Installation

Follow these steps to clone the Cosmos Predict1 repository from GitHub and run the Docker container.

Note

Ensure you have the necessary hardware and software prerequisites before installation.

Cosmos-Predict1 Setup

1. Clone the Cosmos-Predict1 repository from GitHub.

   git clone git@github.com:NVIDIA/Cosmos.git
   cd cosmos-predict1
   

2. Set up the conda environment and install Cosmos-Predict1 dependencies for the environment.

   # Create the cosmos-predict1 conda environment.
   conda env create --file cosmos-predict1.yaml
   # Activate the cosmos-predict1 conda environment.
   conda activate cosmos-predict1
   # Install the dependencies.
   pip install -r requirements.txt
   # Patch Transformer engine linking issues in conda environments.
   ln -sf $CONDA_PREFIX/lib/python3.10/site-packages/nvidia/*/include/* $CONDA_PREFIX/include/
   ln -sf $CONDA_PREFIX/lib/python3.10/site-packages/nvidia/*/include/* $CONDA_PREFIX/include/python3.10
   # Install Transformer engine.
   pip install transformer-engine[pytorch]==1.12.0
   

3. Test the environment using the test_environment.py script.

   CUDA_HOME=$CONDA_PREFIX PYTHONPATH=$(pwd) python scripts/test_environment.py
   

Next Steps

If you haven’t done so already, determine which model you want to work with–refer to the Model Matrix page for more information.

You can then move on to the Diffusion Quickstart Guide or Autoregressive Quickstart Guide.