Google launches Nano Banana 2 model with faster image generation

Google has launched Nano Banana 2, the latest iteration of its viral image generation model, officially designated as Gemini 3.1 Flash Image. This update makes the model the new default across Google's ecosystem, replacing its predecessor in the Gemini app's Fast, Thinking, and Pro modes. The rollout extends its reach significantly, integrating it as the default generator in Google Search results via Google Lens and AI Mode, available across 141 countries on web and mobile platforms. This strategic deployment follows the original Nano Banana's massive adoption, which saw users generate millions of images, particularly in regions like India, after its August 2025 debut.

The technical upgrades in Nano Banana 2 focus on speed and compositional fidelity. It retains the high-quality characteristics of the November 2025 Nano Banana Pro model but processes requests faster. Key capabilities include maintaining character consistency for up to five distinct characters and tracking fidelity for up to 14 objects within a single workflow, enabling more complex storytelling. The model supports resolutions from 512px up to 4K in various aspect ratios and promises more vibrant lighting, richer textures, and sharper detail. For developers, it's available in preview via the Gemini API, Vertex API, and AI Studio. All generated images will carry Google's SynthID watermark and be interoperable with C2PA Content Credentials, building on a verification tool used over 20 million times since November.