@rohanpaul_ai: The next step for 3D models is probably fewer prompts and more API calls. Lux3D points in that direction. Instead of ge…
Summary
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.
View Cached Full Text
Cached at: 08/27/26, 11:42 PM
The next step for 3D models is probably fewer prompts and more API calls.
Lux3D points in that direction.
Instead of generating one asset manually, a coding agent can call the Lux3D API repeatedly from a specification, produce a batch of 3D props, then send those assets into Blender for placement, scaling and material processing.
From there the control loop can keep going: inspect the scene, identify what is missing, generate more assets, modify the layout, repeat.
That is a different workload from “turn this image into a 3D object.”
It turns 3D generation into one tool inside a larger agent execution loop.
Can reconstructs PBR properties including metallicity, roughness, transparency and refractive gloss, alongside geometry and texture.
Manycore Tech (@ManycoreTech): Say hello to Lux3D 👋 Manycore Tech’s new 3D generative model.
See it deliver: ⚡ 3D generation in as little as 20s 🎨 High-quality materials and textures ⚙️ Cost-efficient batch creation with Harness Mode
Learn more: https://t.co/NCyQFDvlaK
#Lux3D #GenAI #3D #ManycoreTech
Similar Articles
@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.
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.
Luce: Relightable Gaussians for 3D Asset Generation
Luce unifies geometry and PBR materials in a voxelized Gaussian cloud to generate relightable 3D assets from single images, achieving state-of-the-art results on benchmarks like Toys4K.
@theworldlabs: Today we are sharing three new research papers, each exploring a new way to generate 3D content by leveraging large-sca…
World Labs announces three new research papers focused on generating 3D content using large-scale generative models and 2D priors, led by interns Hao Zhang, Bert Duisterhof, and Ben Tunnels.
What does the next generation of models need?
A discussion about the next evolution of frontier AI usage, questioning whether cloud-based agent workflows and massive distributed compute will replace local setups, referencing Tibo's tweet and OpenAI's recent math results.
@DeemosTech: Introducing #Rodin Gen-2.5 World’s 1st 10 MILLION polygon #3D GenAI — down to skin microstructures. 1M-poly in 4s Adapt…
DeemosTech introduces Rodin Gen-2.5, claiming it as the world's first 10 million polygon 3D generative AI model, capable of generating 1 million polygons in 4 seconds with adaptive thinking and 3D-native textures.