跳到正文
@TencentHunyuan· @tencenthunyuan · X·· 2026-04-21AI 评分55
AI 导读

腾讯混元转发 @svpino 的演示,展示一款新的开源 3D 世界生成模型。该多模态世界模型可用于生成新世界、重建世界,以及根据提示词、图像或视频模拟 3D 交互世界,3D 输出可导出为 meshes、3DGS 文件和点云,并在 Unity 和 Unreal Engine 中编辑,还能生成 3D 角色在其中行走。模型已在 GitHub 和 Hugging Face 提供链接。

正文

Great demo @svpino 🙌

引用Santiago (@svpino)@svpino
New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the @huggingface links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff! Video
在 X 查看被引用的帖子

来源:@TencentHunyuan · x.com