Google has unveiled the latest iteration of its widely used image generation model, Nano Banana 2. This new model, officially designated as Gemini 3.1 Flash Image, is engineered to produce more lifelike images than its predecessor. Significantly, Nano Banana 2 will now serve as the default image generation model within the Gemini app for its Fast, Thinking, and Pro modes.
The company initially introduced Nano Banana in August 2025, a launch that spurred users to generate millions of images within the Gemini app, particularly in regions such as India. Building on this success, Google released Nano Banana Pro in November, which offered users the capability to create images with enhanced detail and superior quality.
Nano Banana 2 integrates several high-fidelity characteristics inherited from the Pro model but distinguishes itself by delivering faster image generation. Google states that users can generate images with resolutions spanning from 512px up to 4K, supporting a diverse range of aspect ratios.
A notable advancement in Nano Banana 2 is its ability to maintain character consistency for up to five distinct characters and preserve the fidelity of up to 14 objects within a single workflow, thereby enhancing storytelling potential. Google also highlights that users can now submit intricate requests with nuanced details for image generation, resulting in media that boasts more vibrant lighting, richer textures, and sharper overall detail.
With its official launch, Nano Banana 2 is set to become the standard model for image generation across all integrated applications within the Gemini ecosystem. Furthermore, Google is implementing it as the default image generation model within its video editing tool, Flow.
In the realm of Search, Nano Banana 2 will be the default for Google Search results accessed via Google Lens and within AI Mode across 141 countries. This integration extends to both the Google app and the web, covering desktop and mobile platforms.
Subscribers to Google's premium plans, Google AI Pro and Ultra, will retain the option to utilize Nano Banana Pro for specialized tasks. This can be done by regenerating images through the dedicated three-dot menu, providing flexibility for advanced users.
For developers, Nano Banana 2 will be accessible in preview via the Gemini API, Gemini CLI, and the Vertex API. It will also be made available through AI Studio and Antigravity, the company's development tool that was launched last November.
Google has affirmed that all images generated using the new model will incorporate a SynthID watermark, which serves as the company's identifier for AI-generated content. These images are also compatible with C2PA Content Credentials, a standard established by an industry consortium that includes prominent companies such as Adobe, Microsoft, Google, OpenAI, and Meta. Google reported that since the introduction of SynthID verification in the Gemini app in November, it has been utilized over 20 million times.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.