Preparation for installation
在使用Step-Video-T2V前,需确保系统满足以下条件:Python 3.10环境、Git版本控制系统,推荐使用Conda管理环境。
Detailed installation steps
- Cloning GitHub repositories:
git clone https://github.com/stepfun-ai/Step-Video-T2V.git
- Go to the project catalog:
cd Step-Video-T2V
- Create a virtual environment:
conda create -n stepvideo python=3.10
conda activate stepvideo - Install the dependencies:
pip install -e .
可选安装flash-attn加速模块:pip install flash-attn --no-build-isolation
hardware requirement
项目支持单GPU推理和量化技术,可显著降低显存需求。建议使用NVIDIA GPU并安装CUDA驱动程序,具体配置需求可参考GitHub文档。
This answer comes from the articleStep-Video-T2V: A Vincennes Video Model Supporting Multilingual Input and Long Video GenerationThe