for download, though the latter is only available for research purposes (for now). The algorithm identifies different objects in a photo, and then you click to choose which ones you want to remove. Eventually, the company says it will pair this technology with AI-powered language prompts, so you can tell the tool something like, “Get rid of that stapler,” for example.

This isn't just a photo editing tool, as the technology can easily be applied to video. However, Meta says it'll be a while before we can try out that particular aspect of the model.