Install Now
How to install Stability-AI/generative-models. Official installation instructions. Project installation guide. Framework or library installation. Build installation instructions. How to setup and install from GitHub. Installation steps and setup instructions. Official docs and installation instructions GitHub.
Stability-AI/generative-models Installation Guide
How to install Stability-AI/generative-models. Official project installation instructions and setup guide.
⚡
Automated Install (Recommended)
Quick installation instructions for Stability-AI/generative-models. This is the fastest way to complete project installation and setup.
Install via curl
curl -fsSL https://hexmos.com/ipm-install | bash &&
ipm i Stability-AI/generative-modelsor
Install via npx
npx @hexmos/ipm i Stability-AI/generative-modelsPrerequisites
Python
languageVersion: >=3.10
Required for running the generative model scripts. Python 3.10 is specifically recommended.
CUDA
system_toolVersion: >=11.8
NVIDIA GPU with CUDA support (recommended 11.8+) is required for model inference.
Git
system_toolUsed to clone the repository and fetch submodules.
Manual Installation Methods
Manual installation instructions. How to install from GitHub source.
Conda/Venv Setup & Dependency Install
git clone https://github.com/Stability-AI/generative-models.git
cd generative-models
python3 -m venv .pt2 && source .pt2/bin/activate
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
pip3 install -r requirements/pt2.txt
pip3 install .Post Installation Steps
- Download model weights (e.g., sv4d2.safetensors) and place them in the `checkpoints/` directory.
- To run Video 4D inference: `python scripts/sampling/simple_video_sample_4d2.py --input_path <path_to_video>`.
- To run the interactive UI: `streamlit run scripts/demo/video_sampling.py`.
- For training, ensure you install sdata: `pip3 install -e git+https://github.com/Stability-AI/datapipelines.git@main#egg=sdata`.