When I experimented with Google’s latest AI tool, the Nano Banana Pro, I was in for a surprise. Without any prompting, the AI began altering my clothing in a digital card creation. It seems the tool had its own ideas about how my image should be presented.

Designed with professionals in mind, the Nano Banana Pro is powered by the advanced Gemini 3. This tool is an upgraded version of Google’s image generation and editing software, which gained widespread attention by transforming selfies into detailed 3D figures. Google boasts that the tool can produce high-resolution images suitable for printing, overlay text onto images clearly, and seamlessly merge multiple images into one cohesive piece. “It’s also for those aspiring to feel like professionals,” explained Naina Raisinghani, a product manager at Google DeepMind, in a conversation with The Verge. While the tool certainly delivered visually appealing results, they sometimes felt more humorous than professional in my hands.

Using Nano Banana Pro is straightforward. You simply access the Gemini app, select “create images,” and activate the ‘thinking’ mode. You then input your desired prompt, along with an image if you have one. The service is free, but it does have limits, with increased quotas available for Google AI Plus, Pro, and Ultra subscribers.

Google makes ambitious promises with the Nano Banana Pro, claiming it can deliver “studio-quality designs” and “flawless text rendering” alongside a variety of creative edits. To put these claims to the test, I uploaded a simple photo of myself with the Brooklyn Bridge in the background, taken near The Verge’s New York office. I requested that the lighting be changed from day to night, and the AI executed this impressively, creating a convincing transformation. It even managed intricate details, like ensuring traffic moved in the correct direction. Adjusting the camera angle was similarly intuitive; I asked for a higher angle from the right, and it delivered.

Moreover, Google claims the Nano Banana Pro can generate infographics and diagrams for visualizing real-time data, such as weather or sports statistics. Curious about the weather, I inquired about the forecast for the next four days in Washington, DC, and New York City. The resulting infographic resembled what you’d find on a standard weather site. Unlike the usual AI-generated text chaos, the information was clear and accurate, complete with citations for verification.

The model stumbled a little on more complex tasks. I asked it to summarize a recent Verge story about how Europe is scaling back its AI and privacy laws in a comic book-style format. The images and text were indeed rendered flawlessly in a cartoonish font, but the comic didn’t summarize the story at all, giving a vague overview of the bloc’s AI Act instead. The issue may have been because I gave Gemini a link to the story, rather than pasting the text in.

It gave me a passable comic-style summary when I did. It communicated the gist of the actual story, though I don’t think I’d have been able to understand easily had I not written the source material. It also made up phrases that didn’t appear anywhere in my article.

To really feel like a pro designer, I tried my hand at making greetings cards. Christmas is coming up, after all. Considering I only uploaded three selfies, Gemini did a frankly amazing job creating three full-body versions of myself, each in different outfits and sporting a different facial expression. It also created a realistic, snowy setting with Christmas trees, like I’d asked it to, and plastered “Merry Christmas!” on the top like I’d asked it to.

Gemini took liberties when I asked it to change the card’s snowy backdrop to a summery beach for an Australian-style holiday. Those liberties were my deepfaked clothes: two of my clones were topless. It was weird. There were also some prominent AI-generated feet and a smiley sandman to replace the snowman from the wintery scene (being built by my topless lookalike). There were issues, though — the sandman was missing a shadow, unlike other rendered objects in the picture, and the Christmas lights in the palm trees were magically glowing in the bright sun. I tested its precision editing skills by asking it to add some muscle to only one clone, which it did in seconds (if only it were that easy in the real world). Overall, the quality was superb, and the image would’ve been somewhat believable (abs aside) if you didn’t know there was a large tattoo missing on my chest.

It wasn’t all great, though. The model failed to preserve the exact text on my card that I’d asked it to. Instead of “Merry Christmas!” it opted for “Aussie Summer Christmas!” It also seems to struggle with animals: my sister’s cat is sitting in exactly the same stilted pose as the reference image I’d provided in every version of the card (he was given a whimsical Santa hat, though).

All in all, I was impressed. Nano Banana Pro is a clear upgrade on the basic model. I was able to ask for more precise edits and it actually produces intelligible text, removing a massive roadblock stopping generative AI tools like this being usable in the real world. But, alas, these features were not enough to make me a good designer.