Google Gemini’s new image generator, Gemini 2.5 Flash Image, colloquially called Nano Banana, has captured the imagination of the masses in the last few days, with users on social media using their creativity to power many interesting trends like 3D models, vintage sarees, and stylish portraits.
While it makes sense for most users to be blown away by the advanced capabilities of Nano Banana, the model’s advanced capabilities allow users to make complex edits to images while retaining facial detail and overall visual coherence. However, what may come as a surprise to many people is that Nvidia CEO Jensen Huang, whose company’s GPUs are responsible for handling computing for most AI companies, is also equally impressed by the new model.
Jensen Huang on Nano Banana:
”How could anyone not love Nano Banana? I mean Nano Banana, how good is that? Tell me it’s not true!” Huang was quoted as saying by WIRED.
”Tell me it’s not true! It’s so good. I was just talking to Demis [Hassabis, Google DeepMind CEO] yesterday and I said, ‘How about that Nano Banana! How good is that?'” he added.
Huang also talked about how using AI chatbots has helped improve his learning and thinking while helping him access knowledge more efficiently.
”I use it (AI) every day, and it’s improved my learning, my thinking. It’s helped me access information, access knowledge a lot more efficiently. It helps me write, helps me think, it helps me formulate ideas. So my experience with AI is likely going to be everybody’s experience. I have the benefit of using all the AI—how good is that?”
Gemini Nano Banana trend:
Google had launched the Nano Banana model late last month, and the model has been slowly catching pace since then. The new model has been used to generate over 300 million images already, as per Josh Woodward, Vice President of Google Labs and Google Gemini.
While there are plenty of other AI image generators and editors out there, Gemini Nano Banana has become a preferred option among the masses owing to its speed, along with the ability to maintain consistency in subjects across different prompts. In practical terms, this meant that users were able to transport their images into 3D figurines or stylish portrait shots without the end product looking like a random image, due to Nano Banana retaining the facial textures.
