Google launches Nano Banana 2 model with faster image generation

In an exciting development, Google has unveiled the latest iteration of its acclaimed image generation model, dubbed Nano Banana 2. This upgraded version, technically known as Gemini 3.1 Flash Image, boasts the ability to produce more lifelike images than its forerunner, setting a new standard in the Gemini app. Originally introduced in August 2025, the Nano Banana model quickly gained popularity, resulting in millions of images generated through the Gemini application, particularly in regions like India. Following this success, the company launched Nano Banana Pro in November, which enabled users to craft highly detailed and high-resolution images. Now, with the release of Nano Banana 2, users can expect rapid image generation while retaining many of the Pro model's high-fidelity features. The new model allows for image resolutions ranging from 512px up to 4K, with various aspect ratios to choose from. Additionally, Nano Banana 2 excels in maintaining character consistency for up to five characters and can handle the fidelity of 14 objects in a single workflow, enhancing storytelling capabilities. Users can also make intricate requests with specific details for image creation. With this launch, Nano Banana 2 will serve as the default image generation model across the entire Gemini suite, including the video editing tool Flow. Furthermore, it will be integrated into Google Search results through Google Lens and AI Mode in 141 countries on both mobile and desktop platforms. For those subscribed to Google AI Pro and Ultra plans, access to Nano Banana Pro remains available for specialized tasks, allowing for image regeneration via a simple menu option. Developers can experiment with Nano Banana 2 in preview mode through the Gemini API, CLI, and Vertex API, along with AI Studio and the recently introduced Antigravity development tool. To ensure transparency, every image generated with the new model will feature a SynthID watermark, indicating its AI-generated nature. These images will also comply with C2PA Content Credentials, a standard supported by an alliance of tech giants including Adobe, Microsoft, Google, OpenAI, and Meta. Since the introduction of SynthID verification in the Gemini app last November, users have reportedly leveraged this feature over 20 million times.