Hands on with Google Gemini

Can AI Understand Your Outfit? In this test, we'll see if Gemini can understand outfits and even name a new hypothetical fashion trend. Gemini is our natively multimodal AI model capable of reasoning across text, images, audio, video, and code. Learn more about what's possible and try Gemini: https://deepmind.google/gemini Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google

Testing if AI understands its surroundings by deciding where houseplants might receive the most sunlight. Gemini is Google's multimodal AI model capable of reasoning across text, images, audio, video, and code. Learn more about what's possible and try Gemini: https://deepmind.google/gemini Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google

AI understanding emojis. Testing if Gemini can recognize some unusual emojis that were created using Emoji Kitchen. Gemini is our multimodal AI model capable of reasoning across text, images, audio, video, and code. Learn more and try Gemini: https://deepmind.google/gemini Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google

AI is tested beyond image recognition and into image reasoning, let's see how Gemini can find similarities between images. Gemini is Google's multimodal AI model capable of reasoning across text, images, audio, video, and code. Learn more and try Gemini: https://deepmind.google/gemini Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google

Can AI guess the movie based on the words hidden in a set of images? Let's explore the capabilities of Gemini. Gemini is Google's multimodal AI model capable of reasoning across text, images, audio, video, and code. Learn more and try Gemini: https://deepmind.google/gemini Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google

Using AI to convert images into code using Gemini's code generation capabilities. Watch as we turn an image into an SVG and interactive HTML. Gemini is our natively multimodal AI model capable of reasoning across text, images, audio, video, and code. Learn more about what's possible and try Gemini: https://deepmind.google/gemini Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google

Our natively multimodal AI model Gemini is capable of reasoning across text, images, audio, video and code. Here are favorite moments with Gemini Learn more and try the model: https://deepmind.google/gemini Explore Gemini: https://goo.gle/how-its-made-gemini For the purposes of this demo, latency has been reduced and Gemini outputs have been shortened for brevity. Subscribe to our Channel: https://www.youtube.com/google Tweet with us on X: https://twitter.com/google Follow us on Instagram: https://www.instagram.com/google Join us on Facebook: https://www.facebook.com/Google 0:00 Intro 0:19 Multimodal Dialogue 1:32 Multilinguality 2:04 Game Creation 2:31 Visual Puzzles 3:17 Making Connections 3:39 Image & Text Generation 4:06 Logic & Spatial Reasoning 4:55 Translating Visuals 5:27 Cultural Understanding