Google unveils Nano Banana 2
What's the story
Google has unveiled the second iteration of its popular artificial intelligence (AI) image-generation model, Nano Banana. The new version, dubbed Nano Banana 2, is said to be faster and more efficient than its predecessor. It uses real-time information and images from web search to create high-fidelity representations of real-world conditions. The new model, which is technically Gemini 3.1 Flash Image, will now be the default option in the Gemini app for its Fast, Thinking, and Pro modes.
Enhanced capabilities
It can generate images in different aspect ratios
The new model retains some of the high-fidelity characteristics of its Pro counterpart but is capable of generating images at a faster rate. It can create images with resolutions ranging from 512px to 4K and different aspect ratios. The model also maintains character consistency for up to five characters and fidelity for up to 14 objects in one workflow, making it ideal for storytelling.
User control
Users can issue complex requests for image generation
With Nano Banana 2, users can issue complex requests with detailed nuances for image generation. The model also allows creative control over elements like aspect ratio and number of objects. It will be the default model for image generation across all apps in the Gemini app and Google's video editing tool, Flow.
Wide availability
Nano Banana 2 will be available in Google Search
The new model will be the default for Google Search results via Google Lens and in AI Mode across 141 countries on the Google app and web. For developers, Nano Banana 2 will be available in preview through the Gemini API, Gemini CLI, and Vertex API. It will also be accessible via AI Studio and Antigravity, Google's development tool launched last November.
Image verification
All images will have SynthID watermark
All images created through the new model will have a SynthID watermark, Google's mark to denote AI-generated images. The images are also interoperable with C2PA Content Credentials, created by an industry body consisting of companies like Adobe, Microsoft, Google, OpenAI, and Meta. Since launching SynthID verification in the Gemini app in November last year, people have used it over 20 million times.
Twitter Post
Nano Banana 2 is built on latest Gemini Flash model
We’re launching Nano Banana 2, built on the latest Gemini Flash model. 🍌
— Google DeepMind (@GoogleDeepMind) February 26, 2026
It’s state-of-the-art for creating and editing images, combining Pro-level capabilities with lightning-fast speed. 🧵 pic.twitter.com/b3sHCAhrSy