Within just a few days of launching, Google’s VP, Josh Woodward posted on X that the Gemini app has over 10 million new users thanks to Nano Banana. If you’ve tried it, than you already know why users from all over the world are flocking to Google’s new AI image generation and editing tool.
Built directly into Gemini, this ultra-fast model focuses on visuals at much higher speeds than ChatGPT or even MidJourney. Baked right into the Gemini ecosystem, 200 million images have already been generated or edited, and it has spurred a number of viral trends that I just couldn’t wait to try. Here’s what happened when I tried them, as well as the prompts you can use to try them for yourself.
Turn yourself into an action figure
Prompt: "Take this photo of me and turn me into a collectible figurine inside a toy box. The box should include a clear window to show the figurine, bold graphics, and my name on the packaging. Style the figurine in a fun, toy-like way but keep my likeness recognizable. Make it look like an authentic action figure you’d find on a store shelf."
Similar to the ChatGPT-4o trend, Gemini takes the trend to the next level by generating a better image that better resembles the user, faster.
See yourself in a different decade
Prompt: "Take this photo of me and transform me into a 1980s character, with big hair, neon clothes, and a retro mall arcade in the background. Update my clothing, hairstyle, and background to match the era. Make it look like an authentic portrait from that decade, with accurate fashion, colors, and overall style."
Try other decades by using these additions to the prompt:
1920s: "Transform me into the 1920s, styled like a flapper-era portrait with vintage sepia tones, short bob haircut, and art deco patterns in the background."
1950s: "Show me in the 1950s, wearing retro diner-style fashion with a poodle skirt and leather jacket vibe, placed in front of a neon jukebox."
1970s: "Turn me into a 1970s disco look, complete with bell-bottoms, platform shoes, and colorful light patterns."
1980s: "Make me look like an 80s character, with big hair, neon clothes, and a retro mall arcade in the background."
1990s: "Reimagine me in the 90s, dressed in grunge or sitcom fashion, standing in a Blockbuster video store."
Take yourself ‘back to the future’ by placing yourself in different decades. This one is a lot of fun, especially if you try a variety of decades. Pro tip: ask Gemini to generate several decades all at once so you can see them all side-by-side.
Add yourself to any TV show
Prompt: "Create a realistic image of me sitting with Jerry, Elaine, George, and Kramer in Jerry’s apartment from the TV show Seinfeld. I’m part of the group, sitting on the couch with them, laughing as if I just delivered a punchline. Make sure the scene looks like a classic episode, with Jerry’s kitchen in the background and the group’s casual 90s outfits. Include me seamlessly in the style of the show."
One thing I've noticed after testing hundreds of Nano Banana prompts is that if you want the best possible outcome, upload a picture of you doing what you want to be doing in the Nano Banana scene. For example, upload yourself sitting if you want to be sitting.
Integrating into famous art
Prompt: "Take this photo of me and insert me into Edvard Munch’s The Scream. Paint me in the same expressionist style, with bold swirling colors and dramatic brushstrokes. Place me standing on the bridge alongside the central screaming figure, blending seamlessly into the eerie, emotional atmosphere of the painting."
More prompt examples to try:
Mona Lisa (Leonardo da Vinci):
"Insert me into Leonardo da Vinci’s Mona Lisa. Place me next to the original subject, painted in the same Renaissance style with soft lighting and muted colors."
Starry Night (Vincent van Gogh):
"Place me into Vincent van Gogh’s Starry Night, painted in the same swirling brushstroke style, standing beneath the starry sky in harmony with the scene."
The Persistence of Memory (Salvador Dalí):
"Add me to Dalí’s The Persistence of Memory. Show me in surreal form, painted with melting features and dreamlike colors to match the surrealist style."
American Gothic (Grant Wood):
"Put me into Grant Wood’s American Gothic, holding a pitchfork beside the farmer and painted in the same realistic 1930s style."
I had to try this a few times because the image didn't always come out. As in, not at all. When I asked for the Mona Lisa, all I got was two Mona Lisa images side-by-side. Out of all the prompts, this one was probably the hardest. If you try this one, let me know your thoughts in the comments.
Famous landmarks and people
Prompt: "Take this photo of me put me sitting on top of the Hollywood Sign, waving at the city below.. Make it look realistic, with accurate lighting, shadows, and perspective so it feels like I’m actually there. Keep the landmark clear and recognizable and match the overall atmosphere of the location."
More prompt examples to try:
Eiffel Tower (Paris):
"Put me in front of the Eiffel Tower on a sunny afternoon, dressed casually, with tourists and city life around me."
Great Wall of China:
"Place me walking along the Great Wall of China, with the winding wall stretching into the mountains behind me."
Taj Mahal (India):
"Insert me into the gardens in front of the Taj Mahal at sunrise, with the monument reflecting in the water."
Statue of Liberty (New York):
"Show me standing near the Statue of Liberty, with the New York skyline in the background and bright daylight for realism."
Pyramids of Giza (Egypt):
"Place me next to the Pyramids of Giza, with desert sand and camels nearby, blending naturally into the historic scene."
For the second one, I had a little extra fun and asked Gemini to combine two pictures. One of me and one of Harry Styles using the prompt: "Combine these two photos and place the people together in the same scene. Make it look natural and realistic, with consistent lighting, shadows, and background. Position them so they appear to be hanging out casually, smiling and interacting as if the photo was taken in one moment."
This was my favorite prompt, naturally.
Final thoughts
Nano Banana is a blast and easily one of my favorite image generators. It's fast, mostly accurate and does more than other image generators I've tested. It’s shaping trends as more users discover how easy it is to create images with a single prompt.
The best way to understand its appeal is to try it yourself, experiment with prompts and see how far you can push its creativity. Just remember, it’s not always perfect. Sometimes the results are a little off, and it may take a few tries with new photos or extra prompting to get exactly what you want. But if you ask me, that trial-and-error is part of the fun.
Follow Tom's Guide on Google News to get our up-to-date news, how-tos, and reviews in your feeds. Make sure to click the Follow button.
More from Tom's Guide
- OpenAI launches 'OpenAI for Science' initiative to build the ‘next great scientific instrument’ – here’s what we know
- I tested ChatGPT-5 vs Gemini Nano Banana with 9 AI image prompts — and there's a clear winner
- 5 hidden ChatGPT-5 settings you should enable right now
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.
