Shap-E

This is the official code and model release for Shap-E: Generating Conditional 3D Implicit Functions.

• See Usage for guidance on how to use this repository.
• See 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.

             ![A chair that looks like an avocado](samples/a_chair_that_looks_like_an_avocado/2.gif) 
        

        

             ![An airplane that looks like a banana](samples/an_airplane_that_looks_like_a_banana/3.gif) 
        

        

             ![A spaceship](samples/a_spaceship/0.gif) 

A chair that looks
like an avocado

An airplane that looks
like a banana

A spaceship

             ![A birthday cupcake](samples/a_birthday_cupcake/3.gif) 
        

        

             ![A chair that looks like a tree](samples/a_chair_that_looks_like_a_tree/2.gif) 
        

        

             ![A green boot](samples/a_green_boot/3.gif) 

A birthday cupcake

A chair that looks
like a tree

A green boot

             ![A penguin](samples/a_penguin/1.gif) 
        

        

             ![Ube ice cream cone](samples/ube_ice_cream_cone/3.gif) 
        

        

             ![A bowl of vegetables](samples/a_bowl_of_vegetables/2.gif) 

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 - sample a 3D model, conditioned on a text prompt.
• 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 - 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.