Cover Tatler generated this image of a nano banana using Gemini 2.5 Pro, just to see how effective AI imagery is. Not bad, eh?
Tatler generated this image of a nano banana using Gemini 2.5 Pro, just to see how effective AI imagery is. Not bad, eh?
1 / 1
No, it’s not a micro fruit; Nano Banana is Google’s new AI image editor that offers professional-level photo editing to everyday users through simple text commands
Google has launched the viral Nano Banana AI image editing tool that has been making waves across social media platforms. Officially called Gemini 2.5 Flash Image, this state-of-the-art model was introduced on August 26, 2025, and represents a significant leap forward in AI-powered image manipulation.
Google explains on its website: “Gemini lets you combine photos to put yourself in a picture with your pet, change the background of a room to preview new wallpaper or place yourself anywhere in the world you can imagine—all while keeping you, you.”
Experts have already voiced concerns about this model being misused to generate deepfakes, such as manipulating the images of dead historical figures to generate ahistorical photos.
Also read: Zac Liew speaks on reinventing fintech, balancing innovation with trust and the power of AI
What makes Nano Banana special?
The model excels at natural language image editing, allowing users to blur backgrounds, remove stains, change poses or even delete people simply by describing what they want. Unlike traditional photo editing software that requires technical expertise, Nano Banana works through conversational commands: you simply tell it what changes you’d like to see.
One of its standout features is multi-image fusion and consistency, which means it can seamlessly combine multiple photographs. So, you can just drop a product into a new scene, maintain character consistency across multiple frames or reinterpret images using the AI’s vast knowledge base.
Accessibility and integration of Nano Banana
The model has achieved the top rating amongst image editing tools globally and is now integrated directly into Google’s Gemini app. It's also available to developers through Gemini API, AI Studio and Vertex AI platforms, making it accessible to both casual users and professional developers.
Also read: How AI, Gen Z and social media filters are reshaping beauty
Safety concerns around Nano Banana
This launch represents Google’s response to OpenAI's earlier move in March 2025, when it added image generation to GPT-4, intensifying competition in the AI image generation space. With its conversational editing approach and professional-grade results, Nano Banana is positioning itself as a game-changer for across industries.
But there are growing concerns about deepfakes and misinformation in this era of increasingly sophisticated AI imagery. Google’s response to it is that every image carries a SynthID watermark and metadata tag to identify it as AI-generated—but these can be cropped out using other tools.
Google also said that all images will sport an invisible SynthID digital watermark, which should be picked up by the company’s own SynthID Detector. However, this is not yet widely accessible—so an average user will have no way of knowing if a picture is real or generated by Nano Banana.
At the end of the day, as with many other AI-generated content, human intent and ethics continue to feature heavily in this conversation.
Topics
Suchetana Mukhopadhyay is the Digital Content Manager for Tatler Hong Kong. In this role, she leads all digital editorial and branded content on Tatler Hong Kong’s website, from brainstorming story ideas with the writers to editing and publishing the articles, and from managing the overall content flow to driving search engine optimisation. She also leads the beauty content at Tatler Hong Kong and across the region, and is always looking to champion diversity through her articles. She was previously with Cedar Hong Kong and Gafencu, and freelanced for the South China Morning Post, Campaign Asia-Pacific, CNN and more. Contact her here.
