Google launches Nano Banana 2 model with faster image generation

Google today announced the latest version of its popular image generation model, the Nano Banana 2. The new model, which is technically Gemini 3.1 Flash Image, can create images that are more realistic than its predecessor. The model will now also be the default model in the Gemini app for its Fast, Thinking, and Professional modes.

The company first launched Nano Banana in August 2025, prompting people to create millions of photos in the Gemini app, especially in countries like India. In November, the company released Nano Banana Pro, which allows users to create more detailed, high-quality images.

The new Nano Banana 2 retains some of the high-resolution features of the Pro model but produces images faster. The company says you can create images in resolutions ranging from 512p to 4K, in different aspect ratios.

Nano Banana 2 can maintain character consistency for up to five characters and resolution for up to 14 objects in a single workflow for better storytelling. Google says users can also issue complex requests with detailed nuances to create images. Additionally, users can create media with more vibrant lighting, richer textures, and sharper details.

With launch, the Nano Banana 2 will become the default image generation model across all apps in the Gemini app. The company is also making it the default image generation model in its video editing tool, Flow.

In search, the Nano Banana 2 will become the default choice for Google search results via Google Lens and in AI mode across 141 countries on the Google app and on the web across desktop and mobile.

On Google’s higher-end plans, Google AI Pro and Ultra, subscribers can continue to use the Nano Banana Pro for specialized tasks by refreshing images via the three-dot menu.

For developers, Nano Banana 2 will be available for preview through the Gemini API, Gemini CLI, and Vertex API. It will also be available through AI Studio and the company’s own development tool, Antigravity, which was released last November.

The company said that all images created through the new model will contain a SynthID watermark, which is a Google tag to indicate images created by artificial intelligence. Images are also interoperable with C2PA content credentials, created by an industry body consisting of companies such as Adobe, Microsoft, Google, OpenAI, and Meta. Since launching SynthID verification in the Gemini app in November, people have used it more than 20 million times, Google said.