Google has released Nano Banana 2, the latest version of its image generation model, introducing higher realism, faster performance, and broader integration across its products. The model, technically named Gemini 3.1 Flash Image, will become the default image generator in the Gemini app, Google Search, and other Google tools.
Model Improvements And Capabilities
Nano Banana 2 builds on earlier versions released in August 2025 and November 2025. The original Nano Banana prompted millions of image generations in the Gemini app, particularly in markets such as India. The November release, Nano Banana Pro, enabled more detailed and higher quality image creation.
Google said Nano Banana 2 retains some of the high fidelity characteristics of the Pro version while producing images more quickly. Users can generate images in resolutions from 512 pixels up to 4K, across different aspect ratios. The model can maintain character consistency for up to five characters and preserve fidelity for up to 14 objects within a single workflow, which Google says supports more coherent storytelling. The company added that users can submit complex prompts with detailed nuances and generate images with more vibrant lighting, richer textures, and sharper detail.
Integration Across Google Products
Nano Banana 2 will now serve as the default image generation model in all modes of the Gemini app, including Fast, Thinking, and Pro. It will also become the default model for image generation in Google’s video editing tool, Flow.
In Google Search, Nano Banana 2 will power image results through Google Lens and in AI Mode across 141 countries, available both in the Google app and on the web for desktop and mobile users.
Subscribers to Google AI Pro and Google AI Ultra plans will continue to have access to Nano Banana Pro for specialized tasks by regenerating images through the three dot menu.
Developer Access And Watermarking
For developers, Nano Banana 2 will be available in preview through the Gemini API, Gemini CLI, and the Vertex API. It will also be accessible via AI Studio and Antigravity, Google’s development tool introduced in November.
Google said all images generated with Nano Banana 2 will include a SynthID watermark, its system for marking AI generated content. The images will also support interoperability with C2PA Content Credentials, a standard developed by an industry group that includes Adobe, Microsoft, Google, OpenAI, and Meta. Google said that since launching SynthID verification in the Gemini app in November, users have accessed the tool more than 20 million times.
Featured image credits: Flickr
For more stories like it, click the +Follow button at the top of this page to follow us.