Stable Video Diffusion本地部署流程

Stable Video Diffusion

Stability AI开源图像到视频生成模型

1、克隆代码仓库

git clone https://github.com/Stability-AI/generative-models
cd generative-models

2、创建并激活虚拟环境

python -m venv venv
.\venv\Scripts\Activate.ps1

3、安装依赖库

pip install torch==2.0.1 torchvision torchaudio –index-url https://download.pytorch.org/whl/cu118
pip install -r .\requirements\pt2.txt
pip install .
pip install -e git+https://github.com/Stability-AI/datapipelines.git@main#egg=sdata

4、下载并运行模型

mkdir checkpoints
cd checkpoints
# 下载模型权重并放入 checkpoints 目录
cd ..
streamlit run scripts/demo/video_sampling.py