Posted by Matthew McCullough, VP of Product Management, Android Developer

Posted by Rebecca Franks – Developer Relations Engineer, Tracy Agyemang – Product Marketer, and Avneet Singh – Product Manager

Androidify is our new app that lets you build your very own Android bot, using a selfie and AI. We walked you through some of the components earlier this year, and starting today it’s available on the web or as an app on Google Play. In the new Androidify, you can upload a selfie or write a prompt of what you’re looking for, add some accessories, and watch as AI builds your unique bot. Once you’ve had a chance to try it, come back here to learn more about the AI APIs and Android tools we used to create the app. Let’s dive in!

Key technical integrations

The Androidify app combines powerful technologies to deliver a seamless and engaging user experience. Here’s a breakdown of the core components and their roles:

AI with Gemini and Firebase

Androidify leverages the Firebase AI Logic SDK to access Google’s powerful Gemini and Imagen* models. This is crucial for several key features:

The Androidify app also has a “Help me write” feature which uses Gemini 2.5 Flash to create a random description for a bot’s clothing and hairstyle, adding a bit of a fun “I’m feeling lucky” element.

UI with Jetpack Compose and CameraX

The app’s user interface is built entirely with Jetpack Compose, enabling a declarative and responsive design across form factors. The app uses the latest Material 3 Expressive design, which provides delightful and engaging UI elements like new shapes, motion schemes, and custom animations.

For camera functionality, CameraX is used in conjunction with the ML Kit Pose Detection API. This intelligent integration allows the app to automatically detect when a person is in the camera’s view, enabling the capture button and adding visual guides for the user. It also makes the app’s camera features responsive to different device types, including foldables in tabletop mode.

Androidify also makes extensive use of the latest Compose features, such as:

Latest updates

In the latest version of Androidify, we’ve added some new powerful AI driven features.

Background vibe generation with Gemini Image editing

Using the latest Gemini 2.5 Flash Image model, we combine the Android bot with a preset background “vibe” to bring the Android bots to life.

This is achieved by using Firebase AI Logic – passing a prompt for the background vibe, and the input image bitmap of the bot, with instructions to Gemini on how to combine the two together.

override suspend fun generateImageWithEdit(
        image: Bitmap,
        backgroundPrompt: String = "Add the input image android bot as the main subject to the result... with the background that has the following vibe...",
    ): Bitmap {
        val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
            modelName = "gemini-2.5-flash-image-preview",
            generationConfig = generationConfig {
                responseModalities = listOf(
                    ResponseModality.TEXT,
                    ResponseModality.IMAGE,
                )
            },
        )
	  // We combine the backgroundPrompt with the input image which is the Android Bot, to produce the new bot with a background
        val prompt = content {
            text(backgroundPrompt)
            image(image)
        }
        val response = model.generateContent(prompt)
        val image = response.candidates.firstOrNull()
            ?.content?.parts?.firstNotNullOfOrNull { it.asImageOrNull() }
        return image ?: throw IllegalStateException("Could not extract image from model response")
    }

Sticker mode with ML Kit Subject Segmentation

The app also includes a “Sticker mode” option, which integrates the ML Kit Subject Segmentation library to remove the background on the bot. You can use “Sticker mode” in apps that support stickers.

The code for the sticker implementation first checks if the Subject Segmentation model has been downloaded and installed, if it has not – it requests that and waits for its completion. If the model is installed already, the app passes in the original Android Bot image into the segmenter, and calls process on it to remove the background. The foregroundBitmap object is then returned for exporting.

