openai/shap-e

★ 12,247PythonAudience · researcherComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((shap-e))
    What it does
      Text to 3D shape
      Image to 3D shape
      Implicit function output
    Inputs
      Text prompt
      Photo or render
      Existing 3D model
    Tech Stack
      Python
      Jupyter Notebook
      Blender
    Getting Started
      Three starter notebooks
      Google Colab demo
      pip install
    Audience
      Researchers
      3D artists

mindmap root((shap-e)) What it does Text to 3D shape Image to 3D shape Implicit function output Inputs Text prompt Photo or render Existing 3D model Tech Stack Python Jupyter Notebook Blender Getting Started Three starter notebooks Google Colab demo pip install Audience Researchers 3D artists

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Generate a 3D model of any object from a text description like 'a chair shaped like an avocado'.

USE CASE 2

Convert a photograph into a 3D shape for use in design or game prototyping.

USE CASE 3

Experiment with encoding existing 3D models back into the Shap-E learned representation.

Tech stack

PythonJupyter NotebookBlender

Getting it running

Difficulty · moderate Time to first run · 30min

The encoding notebook requires Blender, image-to-3D works best with background-removed input images.

In plain English

Shap-E is a research project from OpenAI that generates three-dimensional objects from text descriptions or images. You can type a prompt like "a chair that looks like an avocado" or "a birthday cupcake" and the model produces a 3D shape. You can also provide a photograph or rendered image and have the model generate a 3D version of the object shown. The approach is based on a research paper and works by learning a compact mathematical representation of 3D shapes, called implicit functions, which can be decoded into viewable 3D models. This is different from producing a mesh or a point cloud directly. The outputs can be displayed as rotating animated previews. Installing the library requires Python and pip. The repository includes three Jupyter notebooks to help people get started: one for text-to-3D generation, one for image-to-3D generation, and one that demonstrates encoding an existing 3D model back into the learned representation. The image-to-3D path works best when the background is removed from the input image first. The encoding notebook additionally requires Blender, a free open source 3D software application, to generate the image renders it needs as input. This is a research release, meaning it is intended to share the methods and models described in the accompanying paper rather than to serve as a finished product for end users.

Copy-paste prompts

Prompt 1

Using Shap-E, generate a 3D model from the text prompt 'a small red sports car' and export it for viewing.

Prompt 2

How do I run the Shap-E image-to-3D notebook with a PNG where I have already removed the background?

Prompt 3

Walk me through installing Shap-E and running the text-to-3D Jupyter notebook from scratch.

Prompt 4

What format does Shap-E output 3D shapes in, and how can I convert the result to a standard mesh file?

Open on GitHub → Explain another repo

← openai on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.