Discover how Google’s AI model ‘ Gemini Nano Banana’ got its unusual name, from a late-night placeholder to a viral favorite, and how it is redefining AI image generation with creativity and ... Nano Banana (officially Gemini 2.5 Flash Image) is an image generation and editing model powered by generative artificial intelligence and developed by Google DeepMind, a subsidiary of Google. A text-to-image variant of the Gemini family of large language models, it was launched in August 2025 as a feature within the Gemini chatbot and other Google products. " Nano Banana" was the codename used for the model while it was undergoing secret public testing on LMArena. Upon release, it became a ... Gemini Nano brings Google AI directly to your phone, processing data locally, protecting privacy, and speeding up responses. The list of compatible phones includes Google Pixel, Samsung, Xiaomi, Motorola, and realme, with features varying by model and chipset. Only the Google Pixel 9 has access to the multi-modal variant of the Gemini Nano , capable of processing images, audio, and voice in addition to text. Gemini Nano brings multimodal capabilities to Pixel. In addition to text, your Pixel will soon be able to understand more information in context like sights, sounds and spoken language.