override suspend fun generateImageWithEdit(
        image: Bitmap,
        backgroundPrompt: String = "Add the input image android bot as the main subject to the result... with the background that has the following vibe...",
    ): Bitmap {
        val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
            modelName = "gemini-2.5-flash-image-preview",
            generationConfig = generationConfig {
                responseModalities = listOf(
                    ResponseModality.TEXT,
                    ResponseModality.IMAGE,
                )
            },
        )
	  // We combine the backgroundPrompt with the input image which is the Android Bot, to produce the new bot with a background
        val prompt = content {
            text(backgroundPrompt)
            image(image)
        }
        val response = model.generateContent(prompt)
        val image = response.candidates.firstOrNull()
            ?.content?.parts?.firstNotNullOfOrNull { it.asImageOrNull() }
        return image ?: throw IllegalStateException("Could not extract image from model response")
    }

See the LocalSegmentationDataSource for the full source implementation

Learn more

To learn more about Androidify behind the scenes, take a look at the new solutions walkthrough, inspect the code or try out the experience for yourself at androidify.com or download the app on Google Play.

*Check responses. Compatibility and availability varies. 18+.

Posted by Matthew McCullough – VP of Product Management, Android Developer

In this dynamic and complex ecosystem, our commitment is to your success. That’s why in our summer episode of The Android Show, we’re making it easier for you to build amazing apps by unpacking the latest tools and opportunities. In this episode, we’ll cover how you can get building for Wear OS 6, boost your productivity with the latest Gemini in Android Studio updates, create for the new Pixel 10 Pro Fold, and even have some fun with the new AI-powered Androidify. (And for Android users, we also just dropped a bunch of new feature updates today; you can read more about those here). Let’s dive in!

Get the most out of Agent Mode in Android Studio with MCP

We’re focused on making you more productive by integrating AI directly into your workflow. Gemini in Android Studio is at the center of this, helping teams like Entri who was able to reduce UI development time by 40%. You can now connect Model Context Protocol servers to Android Studio, which expands the tools, knowledge, and capabilities of the AI Agent. We also just launched the Android Studio Narwhal 3 feature drop, which brings more productivity boosters like Resizable Compose Preview and Play Policy Insights.

Build for every screen with Compose Adaptive Layouts 1.2 beta

The new Pixel 10 Pro Fold creates an incredible canvas for your app, and we’re simplifying development so you can take full advantage of it. The Compose Adaptive Layouts 1.2 library, now officially in beta, makes it easier than ever to build for large screens and to embrace adaptive app development. This library is packed with tools to help you create sophisticated, adaptive UIs with less code. We’re focused on helping you build intuitive and engaging experiences for every screen. This foundational library is packed with powerful tools to help you create sophisticated, adaptive UIs with less code. Build dynamic, multi-pane experiences using new layout strategies like Reflow and Levitate, and use the new Large and Extra-Large window size classes to make your app more intuitive and engaging than ever. Read more about these new tools here.

Bring your most expressive apps to the wrist with Wear OS 6

We want to help you build amazing experiences for the wrist, and the new Pixel Watch 4 with Wear OS 6 provides a powerful new stage for your apps. We’re giving you the tools to make your apps more expressive and personal, with Material 3 Expressive to create stunning UIs. You can also engage users in new ways by building your own marketplace with the Watch Face Push API. All of this is built on a more reliable foundation, with watches updating to Wear OS 6 seeing up to 10% better battery life and faster app launches.

Androidify yourself, with a selfie + AI!

Our journey to reimagine Android with Gemini at its center extends to everything we do—including our mascot. That’s why we rebuilt Androidify with AI at its core. With the new Androidify, available on the web or on Google Play, you can use a selfie or a prompt to create your own unique Android bot, powered by Gemini 2.5 Flash and Imagen. This is a fun example of how we’re building better user experiences powered by AI… Try it out for yourself—we can’t wait to see what you build.

Under the hood, we’re using Gemini 2.5 Flash to validate the prompt and Imagen to create your Android bot. And on Friday’s this month, you’ll be able to animate your Android bot into an 8-second video; this feature is powered by Veo and available to a limited number of creations. You can read more about the technical building of the Androidify app here. Try it out for yourself – we can’t wait to see your inner Android!

