Tip Of AI
Discover what you can do with AI
Shap-E is a code and model release for generating conditional 3D implicit functions. It allows users to generate 3D objects based on text or images. The code is available on the openai/shap-e repository on GitHub. The repository contains several files, including a README.md file that provides guidance on how to use the code and model. There are also sample files that showcase what the text-conditional model can generate. Some highlighted samples include a chair that looks like an avocado, an airplane that looks like a banana, a spaceship, and more. To install Shap-E, users can use pip install -e .. command. The repository also provides notebooks with examples to get started, such as sample_text_to_3d.ipynb for sampling a 3D model based on a text prompt, sample_image_to_3d.ipynb for sampling a 3D model based on a synthetic view image, and encode_model.ipynb for encoding 3D models or trimesh into a latent representation. Shap-E is licensed under the MIT license and is written in Python with 98.3% of the code in Python and 1.7% in Jupyter Notebook. The repository has gained significant popularity, with over 10.2k stars, 219 watchers, and 752 forks. It has also attracted contributions from 7 contributors.