Google AI Try-On Now Works With Just a Selfie

Google is simplifying its virtual shopping experience by allowing users to try on clothes using only a single selfie. Announced this Thursday, the update removes the previous requirement for users to upload full-body photos to visualize apparel.

The new functionality leverages Nano Banana, which is part of Google’s Gemini 2.5 Flash Image model. This technology processes a standard selfie to generate a full-body digital representation of the user, facilitating a more accessible virtual fitting room experience.

How the Updated Feature Works

Once a user uploads their selfie and selects their preferred clothing size, the system generates several images. Users can then designate one of these outputs as their default photo for future try-ons. Flexibility remains a priority, as Google continues to offer:

• The ability to use traditional full-body photos.
• The option to select from a diverse range of models with various body types.

This update is currently rolling out to users in the United States.

Expanding the AI Shopping Ecosystem

Google’s virtual try-on tool, which debuted in July, integrates with the company’s Shopping Graph across Search, Google Shopping, and Google Images. Users access it by tapping the “try it on” icon on eligible product listings.

The company is also pushing further into this space with its dedicated app, Doppl, which helps visualize outfits using AI. Earlier this week, Google enhanced Doppl with a shoppable discovery feed. This feed provides personalized style recommendations and AI-generated videos of products, mirroring the interface style popularized by platforms like TikTok and Instagram to drive direct engagement with merchant inventory.