# Stability-AI/stable-fast-3d

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

Repository: https://github.com/Stability-AI/stable-fast-3d
Canonical: https://ross.abutalabs.com/products/stable-fast-3d
Homepage: https://stable-fast-3d.github.io
Language: Python
License: NOASSERTION
License Family: other
Last push: 2025-01-22T14:55:42+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 2, release rhythm 35, longevity 55
- inputs: {"age_days": 777, "days_push": 588, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1794, forks 225 (observed 2026-08-28T04:05:37.300790+00:00)

## What it is
Stable Fast 3D (SF3D) is Stability AI's open-source model that reconstructs a textured, UV-unwrapped 3D mesh from a single input image in about half a second. It builds on TripoSR and adds UV unwrapping, material parameter prediction, and illumination delighting so assets are ready for games and other rendering pipelines.

## Use cases
- generate a 3d model from a single photo
- image to 3d mesh reconstruction
- create game-ready textured 3d assets from images
- unwrap uv textures for a reconstructed mesh
- remove lighting from a photo before 3d reconstruction
- fast 3d asset generation for game development

## When to choose
- you need fast (sub-second) single-image to 3D mesh generation
- you need UV-unwrapped textured meshes with material parameters for game or rendering pipelines
- you want an open-source alternative to commercial image-to-3D services
- you have a CUDA GPU (or experimental Apple MPS support) available

## When to avoid
- you need high-fidelity 3D from multiple views or video rather than a single image
- you require a permissive license - the model weights are gated under a custom Stability AI license
- you have no GPU and need production-quality speed
- you need precise CAD-quality geometry rather than approximate visual meshes

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, image-processing, graphics, deep-learning, llm-inference
- domain: computer-vision, graphics, artificial-intelligence
- platform: python, windows
- tags: 3d-reconstruction, image-to-3d, mesh-generation, uv-unwrapping, texture-generation, delighting, stability-ai, gradio-demo, game-development, gpu, linux, macos

## Member repositories
- Stability-AI/stable-fast-3d (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:37.300790+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 2026-08-30T03:22:53.119745+00:00, confidence not recorded.
  - readme: https://github.com/Stability-AI/stable-fast-3d (fetched 2026-08-28T04:05:37.300790+00:00, sha 182a7ece4589)
  - homepage: https://stable-fast-3d.github.io (fetched 2026-08-29T11:01:44.413526+00:00, sha 600b0d29411c)
- Data as of 2026-08-30T08:39:29.467469+00:00.