Google reveals new retro baby selfie trend as Nano Banan hits over 5 billion images in under a month
Google has said that its new Gemini 2.5 Flash Image model, also known as Nano Banana, has seen its popularity lead to over 5 billion images being created in less than a month since the AI tool first became available to the public. The AI image generator and editor is available for free on the Gemini app and has been powering various social media trends, including 3D Models, vintage sarees, polaroid selfies with celebrities, and more.
Josh Woodward, Vice President at Google, while announcing the figures in a post on X (formerly Twitter), wrote:
“🍌@GeminiApp just passed 5 billion images in less than a month. What a ride, still going! Latest trend: retro selfies of you holding a baby version of you. Can’t make this stuff up!” Woodward wrote.
Reacting to Woodward’s post, Google CEO Sundar Pichai created a 3D model of himself holding a dog using Nano Banana and posted, “Make that 5 billion and 1 😂”
What is Gemini Nano Banana? Why is it popular?
Gemini Nano Banana is the latest image generation and editing model developed by Google DeepMind. While there are a lot of free image generators on the market, Nano Banana is distinct for its ability to make complex edits to images, like removing objects from the background or changing the background altogether or a subject’s clothes, while keeping the overall image coherency intact.
While ChatGPT’s native image generation model had led to a similar kind of craze on social media, the OpenAI chatbot only allowed free users to generate very limited images. In contrast, Nano is not only faster but also allows users to generate many more images (we generated at least 6–7 images per day using Nano Banana), although Google doesn’t actually provide a specific number for that.
How to create retro selfies holding a baby version of you?
Open the Gemini app or website.
Tap on the Nano Banana icon.
Upload your desired image and then give Gemini a prompt or use one provided below.
Prompt 1:
“Create a fun, high-quality retro-style selfie where the adult in [Image 1] is holding the baby from [Image 2] as if they’re taking a casual smartphone selfie together.
Match lighting and skin tones so both look naturally in the same scene.
Add a subtle vintage/film filter—soft warm tones and slight grain.
Keep the adult’s current outfit and hairstyle from Image 1.
Make sure the baby remains clearly recognizable from Image 2 and is held comfortably in one arm.
Background: cosy indoor setting with gentle light, like a living-room or café vibe.”
Prompt 2:
“Create a realistic, high-quality photo of me (adult) holding a baby version of myself. The baby should look like my younger self from the uploaded childhood photo, but as a toddler/infant. The adult me should be in the same pose and clothing as in the uploaded current photo. The setting should be warm, nostalgic, and slightly retro—like a vintage family portrait with soft lighting and a timeless feel. Ensure the baby’s facial features, hair, and expressions closely match my childhood photo, and blend the two images seamlessly for a natural, heartwarming result.”
