The more descriptive you are, the better the results. However, Google says it works best with backgrounds and objects, not people—there are safeguards in place to make sure you’re not changing someone’s appearance. It’s similar to Samsung’s Sketch to Image feature on its latest foldable phones, except Samsung asks you to sketch what you want to see instead of using text.
Reimagine isn’t perfect—sometimes it didn’t produce results with what I typed, and sometimes the results were just plain wrong. But you have four results to choose from, and you can always try again and be more descriptive.
Autoframe
Photo: Joel Chokkattu
Composition matters a lot in photography, and if adding grid lines in your camera app doesn’t assist you get the shot you want (yes, most smartphone cameras offer this feature in the camera settings), Google thinks it’s another task that AI can assist with.
Autoframe works in Magic Editor similarly to Reimagine. When you edit a photo, you’ll see the Autoframe option. Tap it and it will generate four images with different frames. For example, I intentionally took a photo where I was standing very close to the edge of the frame. Not great composition-wise! I used Autoframe and it generated pixels above and to the right of me, moving me closer to the center, following the classic rule of thirds. It even gave me a vertical crop of the originally horizontal photo.
These “generated pixels” essentially understand the context of the photo and extend the edges of the frame so that it looks natural, even if it’s artificial. In the photos I tested it on, it didn’t know how much of the tree was really to my left or how far the fence was, so it made some assumptions. If you look closely, you’ll probably find a few errors, but most people would never notice the difference.
Zoom Enhance is finally here
Photo: Joel Chokkattu