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

September 3, 2025

•

1 min read

•

Ars Technica

Openly available AI tool creates steerable 3D-like video, but requires serious GPU muscle.

On Tuesday, Tencent released HunyuanWorld-Voyager, a new open-weights AI model that generates 3D-consistent video sequences from a single image, allowing users to pilot a camera path to "explore" virtual scenes. The model simultaneously generates RGB... [1709 chars]

Read Original Article

Source: Ars Technica

Visit Source

Share this article

Twitter Facebook

Back to technology news