Google announced Nano Banana 2, technically named Gemini 3.1 Flash Image, which generates more realistic images faster than its predecessor. The model will become the default for image generation in the Gemini app’s Fast, Thinking, and Pro modes. Google first released the original Nano Banana model in August 2025, leading to millions of images generated in the Gemini app, particularly in countries like India. In November 2025, Google released Nano Banana Pro, which enabled users to create more detailed and high-quality images.
Nano Banana 2 retains high-fidelity characteristics from the Pro model but produces images faster, supporting resolutions from 512px to 4K and various aspect ratios. The model can maintain character consistency for up to five characters and fidelity for up to 14 objects in a single workflow, allowing for complex requests and improved storytelling. It enables media creation with more vibrant lighting, richer textures, and sharper details.
Nano Banana 2 will be the default image generation model across all apps in the Gemini app, in the video editing tool Flow, and in Google Search results via Google Lens and AI Mode across 141 countries on the Google app and web. Subscribers to Google AI Pro and Ultra plans can continue using Nano Banana Pro for specialized tasks by regenerating images via the three-dot menu. For developers, Nano Banana 2 is available in preview through the Gemini API, Gemini CLI, Vertex API, AI Studio, and the Antigravity development tool released in November 2025.
All images created with Nano Banana 2 will have a SynthID watermark to denote AI generation and are interoperable with C2PA Content Credentials, supported by an industry body including Adobe, Microsoft, Google, OpenAI, and Meta. Since the November 2025 launch of SynthID verification in the Gemini app, it has been used over 20 million times.
