{"id":393141,"date":"2025-11-20T21:47:20","date_gmt":"2025-11-20T21:47:20","guid":{"rendered":"https:\/\/www.europesays.com\/us\/393141\/"},"modified":"2025-11-20T21:47:20","modified_gmt":"2025-11-20T21:47:20","slug":"mixup-is-a-new-mad-libs-style-app-for-creating-ai-images-from-photos-text-and-doodles","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/us\/393141\/","title":{"rendered":"Mixup is a new, Mad Libs-style app for creating AI images from photos, text, and doodles"},"content":{"rendered":"

The ex-Googler team behind the 3D design app Rooms<\/a> from Things, Inc.<\/a> is out with its latest project: a playful AI photo editor called Mixup<\/a>. The iOS-only app lets anyone create new AI-generated photos using \u201crecipes,\u201d which are like Mad Lib-style, fill-in-the-blank prompts for your photos, texts, or sketches.<\/p>\n

For instance, you could ask Mixup<\/a> to turn your scribbled sketch into a beautiful Renaissance painting, or to reimagine your pet in a funny Halloween costume. You could use a selfie to see what you\u2019d look like with a different hairstyle, or create something even sillier \u2014 like envisioning a friend transformed into the form of Italian brainrot<\/a>.<\/p>\n

\"\"Image Credits:<\/strong>Mixup<\/p>\n

The app is built on top of Google\u2019s Nano Banana, but the \u201crecipe\u201d format opens up a new way to interact with the model \u2014 turning a generative tool into an online party game.<\/p>\n

\u201cThe thing that [Nano Banana] did that no model did before was that it could take your image and maintain it in a convincing way that wasn\u2019t creepy,\u201d said Things, Inc. founder and CEO Jason Toff<\/a>, whose background includes working on experimental apps inside Big Tech companies like Google and Meta, as well as time spent managing product at Twitter.<\/p>\n

But what makes Mixup particularly fun to use is that the app\u2019s \u201crecipes\u201d \u2014 the user-generated AI prompts \u2014 are shareable.<\/p>\n

\"\"Image Credits:<\/strong>Mixup<\/p>\n

\u201cGenerative AI is so powerful, and yet most of the time you go to these tools and it\u2019s like, here\u2019s your text box \u2014 come up with something creative. And what do you write?\u201d Toff said, speaking to the shortcomings his team saw with the current AI landscape.<\/p>\n

\u201cAnd so, rather than having to be creative and think about what to create, you see something that worked, and you can just fill in the blanks,\u201d he said.<\/p>\n

\"\"Image Credits:<\/strong>Mixup<\/p>\n

After users create a new prompt in Mixup, they can choose to publish it along with the resulting photo to a public feed or just download it for personal use. From the feed, other users can view the photo and tap the button next to it to \u201cTry recipe.\u201d This allows anyone on the app to reuse the recipe to generate an image using their own photo, text, or doodles. (The latter can be made via a simple, in-app drawing feature.) <\/p>\n

Seeing a photo alongside the recipe that created it can also help address the unpredictable nature of generative AI images, the team believes.<\/p>\n

\u201cAnother problem [with generative AI] is what we were referring to internally as a \u2018slot machine\u2019 problem, where you push the button, something comes out, you push it again, something different comes out, and you don\u2019t feel like you have control over the output,\u201d Toff explained. <\/p>\n

\"\"Image Credits:<\/strong>Mixup<\/p>\n

In Mixup, however, users can see both the photo and the prompt that created it in one place, giving them an idea of what their output would look like. They can also toggle a button to see both the before and after image, if the creator opts to leave this setting on.<\/p>\n

Plus, similar to OpenAI\u2019s AI video app Sora, users can upload their own photos to Mixup to use in their AI images. If you choose to do so, then any person you follow in the app can also create AI images with your likeness \u2014 a feature it calls \u201cmixables.\u201d <\/p>\n

The company imagines that groups of friends would follow each other to take advantage of the feature, but a creator class could also potentially emerge on the platform \u2014 if they don\u2019t mind seeing themselves mashed up in bizarre ways. (Of course, if you don\u2019t want your image out there, either don\u2019t upload it or don\u2019t follow anyone.)<\/p>\n

\"\"Image Credits:<\/strong>Mixup<\/p>\n

The app also uses OpenAI technology to handle some of the expected moderation concerns around AI imagery, but Toff admits that Mixup also leans heavily on Google\u2019s built-in controls within its image model to restrict things like sexual content or violence. <\/p>\n

At launch, Mixup is optimized for iOS 26 but is supported on iOS 18 and up. If it takes off, a web version or Android app may be added later.<\/p>\n

Free users receive 100 credits, which equates to $4. Meanwhile, images cost nearly 4 cents to produce. When the credits run out, users can subscribe to different tiers offering 100, 250, or 500 credits per month.<\/p>\n

The app launches at midnight on November 21 on the App Store globally but will require an invite to get in. Mixup is available for preorder ahead of its launch.<\/p>\n<\/p>\n

This post was updated after publication to note the app launches Nov. 21, not Nov. 20 as previously stated. <\/p>\n","protected":false},"excerpt":{"rendered":"The ex-Googler team behind the 3D design app Rooms from Things, Inc. is out with its latest project:…\n","protected":false},"author":3,"featured_media":393142,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[21],"tags":[691,186799,738,92746,158,67,132,68],"class_list":{"0":"post-393141","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-ai-image-generator","10":"tag-artificial-intelligence","11":"tag-nano-banana","12":"tag-technology","13":"tag-united-states","14":"tag-unitedstates","15":"tag-us"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@us\/115584228092795203","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/posts\/393141","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/comments?post=393141"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/posts\/393141\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/media\/393142"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/media?parent=393141"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/categories?post=393141"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/tags?post=393141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}