Gemini can now see your Google Photos — and generate AI images of ‘you’ from them | Tech Radar

Overview

News, deals, reviews, guides and more on the newest computing gadgets

Start exploring exclusive deals, expert advice and more

Details

Unlock and manage exclusive Techradar member rewards.

Gemini can now see your Google Photos — and generate AI images of ‘you’ from them

Nano Banana 2 uses your pictures to fill in the details

When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

Unlock instant access to exclusive member features.

Get full access to premium articles, exclusive features and a growing list of member rewards.

Gemini can now browse a vast library's worth of images about you and produce its own AI creations that are based on them. The AI chatbot's Personal Intelligence features, designed to help Gemini adapt to your preferences and personality, are now, with your permission, able to browse your Google Photos library.

The Nano Banana 2 image-making model can then use that information to shape its visuals without lots of explanation on your part.

Instead of carefully writing prompts that explain your appearance, your environment, or your general vibe, you can simply say “me” and let the system handle the rest. Once you give Gemini permission to access your photos, you type a prompt as usual. The difference is that Nano Banana 2 now fills in the blanks using what it already knows. The output is not just based on your words, but on a version of you assembled from your own images.

Nano Banana 2 shows off its powerful image creation enhancements

I upgraded my AI image prompts using Gemini’s advice: it changed everything

To see how well Gemini now knew me, I gave it a fairly open-ended prompt. “Create a cinematic scene from my life as if it were a movie.”

The result leaned heavily into an atmosphere of anticipation. A very good AI likeness of me stares pensively out at the rain in some sort of old hotel. I am apparently planning a big adventure, judging from the notebook, compass, and small plane outside, but I look as if I haven't made a decision.

It's essentially a more dramatic version of many photos of me on trips or in hotel lounges with guidebooks. A cinematic, more narratively interesting version of many of my photos.

Next, I wanted to see if Gemini would still be able to recognize me if it put me in a less realistic setting. So I asked it to "turn me into a character in a fantasy adventure.”

This time, realism disappeared in favor of scale and spectacle. I was placed on a winding stone path that stretched toward a towering castle carved into a mountainous landscape. My clothes had transformed into layered armor and leather, complete with a satchel marked by glowing symbols. A staff replaced the compass, emitting a faint light, while strange creatures hovered nearby as if they were part of the same ecosystem.

Despite the setting, the continuity was impressive. The face was clearly mine, not a generic placeholder but a direct translation from my photos. The expression, slightly serious, slightly focused, carried over without exaggeration. Even the posture felt familiar.

That consistency made the image more effective than it might have been otherwise. It did not feel like a fantasy character loosely inspired by me. It felt like me inserted into a fantasy world, which is a very different experience. The system was not inventing a new identity. It was adapting an existing one.

5 prompts for Gemini 3.1 that show off its full potential

Chrome puts AI agents, multitasking, and Nano Banana inside the browser

As Gemini had proven it knew what I looked like and what a movie version of me might be like, I asked for a more holistic, if over-the-top interpretation. I asked Gemini to “create an image of me doing my favorite hobbies in an extreme or exaggerated way.”

The result was far less restrained. I appeared in a vividly stylized scene that blended multiple interests into a single, energetic composition. Books floated midair, pages turning as if caught in a controlled storm. A small plane cut across the background, while futuristic cityscapes and distant planets filled the horizon. I was mid-motion, holding objects that hinted at different pursuits, reading, exploring, creating, all dialed up beyond anything that would happen in real life.

The tone was exaggerated but not random. Each element seemed to connect back to something the system had inferred from my photos and context. Except for the wings. I don't know what they were about, and Gemini seemed at a loss to explain the reason behind it. The illustrative style was bold, but even so, the underlying likeness remained consistent.

The feature sets up a much more powerful way to teach Gemini about yourself. Traditional AI image generation depends heavily on how well you describe what you want. Here, description becomes secondary. The system is already working from a base layer of information.

Prompts become shorter and easier to write, and results feel more specific without requiring extra effort. How comfortable you are in sharing that information with Google is another question, of course. The company is good at encouraging people to upload their life story, but in this case, if you already use Google Photos, you're not adding to the database Google already hosts for you. And the frictionless way you get from a brief idea to a personalized artwork is undeniably appealing. Even if it makes you part bird for no particular reason.

Follow Tech Radar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!

And of course you can also follow Tech Radar on Tik Tok for news, reviews, unboxings in video form, and get regular updates from us on Whats App too.

➡️ Read our full guide to the best business laptops

1. Best overall: Dell Precision 5690
2. Best on a budget: Acer Aspire 5
3. Best Mac Book: Apple Mac Book Pro 14-inch (M4)

Eric Hal Schwartz is a freelance writer for Tech Radar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as Open AI’s Chat GPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.

You must confirm your public display name before commenting

1'No barbell, no special equipment and no gym membership required': the forward lunge is the best simple move you're not doing, and it's vital for over-50s

2 Creality Sermoon S1 review: This pro-grade 3D scanner produced impressive results, but my tests revealed a huge learning curve

3I swapped my phone for a cycle computer after a crash — but a tiny, underrated device was the real safety upgrade

4'Global, 24/7, all-weather reconnaissance coverage': China deployed "Eye of Sauron" satellite that can track ships — and the US Navy — from its safe sky abode

5NYT Strands hints and answers for Saturday, April 18 (game #776)

Tech Radar is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site.

© Future US, Inc. Full 7th Floor, 130 West 42nd Street, New York, NY 10036.

Key Takeaways

• News, deals, reviews, guides and more on the newest computing gadgets

• Start exploring exclusive deals, expert advice and more

• Unlock and manage exclusive Techradar member rewards

• Gemini can now see your Google Photos — and generate AI images of ‘you’ from them

• Nano Banana 2 uses your pictures to fill in the details