Close Menu
  • Home
  • AI
  • Art & Style
  • Economy
  • Entertainment
  • International
  • Market
  • Opinion
  • Politics
  • Sports
  • Trump
  • US
  • World
What's Hot

Toto Wolff says Mercedes’ F1 rivals who question the legality of new engine need to get a home for the 2026 F1 season | F1 News

February 2, 2026

Bitcoin temporarily falls below key break-even level for crypto companies, causing strategy setback

February 2, 2026

5 things to know before the stock market opens on Monday

February 2, 2026
Facebook X (Twitter) Instagram
WhistleBuzz – Smart News on AI, Business, Politics & Global Trends
Facebook X (Twitter) Instagram
  • Home
  • AI
  • Art & Style
  • Economy
  • Entertainment
  • International
  • Market
  • Opinion
  • Politics
  • Sports
  • Trump
  • US
  • World
WhistleBuzz – Smart News on AI, Business, Politics & Global Trends
Home » Mixup is a new Mad Libs-style app for creating AI images from photos, text, and doodles
AI

Mixup is a new Mad Libs-style app for creating AI images from photos, text, and doodles

Editor-In-ChiefBy Editor-In-ChiefNovember 21, 2025No Comments4 Mins Read
Share Facebook Twitter Pinterest LinkedIn Tumblr Telegram Email Copy Link
Follow Us
Google News Flipboard
Share
Facebook Twitter LinkedIn Pinterest Email


The team of former Googlers behind the 3D design app Rooms from Things, Inc. has announced their latest project: a playful AI photo editor called Mixup. The iOS-only app allows anyone to create new AI-generated photos using “recipes.” Recipes are like Mad Libs-style fill-in-the-blank prompts for photos, text, or sketches.

For example, you can have Mixup turn a scribbled sketch into a beautiful Renaissance painting or reimagine your pet in a funny Halloween costume. You can also create something even more ridiculous, such as using a selfie to see how you would look with a different hairstyle or imagining your friend transformed into an Italian brain rotten figure.

Image credit: mixup

The app is built on top of Google’s Nano Banana, but the “recipe” format opens up new ways to interact with the model and turns the generation tool into an online party game.

“What[Nano Banana]can do that no previous model has been able to do is take an image of the user and maintain it in a convincing, non-creepy way,” said Jason Toff, founder and CEO of Things, Inc. His background also includes time spent working on experimental apps within Big Tech companies like Google and Meta, and in product management at Twitter.

But what makes Mixup especially fun to use is that the app’s “recipes” (user-generated AI prompts) can be shared.

Image credit: mixup

“Generative AI is very powerful, but most of the time, when you access these tools, this is a text box. Come up with something creative. So what are you going to write?” Tov said of the shortcomings his team sees in the current AI environment.

“So you don’t have to be creative and think about what to create, you just fill in the blanks when you see something that works,” he said.

Image credit: mixup

After users create a new prompt in Mixup, they can choose to publish it to a public feed along with a photo of the results, or download it for personal use. Other users can see the photo from your feed and tap the Try Recipe button next to it. This allows anyone on the app to reuse recipes and generate images using their own photos, text, or doodles. (The latter can be created using a simple drawing feature within the app.)

The team believes that viewing photos alongside the recipes that created them can also help address the unpredictable nature of generated AI images.

“Another problem[with generative AI]is what we internally call the ‘slot machine’ problem, where you press a button and something comes out, and you press it again and something else comes out, and you don’t feel like you’re in control of the output,” Toff explained.

Image credit: mixup

But with Mixup, users can see both the photo and the prompt that created it in one place, so they know what the output will be. If the author chooses to leave this setting on, they can also toggle the button to display both the before and after images.

Additionally, similar to OpenAI’s AI video app Sora, users can upload their own photos to Mixup to be used in AI images. If you choose to do so, anyone you follow within the app can create an AI image with your likeness. This is a feature called “mixable.”

The company envisions groups of friends following each other to take advantage of the feature, but it’s also possible that a creator class will emerge on the platform if they don’t mind seeing themselves mashed up in bizarre ways. (Of course, if you don’t want your image public, just upload it or don’t follow anyone.)

Image credit: mixup

The app also uses OpenAI technology to address some of the expected moderation issues with AI images, but Toff admits that Mixup also relies heavily on Google’s built-in controls within the image model to limit things like sexual content and violence.

At the time of release, Mixup is optimized for iOS 26, but is supported on iOS 18 and later. If things go well, a web version and Android app may be added at a later date.

Free users receive 100 credits (equivalent to $4). An image, on the other hand, costs nearly 4 cents to produce. Once credits are exhausted, users can subscribe to different tiers offering 100, 250, or 500 credits per month.

The app will be available worldwide on November 21 at midnight on the App Store, but you’ll need an invitation to access it. TechCrunch readers can access using code TCHCRH (while code runs out). Mixup is available for pre-order ahead of release.

This post was updated after publication to note that the app’s release date is now November 21st, rather than the previously mentioned November 20th.



Source link

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
Editor-In-Chief
  • Website

Related Posts

Linq raises $20 million to bring AI assistants inside messaging apps

February 2, 2026

These AI note-taking devices help you record and transcribe meetings

February 2, 2026

AI staff reduction or “AI cleaning”? |Tech Crunch

February 1, 2026
Add A Comment

Comments are closed.

News

President Trump on how Balochistan attack threatens Pakistan’s commitments to China | Conflict News

By Editor-In-ChiefFebruary 2, 2026

ISLAMABAD, Pakistan – During a meeting with U.S. President Donald Trump in the Oval Office…

Cuba denies accusations of security threat as US increases pressure | Political News

February 2, 2026

President Trump to close Kennedy Center for renovations following backlash from performers | 2020 Donald Trump News

February 1, 2026
Top Trending

Linq raises $20 million to bring AI assistants inside messaging apps

By Editor-In-ChiefFebruary 2, 2026

In some cases, you may have a hot product but don’t know…

These AI note-taking devices help you record and transcribe meetings

By Editor-In-ChiefFebruary 2, 2026

Digital meeting note-taking tools like Read AI, Fireflies.ai, Fathom, and Granola can…

AI staff reduction or “AI cleaning”? |Tech Crunch

By Editor-In-ChiefFebruary 1, 2026

How many of the companies that have recently made layoffs have truly…

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Welcome to WhistleBuzz.com (“we,” “our,” or “us”). Your privacy is important to us. This Privacy Policy explains how we collect, use, disclose, and safeguard your information when you visit our website https://whistlebuzz.com/ (the “Site”). Please read this policy carefully to understand our views and practices regarding your personal data and how we will treat it.

Facebook X (Twitter) Instagram Pinterest YouTube

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Facebook X (Twitter) Instagram Pinterest
  • Home
  • Advertise With Us
  • Contact US
  • DMCA Policy
  • Privacy Policy
  • Terms & Conditions
  • About US
© 2026 whistlebuzz. Designed by whistlebuzz.

Type above and press Enter to search. Press Esc to cancel.