#270 · Primary category: Computer Vision

magic-copy

chrome-extension computer-vision image-processing

Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard.

Project last updated:05/06/24

GitHub Stars

2.5K

Forks

155

Contributors

2

License

MIT

Why we included this project

Magic Copy is a browser extension that pulls the foreground object out of an image and puts it on your clipboard with one click, using Meta's Segment Anything Model under the hood. You click anywhere on a photo and the extension segments and isolates the subject, ready to paste into a slide, thumbnail, or document. It runs as a Chrome and Firefox add-on and also ships as a Figma plugin, so designers and content editors can use it without leaving their usual tools. No desktop app or account required. If you do not want your images sent to Meta's demo server, the repo includes a simple example of self-hosting the vision transformer that generates the embeddings. It is a narrowly scoped utility rather than a full segmentation framework, and that focus is exactly why it works well for quick everyday editing tasks.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category