Google announced today its latest version popular image creation modelNano Banana 2. The new model, which is technically Gemini 3.1 Flash Image, can create more realistic images than its predecessor. The model will also become the default in the Gemini app for Fast, Thinking and Pro modes.
The company first launched Nano Banana in August 2025, prompting people to create millions of images on the Gemini app, especially in countries like India. In November, the company released Nano Banana Pro, which allows users to create more detailed and high-quality images.
The new Nano Banana 2 retains some of the high-fidelity features of the Pro model, but produces images faster. The company says you can create images with resolutions ranging from 512px to 4K, in different aspect ratios.
Nano Banana 2 can maintain character consistency for up to five characters and fidelity for up to 14 objects in one workflow for better storytelling. Users can also make complex requests with detailed nuances to create images, Google says. Additionally, users can create media with more vivid lighting, richer textures, and sharper details.
At launch, the Nano Banana 2 will become the default imaging model in all Gemini apps. The company also makes it the default model for creating images in its video editing tool, Flow.
In Search, Nano Banana 2 will become the default for Google Search results through Google Lens and AI mode in 141 countries on the Google app and web on desktop and mobile.
On Google’s premium plansGoogle AI Pro and Ultra, subscribers can continue to use Nano Banana Pro for specialized tasks by recreating images through the three-dot menu.
Techcrunch event
Boston, MA
|
June 9, 2026
For developers, Nano Banana 2 will be available in preview through the Gemini API, Gemini CLI, and Vertex API. It will also be available through AI Studio and the company’s Antigravity development tool, which was released last November.
The company said that all images created through the new model will have a SynthID watermark, which is Google’s mark to denote AI-generated images. Images are also interoperable with C2PA Content Credentialscreated by an industry consortium consisting of companies such as Adobe, Microsoft, Google, OpenAI and Meta. Google said that since it launched SynthID verification in the Gemini app in November, people have used it more than 20 million times.
