# VAST-AI-Research/TripoSR

TripoSR: Fast 3D Object Reconstruction from a Single Image

Repository: https://github.com/VAST-AI-Research/TripoSR
Canonical: https://ross.abutalabs.com/products/triposr
Language: Python
License: MIT
License Family: permissive
Last push: 2026-06-04T07:11:09+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 35, longevity 67
- inputs: {"age_days": 938, "days_push": 90, "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 6888, forks 888 (observed 2026-08-28T04:09:51.128903+00:00)

## What it is
TripoSR is an open-source model for fast feedforward 3D object reconstruction from a single image, developed by Tripo AI and Stability AI. It generates high-quality 3D models in under 0.5 seconds on an NVIDIA A100 GPU, based on Large Reconstruction Model (LRM) principles.

## Use cases
- generate a 3d model from a single photo
- reconstruct 3d objects from images
- convert 2d images to 3d meshes
- fast image-to-3d generation
- create 3d assets for games from photos
- single-view 3d reconstruction

## When to choose
- you need rapid 3D model generation from a single image without multi-view capture
- you want an open-source, MIT-licensed alternative to commercial image-to-3D services
- you have GPU resources and need sub-second feedforward 3D reconstruction
- you need a research baseline that outperforms other open-source single-image 3D reconstruction models

## When to avoid
- you need highly detailed, production-ready 3D assets with precise geometry
- you have no GPU available, since inference requires significant GPU compute
- you need textured, rigged, or animation-ready models rather than static meshes
- you require multi-view or video-based 3D reconstruction instead of single-image input

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, computer-vision, graphics, deep-learning
- platform: python, cross-platform
- tags: 3d-reconstruction, single-image-to-3d, large-reconstruction-model, mesh-generation, feedforward-3d, image-to-3d, gpu, linux

## Member repositories
- VAST-AI-Research/TripoSR (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.128903+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 2026-08-29T17:41:39.119590+00:00, confidence not recorded.
  - readme: https://github.com/VAST-AI-Research/TripoSR (fetched 2026-08-28T04:09:51.128903+00:00, sha 891a0756f73d)
- Data as of 2026-08-30T08:39:29.467469+00:00.