# openai/shap-e

Generate 3D objects conditioned on text or images

Repository: https://github.com/openai/shap-e
Canonical: https://ross.abutalabs.com/products/shap-e
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-22T19:19:14+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 88
- inputs: {"age_days": 1232, "days_push": 802, "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 12261, forks 1079 (observed 2026-08-28T04:10:52.178736+00:00)

## What it is
Shap-E is OpenAI's official release of a generative model that produces 3D implicit functions conditioned on text prompts or images. It includes model weights and example notebooks for sampling 3D assets and encoding existing 3D models.

## Use cases
- generate 3d models from text prompts
- create 3d assets from a single image
- convert a mesh into a latent representation
- render generated 3d objects as gifs or meshes
- experiment with conditional 3d generative models

## When to choose
- you want to generate 3D assets from text or images with pretrained models
- you need a research baseline for text-to-3D generation
- you want to encode existing meshes into Shap-E's latent space

## When to avoid
- you need production-quality, game-ready 3D assets with clean topology
- you have no GPU available for inference
- you need actively maintained code with recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, graphics
- domain: artificial-intelligence, machine-learning, graphics
- platform: python
- tags: text-to-3d, image-to-3d, generative-models, 3d-generation, diffusion-models, implicit-functions, game-development, gpu

## Member repositories
- openai/shap-e (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:52.178736+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 2026-08-29T17:14:13.087081+00:00, confidence not recorded.
  - readme: https://github.com/openai/shap-e (fetched 2026-08-28T04:10:52.178736+00:00, sha 5d20c094304e)
- Data as of 2026-08-30T08:39:29.467469+00:00.