Google has unveiled Nano Banana 2, its latest AI image generation model, marking a significant upgrade. The model, technically known as Gemini 3.1 Flash Image, delivers faster performance, higher precision, and improved text rendering compared to its predecessor.
A key improvement is broader availability: Nano Banana 2 brings Pro-level capabilities to all Gemini users for free, not just paid subscribers. It can generate images from 512 pixels up to 4K resolution in multiple aspect ratios and handles complex prompts more accurately.
Google claims the model maintains better consistency, preserving character resemblance for up to five characters and object fidelity for up to 14 objects in a single workflow. It also promises more vibrant lighting, richer textures, and sharper details.
Nano Banana 2 is now the default image generator across Google's ecosystem, including Gemini, Search AI mode, Lens, and developer tools like AI Studio and the Gemini API. For safety, Google is integrating its SynthID watermarking with C2PA Content Credentials to provide clear attribution for AI-generated images.