Hunyuan World Model 1.1 Open Source: Supports multiple views and video input, single-card deployment, and second-level generation.

Tencent has released and open-sourced the Hunyuan World-Mirror model 1.1. The model now supports multiple views and video input, can be deployed on a single GPU, and generates 3D worlds in seconds. Breaking through the limitations of version 1.0, which only supported text or single-image input, it is the first to achieve end-to-end 3D reconstruction with multimodal prior injection and unified output across multiple tasks. It supports various 3D geometric predictions, including point clouds, depth maps, and camera parameters, and its performance significantly outperforms existing methods.