# microsoft/TRELLIS

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

Repository: https://github.com/microsoft/TRELLIS
Canonical: https://ross.abutalabs.com/products/microsoft-trellis
Homepage: https://trellis3d.github.io
Language: Python
License: MIT
License Family: permissive
Topics: 3d, 3d-generation, image-to-3d, text-to-3d, 3d-aigc
Last push: 2026-06-26T07:27:56+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 45
- inputs: {"age_days": 639, "days_push": 68, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13510, forks 1326 (observed 2026-08-28T04:11:03.442538+00:00)

## What it is
TRELLIS is Microsoft's large-scale 3D asset generation model that creates high-quality 3D assets from text or image prompts. It uses a unified Structured LATent (SLAT) representation to decode into multiple output formats including Radiance Fields, 3D Gaussians, and meshes, with support for local 3D editing.

## Use cases
- generate 3d models from text prompts
- convert images to 3d assets
- create game-ready 3d meshes from a photo
- generate 3d gaussian splat representations
- edit or create variants of generated 3d objects
- produce radiance field assets for rendering

## When to choose
- you need high-quality 3D assets generated from text or images
- you want flexible output formats like meshes, 3D Gaussians, or radiance fields
- you need local editing or variant generation of 3D assets
- you have GPU resources and want a state-of-the-art open 3D generation model

## When to avoid
- you need real-time 3D generation on CPU-only hardware
- you require precise CAD-style or parametric 3D modeling rather than generative assets
- you cannot meet the GPU memory requirements of large pretrained models

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, machine-learning, graphics
- platform: python, cross-platform
- tags: 3d-generation, text-to-3d, image-to-3d, 3d-gaussians, mesh-generation, generative-models, cvpr, diffusion-transformer, game-development, gpu, linux

## Member repositories
- microsoft/TRELLIS (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:03.442538+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:15.096036+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/TRELLIS (fetched 2026-08-28T04:11:03.442538+00:00, sha a04a4cda478d)
  - homepage: https://trellis3d.github.io (fetched 2026-08-29T08:08:04.283946+00:00, sha 266e119a0267)
- Data as of 2026-08-30T08:39:29.467469+00:00.