Google has introduced the newest iteration of its widely-used image generation model, Nano Banana 2. Technically known as Gemini 3.1 Flash Image, this updated model is capable of producing more lifelike images compared to the previous version. It will now serve as the default option within the Gemini app for its Fast, Thinking, and Pro modes.

The original Nano Banana model debuted in August 2025, leading users to create millions of images through the Gemini app, with notable popularity in countries such as India. Following this, Nano Banana Pro was released in November, offering enhanced detail and higher-quality image generation. The new Nano Banana 2 incorporates some of the high-fidelity features from the Pro model while delivering faster image production. According to the company, users can generate images with resolutions from 512px up to 4K, available in various aspect ratios.

Nano Banana 2 supports character consistency for as many as five characters and maintains fidelity for up to 14 objects within a single workflow, improving storytelling capabilities. Users can also submit intricate and nuanced requests for image generation. Additionally, the model enables the creation of media with more dynamic lighting, richer textures, and enhanced detail.

With this launch, Nano Banana 2 will become the default model for image generation throughout all apps in the Gemini ecosystem. It will also serve as the default for image generation within Google’s video editing tool, Flow. In Search, Nano Banana 2 will be the standard for Google Search results via Google Lens and in AI Mode, available across 141 countries on the Google app and web platforms for both desktop and mobile.

Subscribers to Google’s higher-tier plans, Google AI Pro and Ultra, can continue using Nano Banana Pro for specialized tasks by regenerating images through the three-dot menu.

For developers, Nano Banana 2 will be accessible in preview through the Gemini API, Gemini CLI, and the Vertex API. It will also be available via AI Studio and the company’s development tool, Antigravity, which launched last November. All images generated with the new model will include a SynthID watermark, Google’s identifier for AI-created imagery. These images are also compatible with C2PA Content Credentials, a standard developed by an industry consortium that includes companies like Adobe, Microsoft, Google, OpenAI, and Meta. Since introducing SynthID verification in the Gemini app in November, Google reports it has been used more than 20 million times.