Google Photos to gain a new ‘Magic Editor’ feature powered by generative AI

Google Photos is expanding its use of AI to help users edit and enhance their photos. While the company has already leveraged AI for its tools like the distraction-removing Magic Eraser and Photo Unblur’s remedial features in Photos, it’s now turning to AI for more complex edits with the introduction of Magic Editor. The new tool will combine AI techniques, including generative AI, to edit and reimagine photos, Google says.

The company offered a sneak peek at the new experimental feature at this week’s Google I/O developer conference to show off its capabilities.

With Magic Editor, users will be able to make edits to specific parts of photos, such as the foreground or background, as well as fill in gaps in the photo or even reposition the subject for a better framed shot.

For example, Googe showed how the Magic Editor could be used to enhance a photograph of a person in front of a waterfall.

In a demonstration of the technology, a user can first remove other people from the background of the photo and then remove a bag strap from the subject’s shoulder for a cleaner look. While these types of edits were previously available in Google Photos via Magic Eraser, the ability to reposition the subject is new. Here, the AI ​​“crops” the subject in the foreground of the photo, allowing the user to reposition the person elsewhere in the photo by dragging and dropping.

Image credits: Google

This is similar to the image cropping feature that Apple introduced with iOS 16 last year, which could also isolate the subject from the rest of the photo to do things like copy and paste part of the image into another app , take the subject of the images. found through Safari search or place the photo theme in front of the clock on the iOS lock screen, among other things.

In Google Photos, however, the feature is meant to help users create better photos.

Another demo showed how Magic Editor’s ability to reposition a subject could also be combined with its ability to fill in gaps in an image using AI techniques.

In this example, a child is sitting on a bench with a bunch of balloons, but the bench is moved to the left side of the photo. Magic Editor lets you zoom in on the boy and bench in the center of the photo, and as it does so, it uses generative AI to create more bench and the balloons to fill the rest of the photo. As a final touch, you can lighten the sky behind the photo to a brighter blue with fluffy white clouds, instead of the gray, overcast sky of the original.

Image credits: Google

The sky fill feature is similar to what several other photo editing apps can do, like Lensa or Lightricks’ Photoleap to name a couple. But in this case, it’s bundled with users’ primary photo organizer app, rather than requiring an additional download of a third-party tool.

The result of the edits, at least in the demos, is that of natural-looking and well-composed images, not ones that look like they’ve been heavily edited or created with AI, necessarily.

Google says it will release Magic Editor as an experimental feature later this year, warning that there will be times when it won’t work properly. User testing and feedback will help the feature improve over time, as users now edit 1.7 billion photos each month with Google Photos, the company said.

It’s unclear whether Google will eventually charge for this feature, or perhaps make it a Pixel exclusive. Possibly, it will turn Magic Editor into a Google One subscription benefit, as it did with Magic Eraser earlier this year.

The feature will initially be available to “select” Pixel devices, but Google declined to share which phones will get it first.

The company said it also plans to share more information about the AI ​​technology under the hood closer to the feature’s early access launch, but won’t go into details now.