Skip to content

LGM

Generate high resolution 3D models from text or one image

Visit official site

What LGM is

The framework is described as a way to generate high resolution 3D models from text prompts or single view images, using multi view Gaussian features and differentiable rendering.

What you can do with it

  • Generate a 3D model from a text prompt
  • Generate a 3D model from a single view image
  • Render fused multi view Gaussian features

Who it is for

  • 3D content creation work
  • 3D object design work
  • Virtual world building work

Pros & cons

✓ What we like

  • Multi view Gaussian features fused for differentiable rendering
  • An asymmetric U-Net acts as a high throughput backbone

! What to watch out for

  • Inputs are limited to text prompts or single view images
  • Generation depends on a multi view diffusion model

FAQ

What are the inputs?

Text prompts or single view images, with multi view images also shown as an example.

What resolution is named?

The material states 512x512 for 3D content generation.

Last reviewed: 2026-11-15

More AI design tools tools

View all →

How we review