# openai/shap-e

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/openai-shap-e).**

12,251 stars · 1,072 forks · Python · MIT

## Links

- GitHub: https://github.com/openai/shap-e
- awesome-repositories: https://awesome-repositories.com/repository/openai-shap-e.md

## Description

Shap-E is a generative 3D modeling system that creates three-dimensional digital assets from natural language descriptions or two-dimensional images. It functions as a generative model capable of producing three-dimensional implicit functions and assets.

The project includes a 3D latent encoder that converts trimeshes and 3D models into latent representations using point clouds and multiview renders. It utilizes an image-to-3D generator to produce assets from synthetic view images and a text-to-3D generator to build shapes from text prompts.

The system implements a pipeline involving latent diffusion modeling, differentiable rendering, and multiview image conditioning. It processes geometric data through point cloud encoding and maps text embeddings to neural network parameters describing a 3D volume.

## Tags

### Part of an Awesome List

- [Generative 3D Modeling](https://awesome-repositories.com/f/awesome-lists/ai/generative-3d-modeling.md) — Automates the creation of 3D meshes and textures using machine learning from text or image prompts.
- [Point Cloud Encoders](https://awesome-repositories.com/f/awesome-lists/ai/point-cloud-and-3d-processing/3d-point-cloud-representations/point-cloud-encoders.md) — Converts geometric 3D data into latent space using sampled point sets and renders.
- [Shape Representation](https://awesome-repositories.com/f/awesome-lists/ai/shape-representation.md) — Represents 3D shapes as continuous functions that define the interior and exterior of objects.

### Artificial Intelligence & ML

- [Latent Space Encoders](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/latent-space-encoders.md) — Converts 3D models and trimeshes into compressed latent representations using multiview renders and point clouds. ([source](https://cdn.jsdelivr.net/gh/openai/shap-e@main/README.md))
- [Latent Diffusion Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-models/latent-diffusion-models.md) — Generates 3D structures by performing iterative denoising within a compressed latent space.
- [Image-Conditioned 3D Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models/conditional-image-generation/image-conditioned-3d-generation.md) — Produces three-dimensional objects using synthetic view images as visual guidance. ([source](https://cdn.jsdelivr.net/gh/openai/shap-e@main/README.md))
- [Text-to-3D Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-3d-generators.md) — Synthesizes three-dimensional implicit functions and geometry from natural language descriptions. ([source](https://cdn.jsdelivr.net/gh/openai/shap-e@main/README.md))
- [Text-to-Implicit Mappings](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-implicit-mappings.md) — Maps natural language embeddings directly to neural network parameters that describe a 3D volume.

### Graphics & Multimedia

- [3D Asset Pipelines](https://awesome-repositories.com/f/graphics-multimedia/3d-asset-pipelines.md) — Provides a pipeline for generating and encoding 3D models into latent representations for digital environments.
- [Differentiable Rendering](https://awesome-repositories.com/f/graphics-multimedia/mesh-processing-apis/differentiable-mesh-manipulations/differentiable-rendering.md) — Implements a rendering pipeline where outputs are differentiable to optimize 3D shapes via gradient descent.