It’s been 3 weeks since we launched Gemini 3, our most intelligent model yet. But… what does that mean and how can you use it?

Here are 3 ways you can use Gemini 3 today (with sample prompts!) 🧵 🧵(2/5) Build interactive, playable 3D designed games with a single prompt in @GoogleAIStudio.

Example prompt:

“Create a polished, retro-futuristic 3D spaceship web game contained entirely within a single HTML file using Three.js. The game should feature a "Synthwave/Retrowave" aesthetic. Visual style is a dark, immersive, 3D environment. Gameplay mechanics include a third-person view from behind the spaceship. On desktop, use arrow keys for smooth movement. On mobile, render a virtual joystick on the bottom left of the screen.”

Last week, we announced Veo 3.1 and a series of new features that give you more creative control over your video generations.

Here are a few additional tips to make sure you’re using this new model to the fullest. After reading this thread, you can put your Veo skills to the test in @FlowbyGoogle, the Gemini API, or @GoogleCloud Vertex AI. 🧵 Scene extension works by chaining: the last frame of the first video acts as the visual starting point for the next. This means that if your first video ends in music or background noise, the second video will maintain that audio consistency throughout.

Also, you can extend your videos as much as you want, but we’ve found that the sweet spot for optimum video and audio quality is four 8-second clips.

🧵1/5 @GoogleChrome is officially entering its Gemini era ✨

Directly embedded into Chrome, Gemini can now answer questions about your open pages, summarize information from multiple tabs, and help you take action in Google apps like YouTube and Calendar.

Here is a deeper look into some of Chrome's new features: @googlechrome 🧵2/5 You can now ask Gemini to clarify complex information on any webpage (or webpages) you're reading.

Image editing is one of the most popular use cases for @NanoBanana. Try using these image editing prompt templates so you can quickly get the details in your photos just right 🧵

(tip: bookmark this thread for future reference!) @NanoBanana 🧵1/4 Adding and removing elements

Using the provided image of [subject], please [add/remove/modify] [element] to/from the scene. Ensure the change is [description of how the change should integrate].

Want to try Nano Banana but don’t know where to start? Try using these prompting templates to generate images from text 🧵

(note: you may want to bookmark this thread)! 🧵1/5 Photorealistic scenes

A photorealistic [shot type] of [subject], [action or expression], set in [environment]. The scene is illuminated by [lighting description], creating a [mood] atmosphere. Captured with a [camera/lens details], emphasizing [key textures and details]. The image should be in a [aspect ratio] format.

Today, we shared our latest preprint introducing AMIE (Articulate Medical Intelligence Explorer), a large language model (LLM) based research AI system for diagnostic medical reasoning and conversations.🔗 goo.gle/3TZocp0
AMIE uses a novel self-play based simulated environment with automated feedback mechanisms for scaling learning across diverse disease conditions, specialties, and contexts.

Generative AI has the potential to help us expand our creativity and express ourselves in new, artistic ways.

Our Senior Research Director, @douglas_eck, will be sharing the tools we’re building to generate text, audio, images, and videos ↓ (1/5) To explore how a dialogue engine can assist writers with idea generation, we are building a text editing tool on LaMDA.

We teamed up with professional writers who used the editor to create a volume of short stories. Check out their great work. (2/5)
g.co/research/wordc…

How can AI be used to tackle some of humanity’s biggest challenges?

Keep an eye on this thread for exciting updates in this area, shared by Kat Chou, our Sr. Director of Research and Innovation. (1/5) Floods claim thousands of lives every year. We use satellite imagery and AI to accurately map rivers, model what areas will be flooded, and send timely info (g.co/floodhub)

Today, we’re announcing the expansion of flood forecasting coverage to 18 new countries. (2/5)