Watch the Summer episode of The Android Show

Thank you for tuning into this quarter’s episode. We’re excited to continue building great things together, and this show is an important part of our conversation with you. We’d love to hear your ideas for our next episode, so please reach out on X or LinkedIn. A special thanks to my co-hosts, Annyce Davis and John Zoeller, for helping us share the latest updates.

Posted by Fahd Imtiaz – Senior Product Manager and Miguel Montemayor – Developer Relations Engineer

With new form factors like the Pixel 10 Pro Fold joining the Android ecosystem, adaptive app development is essential for creating high-quality user experiences across phones, tablets, and foldables. Users expect your app’s UI to seamlessly adapt to these different sizes and postures.

To help you build these dynamic experiences more efficiently, we are announcing that the Compose Adaptive Layouts Library 1.2 is officially entering beta. This release provides powerful new tools to create polished, responsive UIs for this expanding device ecosystem.

Powerful new tools for a bigger canvas

The Compose Adaptive Layouts library is our foundational toolkit for building UIs that adapt across different window sizes. This new beta release is packed with powerful features to help you create sophisticated layouts with less code. Key additions include:

• Powerful new layout strategies: The beta introduces new layout strategies like reflow and levitate, designed to help you build dynamic layouts that look great on both the outer and inner displays of a device like the Pixel 10 Pro Fold, Galaxy Z Fold7 and Z Flip7.
• New Window Size Classes: The release adds built-in support for the new Large and Extra-Large window size classes. These new breakpoints are essential for designing and triggering rich, multi-pane UI changes on expansive screens like tablets and large foldables.

For a full list of changes, check out the official release documentation. Explore our guides on canonical layouts and building a supporting pane layout.

Engage more users on every screen

Embracing an adaptive mindset is more than a best practice, it’s a strategy for growth. The goal isn’t just to make your app work on a larger screen, but to make it shine by becoming more intuitive for users. Instead of simply stretching a single-column layout, think about how you can use the extra space to create more efficient and immersive experiences.

This is the core principle behind dynamic layout strategies like reflow, a powerful new feature in the Compose Adaptive Layouts 1.2 beta designed to help you build these UIs. For example, a great starting point is adopting a multi-pane layout. By showing a list and its corresponding detail view side-by-side, you reduce taps and allow users to accomplish tasks more quickly.

This kind of thoughtful adaptive development is what truly boosts engagement. And, as we highlighted during the latest episode of #TheAndroidShow, this is why we see that users who use an app on both their phone and a larger screen are almost three times more engaged. Building adaptively doesn’t just make your current users happier; it creates a more valuable and compelling experience that builds lasting loyalty and helps you reach new users.

The expanding Android ecosystem, from foldables to desktops

This shift toward adaptive design extends across the entire Android ecosystem. From the new Pixel 10 Pro Fold to the latest Samsung Galaxy foldables, developers have the opportunity to engage a large and growing user base on over 500 million large-screen devices.

This is also why we’re continuing to invest in forward-looking experiences like Connected Displays, currently available to try in developer preview. This feature opens up new surfaces and interaction models for apps to run on, enabling true desktop-class features and multi-instance workflows. We’ve previously shared details on how you can get started with the Connected Displays developer preview and see how it’s shaping the future of multi-device experiences.

Putting adaptive principles into practice

For developers who want to get their apps ready for this adaptive future, here are a few key best practices to keep in mind:

• Take inventory: The first step is to see where you are today. Test your app on a large screen device or with the resizable emulator in Android Studio to identify areas for improvement, like stretched UIs or usability issues.
• Support optimized layouts: Use libraries like Compose Adaptive Layouts to build UI that adapts to different window sizes and device postures. Your app should work well in both portrait and landscape, without restricting orientation.
• Think beyond touch: A great adaptive experience means supporting all input methods. This goes beyond basic functionality to include thoughtful details that users expect, like hover states for mouse cursors, context menus on right-click, and support for keyboard shortcuts.

