https://github.com/openai/shap-e

Generate 3D objects conditioned on text or images
https://github.com/openai/shap-e

Last synced: 6 days ago
JSON representation

Generate 3D objects conditioned on text or images

• Host: GitHub
• URL: https://github.com/openai/shap-e
• Owner: openai
• License: mit
• Created: 2023-04-19T18:54:32.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-06-22T19:19:14.000Z (10 months ago)
• Last Synced: 2025-04-02T00:16:49.473Z (13 days ago)
• Language: Python
• Size: 11.4 MB
• Stars: 11,851
• Watchers: 236
• Forks: 989
• Open Issues: 100
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome - openai/shap-e - Generate 3D objects conditioned on text or images (Python)
• ai-game-devtools - Shap-E
• AiTreasureBox - openai/shap-e - 04-07_11861_1](https://img.shields.io/github/stars/openai/shap-e.svg) |Generate 3D objects conditioned on text or images| (Repos)
• StarryDivineSky - openai/shap-e - E是一个由OpenAI开发的用于生成3D对象的项目，它可以通过文本或图像来生成3D模型。该项目利用扩散模型，能够从文本描述或图像中创建多样且高质量的3D形状。其核心在于使用神经辐射场（Neural Radiance Fields, NeRFs）作为中间表示，并训练一个扩散模型来生成这些NeRFs的参数。SHAP-E的优势在于其生成速度快，并且能够生成各种各样的3D对象，而无需复杂的3D建模专业知识。它提供了一个简单易用的界面，允许用户通过简单的文本提示或上传图像来生成3D模型。该项目旨在推动3D内容创作的民主化，让更多人能够轻松创建3D对象。SHAP-E的训练数据包括大量的3D模型和相应的文本描述或图像，使其能够学习到文本和图像与3D形状之间的复杂关系。该项目为3D建模、游戏开发、虚拟现实等领域带来了新的可能性。 (3D视觉生成重建 / 资源传输下载)

README

        
# Shap-E

This is the official code and model release for [Shap-E: Generating Conditional 3D Implicit Functions](https://arxiv.org/abs/2305.02463).

 * See [Usage](#usage) for guidance on how to use this repository.

 * See [Samples](#samples) for examples of what our text-conditional model can generate.

# Samples

Here are some highlighted samples from our text-conditional model. For random samples on selected prompts, see [samples.md](samples.md).

    

        

            

                

            

            

                

            

            

                

            

        

        

            A chair that looks
like an avocado

            An airplane that looks
like a banana

            A spaceship

        

        

            

                

            

            

                

            

            

                

            

        

        

            A birthday cupcake

            A chair that looks
like a tree

            A green boot

        

        

            

                

            

            

                

            

            

                

            

        

        

            A penguin

            Ube ice cream cone

            A bowl of vegetables

        

    

# Usage

Install with `pip install -e .`.

To get started with examples, see the following notebooks:

* [sample_text_to_3d.ipynb](shap_e/examples/sample_text_to_3d.ipynb) - sample a 3D model, conditioned on a text prompt.

* [sample_image_to_3d.ipynb](shap_e/examples/sample_image_to_3d.ipynb) - sample a 3D model, conditioned on a synthetic view image. To get the best result, you should remove background from the input image.

* [encode_model.ipynb](shap_e/examples/encode_model.ipynb) - loads a 3D model or a trimesh, creates a batch of multiview renders and a point cloud, encodes them into a latent, and renders it back. For this to work, install Blender version 3.3.1 or higher, and set the environment variable `BLENDER_PATH` to the path of the Blender executable.