Installation

Follow these steps to clone the Cosmos Transfer1 repository from GitHub and run the Docker container.

Note

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

Cosmos-Transfer1 Setup

1. Clone the Cosmos-Transfer1 repository from GitHub.

   git clone git@github.com:nvidia-cosmos/cosmos-transfer1.git
   cd cosmos-transfer1
   git submodule update --init --recursive
   

2. Set up the conda environment and install Cosmos-Transfer1 dependencies for the environment.

   # Create the cosmos-transfer1 conda environment.
   conda env create --file cosmos-transfer1.yaml
   # Activate the cosmos-transfer1 conda environment.
   conda activate cosmos-transfer1
   # 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

Follow the steps in the Transfer Quickstart Guide to try out running inference with a pre-trained Transfer model.