Mixup Launches as Playful AI Photo Editor with Mad Lib‑Style Prompts
Key Points
- Mixup is an iOS‑only AI photo editor that uses "recipe" prompts to generate images.
- Built on Google’s Nano Banana model and supplemented with OpenAI moderation tools.
- Users can share recipes and results on a public feed, allowing others to remix them.
- The "mixables" feature lets friends create AI versions of each other’s uploaded photos.
- Free tier provides 100 credits; subscription plans offer additional credits for a fee.
- Optimized for iOS 26, compatible with iOS 18 and newer; future platforms may be added.
Mixup, the new iOS‑only AI photo editor from the ex‑Google team behind Rooms, lets users generate images using "recipes"—fill‑in‑the‑blank prompts that combine photos, text, or sketches. Built on Google’s Nano Banana model and supplemented with OpenAI moderation tools, the app offers a social feed where creators share prompts and results. Users receive free credits at launch and can subscribe for additional usage. Mixup emphasizes control over generative output, a public feed for remixing, and a feature called "mixables" that lets friends create AI versions of each other’s likenesses.
Overview
Mixup is a newly released iOS‑only application that blends generative AI with a social, game‑like experience. Developed by the team that previously built the 3D design app Rooms at Things, Inc., the app introduces "recipes"—Mad Lib‑style fill‑in‑the‑blank prompts that let users transform selfies, sketches, or text into AI‑generated images. The approach aims to simplify the creative process for users who may find traditional text‑only prompts intimidating.
Core Technology
The underlying image model is Google’s Nano Banana, which the developers cite for its ability to preserve a source image in a convincing manner without producing unsettling results. To address moderation concerns, Mixup also integrates OpenAI’s moderation technology and relies on Google’s built‑in controls to limit sexual content and violence.
Key Features
• Recipe‑Based Prompts: Users select a recipe template, fill in blanks with their own words, and apply the prompt to a photo, text, or doodle. Example recipes let a sketch become a Renaissance‑style painting or a pet appear in a Halloween costume.
• Public Feed and Remixing: After generating an image, creators can publish the result and the associated recipe to a public feed. Other users can tap a "Try recipe" button to apply the same prompt to their own inputs, fostering a collaborative remix culture.
• Before‑After Toggle: When enabled by the creator, a toggle lets viewers compare the original input with the AI‑generated output.
• Mixables: Users who upload their own photos enable friends and followers to generate AI versions of their likenesses, encouraging social interaction and potential creator communities.
Business Model
Mixup launches with a free tier that provides 100 credits, equivalent to a modest monetary value. When credits are exhausted, users may subscribe to plans offering 100, 250, or 500 credits per month. The pricing structure reflects the cost of generating each image, which the source notes as roughly four cents per image.
Platform Availability
The app is optimized for iOS 26 but supports iOS 18 and newer devices. While the initial release is iOS‑only, the developers have hinted at possible future expansion to web or Android platforms.
Launch Details
Mixup became available globally on the App Store at midnight, requiring an invitation for access. Early adopters could use a promotional code to obtain entry before the invitation pool ran out.