[Linux容器]手把手搭建Stable-Diffusion容器

最近的AI绘画可谓是特别火呀,这一期带大家使用容器搭建Stable-Diffusion

1.首先我们安装Docker

 Debian

sudo apt update && sudo apt install -y docker.io

 Redhat

sudo yum makecache && sudo yum install -y podman

 

 2.我们拉取debian镜像

 Debian 

docker pull debian

 RHEL

podman pull debian

3.开始构造镜像

docker run -p 1234:1234 -itd --name stable debian

podman run -p 1234:1234 -itd --name stable debian

docker exec -it stable bash
podman exec -it stable bash

sudo apt update && sudo apt install -y python3 python3-pip python3-venv git \
&& pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple \
&& pip install torch \
&& pip install torchvision \
&& pip install gfpgan \
&& pip install clip
&& pip install opencv-python-headless
&& git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui \

 4.复制模型进去

docker/podman cp models stable:/stable-diffusion-webui-master/models/

 5.运行容器内的SD

普通显卡

python3 launch.py --port 1234 --listen

CPU硬解 

export COMMANDLINE_ARGS=--skip-torch-cuda-test
python3 launch.py --no-half --port 1234 --listen