Google has expanded its virtual try-on shopping feature to allow users to generate digital versions of themselves from selfies, eliminating the need for full-body photographs.
According to the company's announcement, U.S. shoppers can now upload a simple selfie and receive studio-quality, full-body images generated by artificial intelligence. The feature uses Nano Banana, Google's Gemini 2.5 Flash Image model, to create the digital representations.
The process requires users to upload a selfie at g.co/shop/tryon and select their usual clothing size. The system then generates several studio-like images, from which users can choose one as their default try-on photo. Once set up, shoppers can virtually try on items from billions of product listings in Google's Shopping Graph.
The technology aims to address common pain points in online clothing shopping. The company positioned the feature as an alternative to poorly lit dressing room photos and awkward outfit selfies.
Users retain existing options for the try-on tool. According to Google, shoppers can still use full-body photos if they prefer, or select from a range of models representing diverse body types provided by the platform.
The feature is currently available only to shoppers in the United States. Google did not specify whether expansion to other markets is planned.
Virtual try-on technology has gained prominence in e-commerce as retailers seek to reduce return rates and increase customer confidence in online purchases. By allowing shoppers to visualize how clothing might look on their body type before purchasing, such tools aim to bridge the gap between physical and digital shopping experiences.
The new selfie-based feature represents an evolution of Google's existing virtual try-on tool, which previously required full-body photographs. The integration of the Gemini 2.5 Flash Image model demonstrates the company's application of its artificial intelligence capabilities to consumer shopping tools.
I truly appreciate you spending your valuable time here. To help make this blog the best it can be, I would love your feedback on this post. Let me know in the comments: How could this article be better? Was it clear? Did it have the right amount of detail? Did you notice any errors?
If you found it valuable, please consider sharing it.