hao-ai-lab-FastVideo/docs/getting_started/installation.md

🔧 Installation

FastVideo supports the following hardware platforms:

• NVIDIA CUDA
• Apple silicon

Quick Installation

Using pip

# Create and activate a new conda environment
conda create -n fastvideo python=3.12
conda activate fastvideo

pip install fastvideo

Using uv

# Create and activate a new uv environment
uv venv --python 3.12 --seed
source .venv/bin/activate

uv pip install fastvideo

From source

git clone https://github.com/hao-ai-lab/FastVideo.git
cd FastVideo
pip install -e .

# or if you are using uv
uv pip install -e .

Also optionally install flash-attn:

pip install flash-attn --no-build-isolation

Hardware Requirements

• NVIDIA GPUs: CUDA 11.8+ with compute capability 7.0+
• Apple Silicon: macOS 12.0+ with M1/M2/M3 chips
• CPU: x86_64 architecture (for CPU-only inference)

Next Steps

• Quick Start Guide - Get started with your first video generation
• Configuration - Learn about configuration options
• Examples - Explore example scripts and notebooks