
"While many AI models can generate text, images, and video, Tencent's Hunyuan (混元 or "first mix") family of models can dream up 3D objects and interactive scenes. The source says that Tencent's models are also being used by the developers of another Tencent game, GKART, and by some independent developers, too. Tencent declined to comment. "The games industry requires a lot of investment," the source says."
"'Previously you would need a month to design a character. Now you can just type in some text, and Hunyuan can give you four choices in 60 seconds.' The news is an early signal that models capable of understanding and re-creating the physical world could become a standard ingredient in game design. In addition to generating game content, these models could also enable more advanced virtual and augmented reality and help robots learn to do new things."
Riot Games is using 3D-native AI models to prototype characters, scenes, and storylines for Valorant, accelerating creative workflows. Tencent's Hunyuan family of models can generate 3D objects and interactive scenes and is being applied in other games like GKART and by independent developers. Designers can produce multiple character options from a text prompt in about 60 seconds, dramatically shortening development time. Models that understand and recreate physical space could become standard tools in game design, enable advanced virtual and augmented reality, and assist robotic learning. Rapid growth in 3D vision research is expanding applications while raising concerns about job displacement in creative fields.
Read at WIRED
Unable to calculate read time
Collection
[
|
...
]