Overview
LGM is a novel framework for high-resolution 3D content creation, leveraging multi-view Gaussian features and an asymmetric U-Net backbone to generate 3D models from text prompts or single-view images.
Multi-View Gaussian Features
An efficient yet powerful representation for 3D objects, fused together for differentiable rendering.
Asymmetric U-Net Backbone
A high-throughput backbone operating on multi-view images, produced from text or single-view image input by leveraging multi-view diffusion models.
High-Resolution 3D Content Generation
Achieves high-resolution 3D content generation with a training resolution of 512.
Fast 3D Object Generation
Generates 3D objects within 5 seconds.
Get started
- Open the official website and confirm the service is available in your region.
- Check the current plan, usage limits and terms for your intended use.
- Try a small task with sample data before committing to a paid plan.
Editorial note
Pricing checked: Sep 20, 2026. Official website is active. Please verify current pricing and terms directly on the official site.
Record updated: Sep 20, 2026
Suggest a correction