Your app’s potential is no longer confined to a single screen. Explore the large screen design gallery and app quality guidelines today to envision where your app can go. Get inspired and find design patterns, official guidance, and sample apps you need to build for every fold, flip, and screen at developer.android.com/adaptive-apps.

Posted by Christopher Katsaros – Senior Product Marketing Manager

In just a few days, on Wednesday September 3 at 11AM PT, we’ll be dropping our summer episode of #TheAndroidShow, on YouTube and on developer.android.com! In this quarterly show, we’ll be unpacking all of the goodies coming out of this month’s Made by Google event and what you as Android developers need to know!

With the new Pixel Watch 4 running Wear OS 6, we’ll show you how to get building for the wrist. And with the latest foldable from Google, the Pixel 10 Pro Fold, we’ll show how you can leverage out of the box APIs and multi-window experiences to make your apps adaptive for this new form factor. Plus, we’ll be unpacking a set of new features for Gemini in Android Studio to help you be even more productive.

#TheAndroidShow is your conversation with the Android developer community, this time hosted by Annyce Davis and John Zoeller. You’ll hear the latest from the developers and engineers who build Android. Don’t forget to tune in live on September 3 at 10AM PT, live on YouTube and on developer.android.com/events/show!

Posted by Matthew McCullough – Vice President, Product Management, Android Developer

We just dropped an I/O Edition of The Android Show, where we unpacked exciting new experiences coming to the Android ecosystem: a fresh and dynamic look and feel, smarts across your devices, and enhanced safety and security features. Join Sameer Samat, President of Android Ecosystem, and the Android team to learn about exciting new development in the episode below, and read about all of the updates for users.

Tune into Google I/O next week – including the Developer Keynote as well as the full Android track of sessions – where we’re covering these topics in more detail and how you can get started.

Start building with Material 3 Expressive

The world of UX design is constantly evolving, and you deserve the tools to create truly engaging and impactful experiences. That’s why Material Design’s latest evolution, Material 3 Expressive, provides new ways to make your product more engaging, easy to use, and desirable. Learn more, and try out the new Material 3 Expressive: an expansion pack designed to enhance your app’s appeal by harnessing emotional UX, making it more engaging, intuitive, and desirable for users. It comes with new components, motion-physics system, type styles, colors, shapes and more.

Material 3 Expressive will be coming to Android 16 later this year; check out the Google I/O talk next week where we’ll dive into this in more detail.

A fluid design built for your watch’s round display

Wear OS 6, arriving later this year, brings Material 3 Expressive design to Google’s smartwatch platform. New design language puts the round watch display at the heart of the experience, and is embraced in every single component and motion of the System, from buttons to notifications. You’ll be able to try new visual design and upgrade existing app experiences to a new level. Next week, tune in to the What’s New in Android session to learn more.

Plus some goodies in Android 16…

We also unpacked some of the latest features coming to users in Android 16, which we’ve been previewing with you for the last few months. If you haven’t already, you can try out the latest Beta of Android 16.

A few new features that Android 16 adds which developers should pay attention to are Live updates, professional media and camera features, desktop windowing for tablets, major accessibility enhancements and much more:

• Live Updates allow your app to show time-sensitive progress updates. Use the new ProgressStyle template for an improved experience around navigation, deliveries, and rideshares.
• Professional media and camera features include hybrid auto exposure, precise color temperature and tint adjustments, night mode scene detection, and support for the new Advanced Professional Video format.

Watch the What’s New in Android session and the Live updates talk to learn more.

Tune in next week to Google I/O

This was just a preview of some Android-related news, so remember to tune in next week to Google I/O, where we’ll be diving into a range of Android developer topics in a lot more detail. You can check out What’s New in Android and the full Android track of sessions to start planning your time.

We can’t wait to see you next week, whether you’re joining in person or virtually from anywhere around the world!