The team behind the 3D design app Rooms, a group of former Googlers from Things Inc., has introduced a new project. It is a playful AI photo editor for iOS called Mixup. This app allows anyone to create new AI-generated photos using a system of “recipes.” These recipes function like Mad Libs, providing fill-in-the-blank prompts for your own photos, text, or sketches.
For example, you could use Mixup to transform a simple scribble into a beautiful Renaissance painting. You could reimagine your pet in a funny Halloween costume. A selfie could be used to see how you would look with a different hairstyle, or you could create something entirely silly, like envisioning a friend transformed into the form of Italian brainrot.
The app is built on Google’s Nano Banana technology. The recipe format introduces a new way to interact with the model, turning a generative tool into an online party game. The founder and CEO of Things Inc., Jason Toff, noted that Nano Banana’s unique ability was to take a user’s image and maintain it in a convincing way that was not creepy. His background includes work on experimental apps at companies like Google and Meta, as well as product management at Twitter.
What makes Mixup particularly fun is that its user-generated AI prompts, the recipes, are shareable. Toff explained that while generative AI is powerful, most tools simply present a text box and expect the user to be creative. With Mixup, instead of having to think of what to create, you can see something that worked and just fill in the blanks.
After creating a new prompt in Mixup, users can publish it along with the resulting photo to a public feed or download it for personal use. From the feed, other users can view the photo and tap a button to “Try recipe.” This allows anyone to reuse the recipe to generate an image using their own photo, text, or doodles, which can be made with a simple in-app drawing feature.
The team believes that seeing a photo alongside the recipe that created it helps address the unpredictable nature of generative AI. Toff referred to this unpredictability as a “slot machine” problem, where you push a button and get a random output without feeling in control. In Mixup, users see both the final photo and the prompt in one place, giving them an idea of what their own output might look like. They can also toggle a button to see the before and after image, if the creator has left that setting on.
Similar to other AI apps, users can upload their own photos to Mixup for use in AI images. If you do this, any person you follow in the app can also create AI images with your likeness, a feature called “mixables.” The company imagines groups of friends would follow each other to use this feature, but a creator class could also emerge on the platform, provided they do not mind seeing themselves mashed up in bizarre ways. If you do not want your image used, you can choose not to upload it or not to follow anyone.
The app uses OpenAI technology to handle some moderation concerns around AI imagery. Toff also stated that Mixup leans heavily on Google’s built-in controls within its image model to restrict content like sexual material or violence.
At launch, Mixup is optimized for iOS 26 but is supported on iOS 18 and up. If the app becomes popular, a web version or Android app may be added later. Free users receive 100 credits, which is equivalent to four dollars. Each image costs nearly four cents to produce. When credits run out, users can subscribe to different tiers offering 100, 250, or 500 credits per month.
The app launches at midnight on November 21 on the App Store globally, but it will require an invite to access. Mixup is available for preorder ahead of its launch.