LGM 3D
FreemiumLGM 3D (Large Multi-View Gaussian Model) is a framework for generating high-resolution 3D content from text prompts or a single image. It represents 3D objects using multi-view Gaussian features, which are efficient to render, and processes multiple views with an asymmetric U-Net backbone designed for high throughput. The result is high-fidelity 3D objects generated in under 5 seconds, with a training resolution of 512 — a balance of speed and quality.