Gemini videos

From sketches to prototype: Designing with generative AI

Using Gemini and Google DeepMind’s generative image technology, we worked with Lovegrove Studio to build a fine-tuned model to act as a prototyping tool to support their creative process. The model translates Ross Lovegrove's distinct desig...

Uploads from Google DeepMind

Miss your ’90s power bob? Re-create that fly hairstyle with #NanoBanana and #Veo3 in #GoogleGemini

Level up your look, ’90s style! Generate your old school self with #NanoBanana, then add a dramatic hair toss with #Veo3 in #GoogleGemini

The Latest from Gemini

Messy roommates? There’s a chart for that. Go from chaos to clean with help from Gemini ✨🧺

Go from roommate chaos to a clean home. Ask Gemini to build a weekly chore chart and send reminders into your calendar at the start of each week. #GoogleGemini

The Latest from Gemini

Join @OscarPiastri in designing his dream track! He’s looking for your most creative ideas 👀

Time to go bananas! 🍌 #GoogleGemini #GeminiDreamTrack

The Latest from Gemini

Make the pet of your dreams a reality with Nano Banana

Gemini's state-of-the-art image generation and editing lets you create almost anything. Imagine yourself with a pet dinosaur. Try a new hairstyle. Restore an old photo. Combine two photos into one. It's free for everyone. Go Nano Bananas....

The Latest from Gemini

Want your dream big hair? Get it with #NanoBanana and #Veo3 in #GoogleGemini.

The ’80s had big hair, but our imaginations are even bigger. Design your voluminous look with #NanoBanana, then make it sway with #Veo3 in #GoogleGemini.

The Latest from Gemini

We’re gonna need a bigger belt. Get help decoding sushi dishes with Gemini 🍣✨

Gemini’s ready to roll, helping demystify the menu, one dish at a time. #GoogleGemini #Hacks

The Latest from Gemini

Gemini Robotics 1.5: Using agentic capabilities

Gemini Robotics 1.5 can use digital tools to solve tasks. For example, if a robot was asked, “Based on my location, can you sort these objects into the correct compost, recycling and trash bins?" it would need to search for relevant local r...

Uploads from Google DeepMind

Gemini Robotics 1.5: Learning across embodiments

Robots come in all shapes and sizes, and have different sensing capabilities and different degrees of freedom, making it difficult to transfer motions learned from one robot to another. Gemini Robotics 1.5 shows a remarkable ability to le...

Uploads from Google DeepMind

Gemini Robotics 1.5: Enabling robots to plan, think and use tools to solve complex tasks

We’re powering an era of physical agents with Gemini Robotics 1.5 — enabling robots to perceive, plan, think, use tools and act to better solve complex, multi-step tasks. 🤖 Gemini Robotics 1.5 is our most capable vision-language-action (V...

Uploads from Google DeepMind

Gemini Robotics 1.5: Thinking while acting

Previously, robots could complete one tasks per instruction. Now, they can solve longer multi-step challenges. This means they can generate an internal sequence of reasoning and analysis in natural language to perform tasks that require mul...

Uploads from Google DeepMind

Google DeepMind researchers react to Nano Banana demos 🍌

Uploads from Google DeepMind