# VAST-AI-Research/TripoSG

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Repository: https://github.com/VAST-AI-Research/TripoSG
Canonical: https://ross.abutalabs.com/products/triposg
Language: Python
License: MIT
License Family: permissive
Topics: 3d-generation, 3d-reconstruction, image-to-3d, 3d-genai
Last push: 2025-04-18T06:58:52+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 17, release rhythm 35, longevity 37
- inputs: {"age_days": 527, "days_push": 502, "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 1755, forks 196 (observed 2026-08-28T04:05:32.012603+00:00)

## What it is
TripoSG is an open-source image-to-3D generation foundation model that produces high-fidelity 3D meshes from single images using large-scale rectified flow transformers and an SDF-based VAE. It ships as a Python library with inference code, pretrained 1.5B parameter checkpoints on Hugging Face, and interactive demos.

## Use cases
- generate a 3d mesh from a single image
- convert photos into 3d models
- create 3d assets from sketches or cartoons
- reconstruct 3d shapes from images for games
- prototype 3d shapes from scribbles with a text prompt
- run image-to-3d generation locally with a gpu

## When to choose
- you need high-fidelity 3d meshes from single images
- you want an open-source, MIT-licensed image-to-3d model you can self-host
- your inputs span photorealistic images, cartoons, and sketches
- you want to build on a state-of-the-art 3d generative foundation model

## When to avoid
- you need textured, production-ready assets with materials rather than geometry
- you have no gpu available for inference
- you need real-time 3d generation in a production pipeline
- you want a polished end-user application rather than a model and inference code

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, deep-learning, computer-vision, graphics, machine-learning
- platform: python, cross-platform
- tags: image-to-3d, 3d-generation, rectified-flow, mesh-generation, generative-ai, sdf, diffusion-models, gpu, linux

## Member repositories
- VAST-AI-Research/TripoSG (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.012603+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 2026-08-30T03:27:53.923571+00:00, confidence not recorded.
  - readme: https://github.com/VAST-AI-Research/TripoSG (fetched 2026-08-28T04:05:32.012603+00:00, sha 3bd44d4eb603)
- Data as of 2026-08-30T08:39:29.467469+00:00.