Google、AI機能を追加したNano Banana 2をリリース

2 Min Read

Google released an updated version of Nano Banana this week, advancing the popular AI image generator it launched in August.

Nano Banana 2, or Gemini 3.1 Flash Image to use its proper name, builds on the success of Google's Pro version launched in November, which enabled users to go into even more detail than the original. Now a new model is available, delivering what Google says is "high-quality, photorealistic imagery."

Naina Raisinghani, product manager at Google's DeepMind AI research lab, described the upgrade in a blog post as "state of the art," adding: "You get the advanced world knowledge, quality and reasoning you love in Nano Banana Pro, at lightning-fast speed."

The latest model makes use of Gemini's knowledge base, providing access to real-time information and images from web search, allowing more accurate rendering of subjects. Infographics and data visualizations are possible, while notes can be turned into diagrams.

Related:Mistral Pioneers Sovereign AI in Europe

There is now more scope for text, too, as might be needed on marketing mock-ups or greeting cards, including translation capability.

Google highlighted the ability to maintain character resemblance for up to five characters and the fidelity of up to 14 objects as a couple of the upgrades over the original. This improved consistency makes storyboarding and building narratives easier.

Nano Banana 2 can follow instructions more precisely, producing more nuanced imagery, while a wide range of specs are on offer, with resolutions from 512px to 4k, and a variety of aspect ratios, according to Google.

Plus the vendor said it produces images that are more striking visually, with "vibrant lighting, richer textures and sharper details."

Users have an array of options if they're interested in exploring the upgrade. On the Gemini app, Nano Banana 2 will replace Nano Banana Pro across the Fast, Thinking and Pro models, and it will also be used in the video editing tool Flow. It is also available via search in AI mode and Lens, the Google app and mobile and desktop browsers.

Google AI Pro and Ultra subscribers will retain access to Nano Banana Pro for specialized tasks, while developers will have access to the new version through AI Studio, Gemini API and Antigravity.

Google also confirmed that all images created via the model will feature a SynthID watermark to denote that they are AI generated. The SynthID feature has been used more than 20 million times since its launch in November.

About the Author

Contributing Writer

Graham Hope has worked in automotive journalism in the U.K. for 26 years, including spells as editor of leading consumer news website and weekly Auto Express and respected buying guide CarBuyer.