New AI model turns photos into explorable 3D worlds, with caveats

On Tuesday, Tencent launched HunyuanWorld-Voyager, an open-weights AI model that creates 3D-consistent video sequences from a single image, allowing users to navigate virtual scenes via a defined camera path. While it generates spatially consistent 2D video frames and depth information for 3D reconstruction, it does not replace traditional video games, producing short clips that can be extended into longer sequences.

Want More Context? 🔎