Google’s virtual try-on tool adds new outfits for your fit check

1 week ago 10
Graphic showing Google's virtual try on feature for dresses.

TL;DR

  • Google’s virtual try-on feature now supports women’s dresses from multiple brands.
  • The feature uses generative AI to create an image of a model wearing the dress.
  • It offers support for a diverse selection of models, allowing you to see how a dress would look on a person who has a similar body type.

Google introduced a new AI-powered shopping tool in Search last year, allowing users to see how a particular piece of clothing would look on a person with their body type. The virtual try-on feature debuted with support for women’s tops from multiple brands, and Google is now expanding it to support dresses.

Shoppers in the US will now see a “try on” badge when searching for dresses on Google. Selecting a dress with the badge will open the virtual try-on UI, featuring a carousel with a diverse selection of models ranging from sizes XXS-XXXL. Users can then select a model that closely matches their body type to get a better idea of how the dress looks before placing an order.

Google Shopping virtual try on for dresses preview.

Google says that it had to overcome multiple challenges to add support for dresses. It couldn’t simply use the same diffusion-based AI model it used for tops, as dresses “are often more detailed than a simple top in their draping, silhouette, length, or shape — and include everything from midi-length halters to mini shifts to maxi drop waists — plus everything in between.”

Researchers at Google developed a progressive training strategy to accurately recreate fine details, like pleats and prints, in the previews. They also came up with a new technique called VTO-UNet Diffusion Transformer (VTO-UDiT), which “isolates and preserves a person’s important features” in the generated image. You can check out the resulting images for yourself by searching for dresses from brands like Simkhai, Boden, Staud, Sandro, and Maje on Google.

Got a tip? Talk to us! Email our staff at [email protected]. You can stay anonymous or get credit for the info, it's your choice.

Read Entire Article