Google announced Thursday that it has expanded its AI-powered virtual try-on tool to support dresses, allowing users to virtually try on thousands of dresses from hundreds of brands, including Boden, Maje, Sandro, Simkhai and Staud.

Dresses are one of the most popular categories within toolwear, the company said. However, as Google explained in today's blog post, its current distribution methodology is more difficult and more complicated than other clothing, so it is difficult to use in dresses.

To provide more contexts, Google Shopper has released a tool last year using its own diffusion technology to create high -quality and important images. It simulates the way clothing drapes, folds, catches, wrinkles and shadows on real people in a variety of poses.

Due to the intricacy of the details in the dress, existing popular models have difficulty accurately capturing the fine prints on the dress, such as floral and geometric patterns. While the model can handle low-resolution images, in the case of the dress it needed a different approach to ensure important details weren't lost. To address this issue, Google said it developed a new training strategy that starts with low-resolution images and gradually introduces higher-resolution ones.

 Additionally, because dresses typically cover large parts of the body and come in a variety of lengths (midi, maxi, mini, etc.), putting a virtual dress on a person often obscures or blurs bodily details. A new technique called VTO-UNet Diffusion Transformer (VTO-UDiT) aims to solve this problem by erasing and replacing the dress while preserving the person's features, resulting in a more accurate representation of the dress and the person wearing it.

Virtual try-on technology aims to take the guesswork out of finding the right solution for customers of all body types, with various companies (Adobe, Amazon, Walmart) launching their own tools that allow customers to try on almost any type of garment, including dresses. But with this new extension, Google seems to be aiming to create a more advanced feature than its competitors.