3DTopia/LGM

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2111 stars · 140 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LGM is the official PyTorch implementation of an ECCV 2024 Oral paper that generates high-resolution 3D models from text prompts or single-view images using a Large Multi-view Gaussian Model. It fuses multi-view Gaussian features produced by diffusion models and renders them differentiably, exporting 3D objects in about 5 seconds.

Use cases

• generate a 3D model from a text prompt
• convert a single image into a 3D asset
• create gaussian splat 3D objects in seconds
• export generated 3D content as meshes for games
• run a gradio demo for text/image to 3D
• visualize generated 3D gaussian ply files in a local gui

When to choose

• you need fast feed-forward text-to-3D or image-to-3D generation
• you want high-resolution 3D output via gaussian splatting
• you need a research baseline for multi-view gaussian 3D generation
• you want pretrained weights and ready-made demos (HuggingFace, Replicate)

When to avoid

• you need production-grade, artist-ready topology meshes without cleanup
• you lack a GPU with ~10GB memory for full inference
• you need precise CAD-like or parametric 3D modeling
• you want a maintained tool with long-term support rather than a research codebase

Facets

library · maturity active

machine-learning deep-learning image-processing graphics simulation artificial-intelligence deep-learning computer-vision graphics python cross-platform gaussian-splatting image-to-3d text-to-3d 3d-generation multi-view-diffusion eccv-2024 3d-content-creation game-development gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="3DTopia/LGM")