# Stable-X/Stable3DGen

A Modular Framework for 3D Generation and Beyond [WIP]

Repository: https://github.com/Stable-X/Stable3DGen
Canonical: https://ross.abutalabs.com/products/stable3dgen
Language: Python
License: MIT
License Family: permissive
Last push: 2025-07-02T08:49:35+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 29, release rhythm 35, longevity 37
- inputs: {"age_days": 525, "days_push": 427, "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 1274, forks 92 (observed 2026-08-28T04:04:12.698061+00:00)

## What it is
Stable3DGen is a modular Python framework for generating 3D assets from images, adapted from Microsoft's TRELLIS with NVIDIA library dependencies removed for commercial use. It implements Hi3DGen, a high-fidelity 3D geometry generation approach using normal bridging, and includes a local Gradio-style demo app.

## Use cases
- generate 3d models from a single image
- create 3d meshes from photos for games
- commercial 3d asset generation without nvidia-only dependencies
- high-fidelity geometry generation from images
- run a local demo to turn images into 3d assets
- research on image-to-3d generation pipelines

## When to choose
- you need MIT-licensed, commercially usable image-to-3d generation
- you want a modular framework built on TRELLIS without kaolin/nvdiffrast dependencies
- you have a CUDA GPU and want local 3D asset generation

## When to avoid
- you need a production-ready, polished tool (project is marked WIP)
- you have no GPU or CUDA environment
- you need text-to-3d rather than image-to-3d generation

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, deep-learning, graphics, computer-vision
- platform: python, cross-platform
- tags: 3d-generation, image-to-3d, 3d-mesh, generative-ai, trellis, hi3dgen, normal-bridging, commercial-friendly, gpu, linux

## Member repositories
- Stable-X/Stable3DGen (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:12.698061+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 2026-08-30T05:03:05.262787+00:00, confidence not recorded.
  - readme: https://github.com/Stable-X/Stable3DGen (fetched 2026-08-28T04:04:12.698061+00:00, sha 77864f39e8d0)
- Data as of 2026-08-30T08:39:29.467469+00:00.