Gemini videos
Browse every published Gemini video in a focused overview with thumbnails, dates, and direct access to each watch page.
Veo 2 demo | Pancakes
Prompt: The sun rises slowly behind a perfectly plated breakfast scene. Thick, golden maple syrup pours in slow motion over a stack of fluffy pancakes, each one releasing a soft, warm steam cloud. A close-up of crispy bacon sizzles, sending...
Uploads from Google DeepMind
Veo 2 demo | Cube
Prompt: A perfect cube rotates in the center of a soft, foggy void. The surface shifts between different hyper-real textures—smooth marble, velvety suede, hammered brass, and raw concrete. Each material reveals subtle details: marble veins...
Uploads from Google DeepMind
Veo 2 demo | Cartoon girl
Prompt: This medium shot, with a shallow depth of field, portrays a cute cartoon girl with wavy brown hair, sitting upright in a 1980s kitchen. Her hair is medium length and wavy. She has a small, slightly upturned nose, and small, rounded...
Uploads from Google DeepMind
Veo 2 demo | Car drive
Prompt: Extreme close-up on the car's speedometer, seen through the steering wheel. The needle climbs rapidly as the driver turns the wheel sharply, the view outside the window blurring into streaks of light. The camera focuses on the speed...
Uploads from Google DeepMind
Veo 2 compilation
Veo creates videos with realistic motion and high quality output, up to 4K. Learn more https://deepmind.google/technologies/veo/veo-2/
Uploads from Google DeepMind
Gemini 2.0 and the evolution of agentic AI | Oriol Vinyals
In this episode, Hannah is joined by Oriol Vinyals, VP of Drastic Research and Gemini co-lead. They discuss the evolution of agents from single-task models to more general-purpose models capable of broader applications, like Gemini. Vinyals...
Uploads from Google DeepMind
Introducing Gemini 2.0 | Our most capable AI model yet
We're announcing Gemini 2.0, our most capable AI model yet that’s built for the agentic era. Gemini 2.0 brings enhanced performance, more multimodality, and new native tool use. Learn more about Gemini: https://deepmind.google/gemini Rea...
The Latest from Gemini
Project Astra | Exploring the future capabilities of a universal AI assistant
Project Astra is our research prototype that explores the future capabilities of a universal AI assistant. Using capabilities like multimodal understanding, multilinguality, tool use, native audio, and memory, it helps you understand your w...
The Latest from Gemini
Building with Gemini 2.0: Multimodal live streaming
The Multimodal Live API lets you build real-time multimodal applications using Gemini 2.0 Flash Experimental. Watch this demo to see how this new capability can help developers build AI agents, and start building with Gemini 2.0 at aistudio...
The Latest from Gemini
Building with Gemini 2.0: Native image output
Gemini 2.0 can now natively generate images as part of your conversation. Watch this demo to see how this new capability can help developers build multimodal AI agents. These new output modalities are available to early testers, with wider...
The Latest from Gemini
Building with Gemini 2.0: Native tool use
Gemini 2.0 is natively built to use tools like Google Search and code execution. Watch this demo to see how this new capability can help developers build multimodal AI agents. Start building with Gemini 2.0 at aistudio.google.com. Learn m...
The Latest from Gemini
Building with Gemini 2.0: Native audio output
Gemini 2.0 introduces multilingual native audio output. Watch this demo to see how this new capability can help developers build multimodal AI agents. These new output modalities are available to early testers, with wider rollout expected n...
The Latest from Gemini
Showing 277 to 288 of 314 videos.