← Discover
Discover · GitHub · TRELLIS.2↑ +107 today

Generate high-quality 3D models from images

Developed by Microsoft, TRELLIS is a structured latent representation architecture that transforms text or visual inputs into three-dimensional (3D) models. This technology uses generative AI methods to create high-quality 3D assets quickly and compactly.

Updates

  • September 3, 2026: Stars 9,992 → 11,002.

What you get

  • Creates detailed and textured 3D assets from a single image.
  • It successfully processes complex structures and open surfaces.
  • It provides realistic results with PBR, physics-based visualization materials.

Installation

Clone the repository
git clone -b main https://github.com/microsoft/TRELLIS.2.git --recursive
    cd TRELLIS.2
Install dependencies
. ./setup.sh --new-env --basic --flash-attn --nvdiffrast --nvdiffrec --cumesh --o-voxel --flexgemm

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to convert my 2D image into a 3D model. Explain the basic processing steps and sample Python code structure required for me to create a 3D asset that preserves complex topologies, with high-quality textures and physics-based material properties, using the TRELLIS.2 model.

Related dictionary terms

Who it is forIt is for users with a Linux-based system and a powerful NVIDIA graphics card who want to produce high-resolution and detailed 3D assets.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-02: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.