The power of the new ChatGPT Images 2.0 has sparked a new online trend for connecting your past with your present. People are combining childhood pictures with present-day portraits to create a single, carefully staged image that feels like a meeting across time.

The idea is simple and surprisingly effective. You upload one photo from your childhood and one from today, then guide the AI to place both versions of you into the same scene. The result is not just a side-by-side comparison. It looks like a shared moment, lit and composed as if it were photographed in a studio. It's not an entirely original idea, but ChatGPT Images 2.0 gives it a lot more power with the right composition and tone. The most popular version going around uses a prompt similar to this:

“Using the two uploaded images, create a black-and-white portrait. On the left, place the childhood version facing right. On the right, place the present-day version looking toward the child. In the center, set a table with a birthday cake displaying my current age. Make the image ultra-realistic with natural skin texture."

That level of detail matters. Modern image systems like those powering ChatGPT can interpret precise spatial instructions, meaning you can decide where each subject sits, how they look at each other, and even how light falls across the scene. The more grounded the instructions, the more cohesive the result.

The two versions of me shared the same lighting and shadows, which helped blend the decades between them. The black-and-white styling removed distractions and gave the scene a quiet, reflective tone. The birthday cake at the center acted as a small anchor, tying the moment to the present without overwhelming the composition.

What makes this trend stand out is how restrained it is. Earlier waves of AI imagery leaned toward fantasy, turning people into superheroes or animated characters. This approach is almost the opposite.

Library pals

Once you have the basic version, it becomes tempting to push the idea further. Using the same two photos, I tried a second, more active prompt:

“Using the uploaded images, create a realistic indoor scene at a library where both versions of me are engaged in reading some of my favorite books."

The result did exactly that, putting the two versions of me in a library, and, all on its own, picking out books by one of my favorite authors for us to both read. Particularly impressively, the book my younger self is reading is one aimed at children specifically.

It also showed how flexible these tools have become. With the same two source photos, the AI can move characters into different settings while keeping them looking the same. The trick is to be just as specific about the new setting as you were with the original composition.

There is still a limit to how perfect these images can be. Small inconsistencies in hands or textures occasionally appear, and expressions may need a second attempt to feel natural. Even so, the overall quality is high enough that the illusion holds.

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

Eric Hal Schwartz is a freelance writer for TechRadar 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 OpenAI’s ChatGPT, 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.