Tencent Steps Up AI Game with Open-Source 3D Generation Tools

Tencent has unveiled a collection of new artificial intelligence tools, designed to convert text and images into 3D visuals, as reported by Reuters. This latest move highlights China's growing momentum in the field of generative AI

The Chinese tech giant announced in a statement, that it released five open-source models based on its Hunyuan3D-2.0 technology, including "turbo" versions that generate 3D visuals within 30 seconds while maintaining high precision and quality.

This launch follows in the wake of other Chinese firms challenging U.S. dominance in AI.

The increasing adoption of AI in video game development is driven by rising development costs. Additionally, consumer spending on new games has been sluggish, with players preferring established titles due to the current economic climate.

Tencent first unveiled its 3D AI models in November 2024, primarily targeting designers and game developers. It touted the launch as an effort to establish itself as an early innovator in text-to-3D and image-to-3D generation capabilities. The Hunyuan3D-2.0 model followed in January, with Tencent claiming that it outperforms leading industry models in text consistency, geometric accuracy, and visual quality benchmarks.

ByteDance, parent company of TikTok, is also focusing on text-to-3D and image-to-3D field with its VeOmniverse model, which it released in 2024. However, that technology is proprietary, unlike Tencent’s open-source option.