Microsoft has silently launched a brand new synthetic intelligence (AI) characteristic for Copilot that can permit customers to transform a static 2D picture right into a 3D mannequin. Dubbed Copilot 3D, it’s a new experimental characteristic obtainable through Copilot Labs. The Redmond-based tech large mentioned that the characteristic shall be obtainable to all customers globally, offered they’re signed into their private Microsoft accounts. Whereas the tech large will not be the primary to supply such a characteristic, it claims that the 3D belongings generated utilizing Copilot are print and render-ready.

Copilot 3D Is Now Accessible to All Customers

Whereas the corporate didn’t make any announcement for the brand new characteristic, it has printed a brand new post to element it. Microsoft describes Copilot 3D as an AI-powered instrument that lets customers flip a picture into a totally rendered 3D mannequin. That is an experimental characteristic obtainable via Copilot Labs, and no paid subscription is required.

The corporate says the AI instrument makes the method of 3D asset creation straightforward and intuitive. Customers don’t want any data about 3D modelling. They’ll merely add a picture of as much as 10MB in dimension, and Copilot 3D will flip it right into a print and render-ready mannequin. These outputs will also be straight built-in into their gaming, animation, 3D printing, augmented actuality (AR) and digital actuality (VR) apps, and metaverse-focused digital content material initiatives.

In case a consumer doesn’t know methods to get began, they’ll additionally entry a Microsoft-curated library that includes distinctive scenes to behave as inspiration for customers. Notably, Copilot 3D at the moment solely helps 2D image-to-3D mannequin technology. It doesn’t assist text-to-3D at this second. The tech large recommends that customers entry this characteristic through Copilot on a desktop, though it will also be accessed through cell browsers.

Whereas Microsoft’s providing comes as an accessible and user-friendly technique to generate 3D fashions from 2D photographs, the tech large will not be the primary to supply such functionality. Final 12 months, Stability AI launched an open-source AI model, dubbed Stable Video 3D (SV3D), which carried out the identical operate. Tencent and Meta additionally launched their 3D asset technology fashions in 2024. This 12 months, Apple researchers released an open-source mannequin dubbed Matrix3D that may flip photographs into 3D fashions.