The Gemini app turns research into reality, bringing frontier AI experiences like Veo 3, Deep Think, and more to hundreds of millions of people.
Aug 26 • 10 tweets • 5 min read
With state-of-the-art image capabilities, Gemini makes it easier to create and edit images like never before.
You’ll get great results from simple inputs, but if you want even more creative control, our team pulled together some tried-and-true nano banana prompting tips to help you unlock next-level photos.
Let’s get into it 🍌
Try adding some or all of these elements in your prompt:
Subject: Be specific about who or what you want in the image. “A fluffy calico cat wearing a tiny wizard hat” specific.
Composition: Note how the photo should be framed. Extreme close-up? Wide shot? Portrait? You call the shot.
Action: Clarify what’s happening. Think: brewing a cup of coffee, casting a magical spell, mid-stride running through a field.
Location: Note where the scene takes place—a futuristic cafe on Mars, a cluttered alchemist's library, or a sun-drenched meadow at golden hour to name a few.
Style: Call out the overall aesthetic, like if you want it to be 3D animated, film noir, watercolor, photorealistic, or 1990s studio photography.
Aug 23 • 10 tweets • 3 min read
This weekend only, everyone gets 3 free #Veo3 video generations from Gemini. To help you make the most of it, we’ve pulled together a few tips from our team so you can get better outputs for your prompts.
Check it out ⬇️
Two ways to get started:
➡️ Open
➡️ Start a new chat
➡️ Select ‘Video’ from the tools menu
➡️ Type your video idea in the prompt bar
➡️ Or upload a photo to turn into a videogemini.google.com
Aug 18 • 8 tweets • 2 min read
We recently rolled out Storybook, a way to create personalized, illustrated stories that you can read, listen to, print, and share. Relive memories. Explain complex concepts. Highlight inside jokes.
Get started with these how-tos & tips 🧵
How to get started:
➡️ Open
➡️ Start a new chat
➡️ Type “Create a storybook…” in the prompt bar
➡️ Tell Gemini what kind story you want to tellgemini.google.com
Aug 11 • 6 tweets • 2 min read
We dropped Deep Think for Ultra subscribers, and we love seeing how you're using it to solve your math and coding problems.
1/ Tips to help you create impressive Veo 3 videos with sound from a single prompt 🧵
2/ More detail = more control.
Detailing the subject (who/what), action (what's happening), scene (the setting), and style (the vibe) in your prompt is key to getting closer to your desired vision.
Jul 18 • 11 tweets • 4 min read
Introducing Gemini Drops: Our new monthly update to discover what’s new, what’s next, and how to get the most out of the Gemini app.
1/ Here’s everything we’ve shipped recently🧵
2/ You can now use Veo 3 to transform your photos into videos in the Gemini app.
Jul 16 • 4 tweets • 1 min read
The photo to video energy is 🤯 and we love seeing your results.
🔊 Sound on. Prompts in thread 🧵1/
2/ A serene, layered-paper flamingo gracefully steps through a shimmering, stop-motion paper marsh, its reflection rippling in the glossy paper water, before taking a serene flight
May 20 • 10 tweets • 2 min read
We announced a lot of updates coming to Gemini at #GoogleIO. Catch up on all the news in the thread below 🧵
Our TPUs are sizzling and we're adding fuel to the fire. 🔥 Now everyone can try Canvas with Gemini 2.5 Pro, rate limits apply.
From prompt to prototype in just a few minutes, anyone can code & create with Canvas.
Some games & ideas from our team using Canvas in 2.5 Pro to inspire your next creation🧵↓
1⃣ Design a kaleidoscope using p5js that generates symmetrical patterns based on mouse movements:
Mar 13 • 7 tweets • 5 min read
Today, we’re making big upgrades to the performance and availability of our most popular Gemini features, and adding a new feature that will make Gemini even more personal and helpful:
Let’s break down today’s updates 🧵⬇️ goo.gle/3R2NZK6
1⃣ 2.0 Flash Thinking Experimental gets new features and a longer context window.
Today, we’re starting to roll out an upgraded version of our 2.0 Flash Thinking Experimental model that supports added features like file upload. Built on the foundation of 2.0 Flash, this model delivers improved performance and better advanced reasoning capabilities with efficiency and speed.
✨ Gemini Advanced users will also have access to a 1M token context window with this model: gemini.google/advanced/
