Generations of Image Playground is much more impressive this year.
Credit: David Nield/Lifehacker
among all others Artificial intelligence upgrade As Apple rolls out to us this year, you’ll notice a significant jump in Image Playground’s AI image generation capabilities. Before now, the output of the application were rather limited In terms of size, style and possible indications. It was very AI images for beginners, with the results mostly basic and generic.
With iOS 27, iPadOS 27 and macOS 27, that’s changing. You can try the developer beta now (however You probably shouldn’t; Public betas are coming in July, and Apple says the full release will appear later in the year (most likely around September). Image generation is something that both ChatGPT and Gemini have been doing Continuous improvementTo the point where some generations are hard to distinguish from real photos. So how does Apple’s new and improved Image Playground compare?
Here’s what Image Playground can do now
Open Image Playground on the latest versions of iOS, iPadOS, or macOS and you’ll notice that there are tons of new capabilities. First, you can ask for photorealistic images in the prompt box, as well as previously possible sketches and pictures: ask for a photo of an English meadow or a huge temple, and the image playground will be obligatory.
Also have more control over your images. You can submit a photo as part of the initial prompt, and you can choose between square, portrait, and landscape orientations for your picture—these options weren’t available before. If you want to take your pet dog into the forest, it is now possible.
Image Playground can now work with existing images.
Credit: Lifehacker
Then there are clever editing tools like that Google’s Nano Banana AI Modelwhich allows you to change specific parts of the generated image without completely re-rendering it. You can use the follow-up prompt to request changes and even highlight the part of the picture you want to edit.
You can now change the color of things, remove things altogether, change the weather of a scene, anything you can think of really. Based on my testing, it all works well, and produces results that look impressive and consistent. I managed to put a cartoon-style cat on the street, and then change the color of the cat without affecting the background.
You can use follow-up hints to make edits.
Credit: Lifehacker
Apple says that everything created by Image Playground will have the same SynthID watermark as generations of Google Gemini and ChatGPT, and we know because of private cloud computing that no user images will be stored or accessed by Apple, or used to train any of its models.
Finally, you can do even more with these images – by setting them As contact posters Or wallpaper for the lock screen, for example. You can find more AI image tools in the Photos app, where you can apply edits possible in Image Playground to anything in your photo library.
What do you think so far?
Competition versus image playground
Image Playground is better – no doubt about it Rising from Gemini—but still, the images are not up to the very high bar that Gemini and ChatGPT now set. You can see below how my request for “a photorealistic image of a small, ancient-looking spaceship floating among the stars, with an Earth-like planet behind it” was interpreted by Image Playground (left), Gemini (center), and ChatGPT (right).
Spaceship AI Challenge.
Credit: Image Playground / Gemini / ChatGPT
Apple does OK, but to me, Gemini and ChatGPT generate results that are more immersive and detailed—like something you’d see in an actual science fiction movie. There’s more detail and more imagination, though to Apple’s credit, Image Playground renders the fastest.
For the next challenge, I tried asking these AI tools to “move my cuddly toy from my floor to a pebble beach, with the tide lapping at its edge.” Again, all of these efforts are good, but Gemini (center) and ChatGPT (right) add additional layers of similarity in terms of color, angle, and texture (although Gemini appears to have created two edges).
Toy on the beach challenge.
Credit: Image Playground / Gemini / ChatGPT
I asked all three models to put away the toy and just leave the beach, and they all managed it more or less perfectly. These are Photoshop-level edits that used to take me hours, but can now be done in seconds. It is really impressive. Gemini and ChatGPT still have the edge in terms of quality, but the image playground is built into billions of Apple devices. Now it’s so good that many users would prefer not to switch to something else when they need to generate images with AI, which can make all the difference.
