@IndieDevHailey: Qunhe has just launched its self-developed 3D generation model Lux3D. With just an image or a sentence, it can produce mesh + PBR materials, with the fastest mode taking about 20 seconds. The material performance for glass, metal, and ceramics is a highlight, and it supports Harness for batch generation, with integration for Codex / Blender.
Summary
Qunhe has released its self-developed 3D generation model Lux3D, which supports quick generation of mesh and PBR materials from images or text, with a maximum speed of 20 seconds, and is compatible with tools like Blender.
View Cached Full Text
Cached at: 08/30/26, 02:13 AM
Hcluster Tech has just launched its self-developed 3D generation model, Lux3D.
With a single image or text prompt, it generates meshes with PBR materials, and the fastest mode takes only about 20 seconds.
Materials like glass, metal, and ceramic are particularly well-rendered. It also supports batch generation via Harness and integrates with Codex/Blender.
https://t.co/3jaUxJMFjs
Similar Articles
@rohanpaul_ai: The next step for 3D models is probably fewer prompts and more API calls. Lux3D points in that direction. Instead of ge…
Lux3D is Manycore Tech's new 3D generative model that enables API-based batch creation of 3D assets with PBR properties, integrating into agent workflows for efficient production.
@Huahuazo: While browsing GitHub, I found an eye-catching project — upload an ordinary photo, and it automatically recognizes the object's structure, proportions, and materials, directly generating a complete 3D model. Let me mention a few designs I found impressively unconventional: It comes with a "semi-finished" attribute out of the box — the generated model isn't a rigid photo texture, but includes clear hierarchy and collision body components...
Introducing the open-source project img2threejs on GitHub. Upload an ordinary photo and it automatically generates a code-based Three.js 3D model with hierarchy and collision bodies, suitable for direct use by developers and game creators.
Structured 3D Latents for Scalable and Versatile 3D Generation
微软提出统一的结构化潜在表示（SLAT），结合 rectified flow transformers 实现高质量、多格式（Radiance Fields、3D Gaussians、网格）的 3D 资产生成，支持文本/图像条件及局部编辑，在 500K 3D 数据集上训练的 2B 参数模型显著超越现有方法。
@pritipatelor: NVIDIA just released a really interesting new tool: with any random image, you can generate a 3D world that's freely ex…
NVIDIA开源了名为Lyra 2.0的模型，可将任意单张图片直接转换为可自由探索的交互式3D世界，甚至可用于向生成的场景中放入机器人进行仿真训练。模型已发布到Hugging Face，UI代码也已在GitHub开源。
@oragnes: Wow, just dug up this amazing tool map3d on GitHub! Based on OpenStreetMap, you select an area on the web page, and it automatically fetches real building and road data, rendering a 3D city model with heights in one click! The craziest part is it can directly export GLB files for use in Blender or game engines…
Introduces two open-source tools on GitHub: map3d, which automatically generates 3D city models from OpenStreetMap and exports GLB files; and Voice-Pro, a local tool integrating video download, voice separation, subtitle recognition, translation, voice cloning dubbing, and video synthesis.