Google released an updated version of Nano Banana this week, further enhancing the popular AI image generator launched in August.
Nano Banana 2, or Gemini 3.1 Flash Image, to use its proper name, is based on Google’s success Pro version launched in NovemberWhich enabled users to go into even greater detail than the original. A new model is now available, which according to Google provides “high-quality, photorealistic imagery.”
Naina Raisinghani, product manager at Google’s DeepMind AI research lab, described it Upgrade to a Blog Post As for “cutting edge”, he added: “You get the advanced world knowledge, quality and logic you love at lightning-fast speed in Nano Banana Pro.”
The latest model uses Gemini’s knowledge base, which provides access to real-time information and images from web searches, allowing more accurate rendering of subjects. Infographics and data visualizations are possible, while notes can be converted into diagrams.
There is now also more scope for text, as may be required on marketing mock-ups or greeting cards, including translation capability.
Google highlighted the ability to maintain character similarity up to five characters and fidelity of up to 14 objects as some upgrades compared to the original. This improved consistency makes storyboarding and narrative creation easier.
According to Google, the Nano Banana 2 can follow instructions more accurately, and produce more subtle imagery, while offering a wider range of specifications with resolutions from 512px to 4k and a variety of aspect ratios.
The vendor also said it produces images that are more visually appealing with “vibrant lighting, rich textures and sharp details.”
If users are interested in exploring an upgrade they have a range of options. On the Gemini app, the Nano Banana 2 will replace the Nano Banana Pro in the Fast, Thinking, and Pro models, and will also be used in the video editing tool Flow. It is also available through AI mode and Lens, Google app, and search in mobile and desktop browsers.
Google AI Pro and Ultra customers will retain access to Nano Banana Pro for specific tasks, while developers will have access to the new version through AI Studio, Gemini API, and AntiGravity.
Google also confirmed that all images created through the model will have a SynthID watermark indicating that they are created by AI. The SynthID feature has been used more than 20 million times since its launch in November.
