Start here
Recent posts
To kick off your creativity, here are some Nano Banana 2 prompts to try out. We hope you find them fruitful 🍌🍌 Prompt: Create a funny 4-part story featuring 3 fluffy creatures building a treehouse. The story has emotional highs and lows and ends in a happy moment. Maintain consistent identity across the 3 characters. Generate 4 images in 16:9 format, one at a time.
Channeling the Fire Horse energy this week 🔥🐎 here’s what we launched: — Gemini 3.1 Pro, a step forward in core intelligence that helps you tackle complex workflows and projects — Photoshoot, a new feature for Pomelli by @GoogleLabs that transforms a single product image into studio-quality visuals for your business — Lyria 3, our most advanced generative music model yet, turns photos and text into dynamic tracks complete with vocals and lyrics — A new featured notebook in @NotebookLM that was created in partnership with @Zillow and is designed to guide first-time buyers — Updates to @NotebookLM’s Slide Decks including slide revisions and export to PPTX
We ❤️ launches! Here’s a recap of what went out this week: — An upgrade to Gemini 3 Deep Think that solves complex modern science and engineering challenges. Scientists, researchers, and enterprises can express interest in Deep Think via our early access program and Google AI Ultra subscribers can access it in @GeminiApp — The @Waymo World Model, which is powered by Genie 3 and allows the autonomous Waymo Driver to master complex scenarios long before it sees them on the road — A trio of top feature requests for @StitchbyGoogle - direct export to Figma as editable layers, the research-driven Ideate Agent, and Design Systems for cross-project style consistency — Perch 2.0, an update to our bioacoustics foundation model, that advances our ability to disentangle underwater sounds (like whale vocalizations!) and monitor marine ecosystems — Video Overviews in the @NotebookLM mobile app, allowing you to learn anything on the go
For more than a decade, Google researchers have been redefining the scientifically impossible. From flood forecasting to brain mapping to our most recent announcement of preserving the genetic code of 13 new endangered species of animals. Learn how ten years of AI innovation for genomics at @GoogleResearch are contributing to this goal. —DeepConsensus sits at the instrument level, removing sequencing errors at the source to produce more of the high-quality data needed for genome assembly. —DeepVariant finds genetic variants. For example, the University of Otago used it to analyze the genome of every living kākāpō, powering the precise breeding plan that is currently pulling the species back from extinction. —DeepPolisher helps make sure the assembled genome get 99.999%+ accuracy. Important for tasks like finding gene models that matter for disease. Learn more (and enjoy some adorable animal photos) here:
How we're helping preserve the genetic information of endangered species with AI
More than a billion images generated later, we love seeing what you create with Nano Banana. Today, we’re inviting more people to join in on the fun with the launch of 🍌Nano Banana 2🍌 This state-of-the-art model is exceptionally good at things like: — Creating images that tap into the Gemini model’s real-world knowledge base + are powered by information and images from web search to more accurately render specific landmarks, locations, objects, and beyond — Adapting creative assets for global markets with regionally relevant localization — Dynamically editing aspect ratios and upscaling to 2k and 4k resolutions — Generating multiple cohesive images that fit together in one world, story, or concept
Introducing Gemini 3.1 Pro 🚀 3.1 Pro represents a major step forward in core reasoning. It scored 77.1% (more than doubling 3 Pro’s score) on ARC-AGI-2, the benchmark that evaluates a model's ability to solve new logic patterns and work through challenges it hasn’t encountered before. This demo illustrates how the model can go beyond the prompt. Instead of rendering a video or static graphic, 3.1 Pro codes a full environment, integrating generative audio and providing UI controls.
Gemini 3 Deep Think is getting an upgrade 🧠 By blending deep scientific knowledge with advanced engineering utility, Deep Think now moves beyond abstract theory to drive practical applications. Researchers are already using it to accelerate their work in the real world: — Materials science: A university lab used Deep Think to optimize the growth of complex crystals that are candidates for high-temperature semiconductors — Mechanical engineering: A researcher demonstrated how Deep Think can be used to iterate on physical prototypes at the speed of software. When applied to things like assistive devices, this pace means faster improvements for life-changing technology (more information on this use case in the video below!) The updated Deep Think is available in @GeminiApp for Google AI Ultra subscribers.
Yesterday, @GoogleLabs' Pomelli launched Photoshoot, a new feature that generates on-brand, campaign-ready product visuals with a few clicks (for free!) 📸 There are easy 3 ways to create images with Photoshoot: 1. Templates: Upload an image of your product then select up to 4 shots from our auto-recommended photo templates, which will help you control the composition, framing, and style of your product shot 2. Edit existing: You can make edits to existing images by prompting Photoshoot to do things like update the background or adjust the lighting of a photo 3. Create new: Leverage our flexible editor to create shots from scratch. Just describe your vision or upload a reference to create custom assets with your aesthetic in mind Once perfected, download the final assets to share across your channels or add them to your Pomelli Business DNA for future use. Then, show us what you’ve created by sharing your Photoshoot visuals below!
Today we introduced Lyria 3, @GoogleDeepMind's latest music generation model, which you can use to turn your ideas into musical tracks through prompts or even photos. Here are 3 tips (and fun facts!) to help you make the most out today's launch: 1. We intentionally built this model to have extremely high customization character limits, so you can feel the full freedom of flexibility. From a pithy haiku to an emotional short story, Lyria 3 allows you to lose yourself in the details. 2. Get creative! When designing this model, we wanted to cater a broad and diverse range of musical tastes (not just pop music). Whether it's unique combinations of instruments or blends of seemingly clashing genres, feel free to experiment. 3. When creating a track, you can prompt the style of music and Gemini can suggest lyrics that fit your theme. Or, you could request specific lyrics transforming the most mundane messages into your very own musical. For example, when testing the model, the team found success in creating tracks with critically acclaimed lyrics like "Check your email" or "Please RSVP to my event.” Lyria 3 is rolling out today in beta in the @GeminiApp for 18+ users. Have fun!
From a window to the web to an AI-powered platform: How do you integrate Gemini into the world's most popular browser? On this week’s Release Notes, @OfficialLoganK sat down with @rosterloh and @laparisa to talk about how they approached this integration and what the future of Chrome looks like. Listen to the full episode here: https://youtube.com/watch?v=5OR4c87Xt-E
