How we used Gemini to build Google I/O 2026

How We Used Gemini to Build Google I/O 2026

Google I/O 2026 was a showcase of the company's latest innovations in AI, and it was also a testament to the power of AI in creating immersive experiences. This year, we challenged ourselves to use the same AI tools that we were putting on stage to out-innovate, out-create, and out-efficient ourselves. We moved faster than ever and prototyped in real-time, blending human artistry with experimental technology.

AI x Film: "TPU Training Day"

The AI products & models used in this project were Google AI Studio, experimental DeepMind models, Gemini Omni, and Nano Banana. We created a short film starring a bunch of TPUs getting ready to do some heavy lifting for I/O 2026. The project started with a question: Could we make an animated film with the simplest materials – cardboard and markers – and then use AI to bring it to life?

We worked with director Laurie Rowan and Nexus Studios to blend puppets, traditional animation, and AI, keeping human craft and artistry right at the heart of "TPU Training Day" (also known as "Timmy TPU"). First, we captured character performances through puppetry and simple 3D animation. This gave us full control over framing and camera movement. We then used Nano Banana to generate stylized first frames from that raw footage.

To keep frames consistent, we built a custom tool inside Google AI Studio. This let us test Nano Banana frames at scale, ensuring pixel-perfect matches before generating sequences. We merged the base animation and stylized frames using Gemini Omni and other experimental models. This elevated the film to a cinematic level while retaining the original human intent.

AI x Visual Design: I/O Visual Brand Identity

The AI products & models used in this project were Gemini models and Nano Banana. We created the visual brand identity for I/O 2026, landing on a four-color gradient with overlapping transparencies and interlocking icons. Our brand identity was a close collaboration between our team and AI. We started by feeding Gemini models our past brand guidelines and five years of I/O recaps.

The early outputs didn't quite hit the mark, so we ran some micro-experiments. We generated new imagery and iteratively fed outputs back into Nano Banana with feedback. We also used Nano Banana to explore icon styles. Finally, we landed on flat 2D icons that dynamically transform into hyper-textured 3D icons. This created a cohesive brand expression across keynotes, physical signage, and digital apps.

AI x Immersive Experiences: The I/O Pre-Show

The AI products & models used in this project were Google Antigravity, Google Colab, Google CoralNPU, Google Flow Music, and Lyria 3 Pro. We kicked off the pre-show with Jellectronica, a generative music experiment in partnership with the Monterey Bay Aquarium that translated moon jelly movements into sound with Lyria 3 Pro.

We trained a YOLO8 model in Google Colab, and then ran it on Google's Coral NPU. This tracked jellyfish movement to control the music, which was made using Google Flow Music and the Lyria API. For example, more jellies in the bass section meant louder, more energetic bass. We also vibe-coded a mass stem generator in Google Antigravity to automate the production of music stems, like bass, chords, melody, and drums.

AI x Immersive Experiences: Infinite Scaler and Code the Countdown

The AI products & models used in this project were Google AI Studio, Gemini API, Gemini Canvas, Google Antigravity, Lyria 3, and Nano Banana. Infinite Scaler, another part of the pre-show, was a video game where players competed and generated the levels as they played.

We wanted players to build infinite 3D worlds quickly just using 2D image generation. To do this, we used Nano Banana to generate sprite sheets from user prompts and reference images via the Gemini API. We sent foreground elements back to Nano Banana to generate normal, roughness, and emission maps. This inferred depth, letting us map textures to a 3D cardboard box rendered in WebGL before adding them to the global stack of worlds.

AI x Creative Delight: Speaker Title Cards

The AI products & models used in this project were Gemini Omni, Google Flow, and Nano Banana Pro. Each speaker got their own custom-generated title card made with our image and video generation models. We used Nano Banana Pro to generate core assets like ingredient reference sheets.

We used these ingredients to storyboard, trying variations and adding personal details. In Google Flow, we first used Veo to help prototype actions and generate animations like a slam dunk. We also generated animations with Gemini Omni in Google Flow, which was particularly helpful when dealing with intricate sports movements.

AI x Creative Delight: Sticker Swag

The AI products & models used in this project were Gemini and Nano Banana. We generated and printed custom I/O stickers for attendees on the spot. We built an interactive sticker game on a custom web app. Players had 20 seconds to catch falling prompts using an Android bot.

There were over 100 prompt categories – from blueberries and disco balls to lasers and wood. Players selected two prompts, or hit "I'm feeling lucky" for a random mix. Our backend – using Nano Banana for Gemini and Android – fused these choices together. This created a highly personalized, custom I/O sticker design.

Conclusion

Google I/O 2026 was a showcase of the company's latest innovations in AI, and it was also a testament to the power of AI in creating immersive experiences. We used Gemini to build a range of experiences, from a short film to a video game, and from a visual brand identity to custom title cards and stickers. These experiences demonstrate the potential of AI to create engaging, interactive, and personalized experiences that can be used in a variety of contexts.

As we look to the future, it's clear that AI will continue to play a major role in shaping the way we experience and interact with technology. Whether it's through the creation of immersive experiences, the development of new products and services, or the improvement of existing ones, AI has the potential to transform the way we live and work.

By leveraging the power of AI, we can create experiences that are more engaging, more interactive, and more personalized than ever before. We can use AI to automate tasks, to analyze data, and to make predictions. We can use AI to create new products and services, to improve existing ones, and to develop new business models.

As we move forward, it's essential that we continue to explore the potential of AI and to develop new applications for it. We must also be mindful of the potential risks and challenges associated with AI, and we must work to ensure that AI is developed and used in a responsible and ethical manner.

Ultimately, the future of AI is full of possibilities, and it's up to us to shape it. By working together, we can create a future where AI is used to improve people's lives, to create new opportunities, and to drive progress.

Source: https://blog.google/innovation-and-ai/technology/ai/io-2026-google-ai/