I turned myself into a 3D figurine with Google's Nano Banana - here's how you can hop on the latest AI image trend

Google’s latest image model, Gemini 2.5 Flash Image, also known as Nano Banana, has produced a fun new trend using its advanced image capabilities. You can turn yourself (or your pet) into a highly detailed 3D figurine.

All you need to do is upload a photo and employ a very detailed prompt to have a stylized image of a miniature, plasticized version of the subject, posed on a little clear base, less than a minute later, with a box and even a wire-frame model to show it off.

This particular flavor of AI-generated toy is exploding across social media right now because the model is fast, free, and surprisingly good at what it does. Unlike earlier versions of these kinds of prompts that ran on GPT-4o or Midjourney, Nano Banana has better prompt adherence, understands packaging and posing more consistently, and renders faces that, while not always perfect, are often impressively accurate.

It’s all built into Google AI Studio and the Gemini apps and website if you want to try it. You just have to upload a picture, ideally a full-body shot, of who or whatever you want to make into a figurine, and submit the right prompt. You can play around with it, but the following template, shared around on social media, works very well.

Type this in:

“Create a 1/7 scale commercialized figurine of the characters in the picture, in a realistic style, in a real environment. The figurine is placed on a computer desk. The figurine has a round transparent acrylic base, with no text on the base. The content on the computer screen is a 3D modeling process of this figurine. Next to the computer screen is a toy packaging box, designed in a style reminiscent of high-quality collectible figures, printed with original artwork. The packaging features two-dimensional flat illustrations.”

When you paste that into Gemini, along with a photo, it doesn’t just try to render a toy version of what’s in the picture, it imagines the toy existing in the real world, with all the context that goes along with a premium 3D figurine release. It's like a high-end collectible a company would make if you became famous for whatever pose you you're in.

Toying with AI

I went with fun photo of myself from a big circus-themed party a few years ago where I went as a lion tamer (see the small lion in my pocket). I shared the photo with Nano Banana along with the prompt and twenty seconds later, there "I" was, six inches tall, standing on a desk and looking jaunty with my whip like I was about to command a herd of miniature jungle cats.

The packaging beside me showed a great illustrated version of the same pose, except it decided I was the ringmaster and named Rhett for some reason. The computer screen behind the figurine showed a 3D modeling window open with “my” miniature wire-frame form on it, being rotated in space like it was being finalized for mass production.

It genuinely looks like a photo, right down to the scuffed desk and random paperwork. Even the stuffed lion in my pocket looked right. It felt like an alternate version of me had been shrink-wrapped and made collectible.

Puppy pose

Next, I decided to try with a photo of my dog, Cabbage. I uploaded a picture of her sitting regally on the ground and used the same default prompt. The toy created by the AI was almost too realistic. I had to look closely to tell it's supposed to be made of molded plastic.

The screen behind the figure showed the hound rendered in a 3D modeling program appropriately, but the packaging went a little awry. It had multiple images of the dog like it was a test of different poses. But I did like that, lacking her real name, the AI went with her bandanna to name her Firecracker Fido.

The thing that struck me after both generations was how smoothly it all worked. No fine-tuning needed to get 95% of the way there. The Nano Banana just understood the visual reference and ran with it. I wouldn't claim it's anything like as valuable as what real human artists can do, but it was a fun experiment.

Much like the Studio Ghibli AI image trend, it's worthwhile for personal amusement, but the idea of using these images for any kind of money-making scheme to sell actual toys would be several steps beyond propriety.

You might also like

• Google’s Gemini app is getting better at editing photos – here’s what I liked, and what I didn’t
• I refuse to jump on ChatGPT’s Studio Ghibli image generator bandwagon because it goes against everything I love
• Google’s Gemini app is getting better at editing photos – here’s what I liked, and what I didn’t