（一）Ubuntu22.04服务器端部署Stable-Diffusion-webui AI绘画环境
一、分析cup型号： Intel(R) Celeron(R) CPU G1610 @ 2.60GHz
内存巨细： 8G
显卡型号：NVIDIA P104-100
留意：系统就寝题目
sudo systemctl mask sleep.target suspend.target hibernate.target hybrid-sleep.target
网卡设置
network:
ethernets:
enp3s0:
addresses:
dhcp4: no
gateway4: 192.168.1.1
nameservers:
addresses:
version: 2
开放端口7860
sudo apt-get install iptables
sudo iptables -I INPUT -p tcp --dport 7860 -j ACCEPT
sudo iptables-save
#永世保持，重启不丢失
sudo apt-get install iptables-persistent
sudo netfilter-persistent save
sudo netfilter-persistent reload
sudo cat /etc/iptables/rules.v4
二、安装nvidia驱动
这将输出关于显卡的详细信息，包罗制造商、型号和利用的内存量等。
sudo lshw -class display
禁用nouveau
编辑文件blacklist.conf：
sudo gedit /etc/modprobe.d/blacklist.conf
在文件最后部门插入以下两行内容
blacklist nouveau
options nouveau modeset=0
更新系统
sudo update-initramfs -u
重启系统（一定要重启）
验证nouveau是否已禁用
lsmod | grep nouveau
没有信息表现，分析nouveau已被禁用，接下来可以安装nvidia的显卡驱动。
下载驱动
wget https://us.download.nvidia.cn/XFree86/Linux-x86_64/550.135/NVIDIA-Linux-x86_64-550.135.run
sudo apt-get remove nvidia-*
安装：
sudo chmod a+x NVIDIA-Linux-x86_64-550.135.run
sudo apt-get update
sudo apt-get install build-essential
sudo ./NVIDIA-Linux-x86_64-550.135.run -no-x-check -no-nouveau-check -no-opengl-files
//只有禁用opengl这样安装才不会出现循环登岸的题目
-no-x-check：安装驱动时关闭X服务
-no-nouveau-check：安装驱动时禁用nouveau
-no-opengl-files：只安装驱动文件，不安装OpenGL文件
安装完毕之后
挂载Nvidia驱动：
modprobe nvidia
查抄驱动是否安装成功：
nvidia-smi
三、安装Anaconda3，安装python环境
wget --user-agent=“Mozilla”https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/Anaconda3-2024.10-1-Linux-x86_64.sh
bash Anaconda3-2024.10-1-Linux-x86_64.sh
source ~/.bashrc
conda -V
conda config --set auto_activate_base false
1、配置清华源
conda config --remove-key channels
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/pro
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
conda config --set show_channel_urls yes
conda config --show channels
channels:
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/pro
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
- defaults
- https://repo.anaconda.com/pkgs/main
- https://repo.anaconda.com/pkgs/r
2、虚拟环境创建
#创建
conda create -n sd python=3.10
#删除
conda remove -n sd --all
conda info --envs
#激活
conda activate sd
#推出
conda deactivate
#查看已有环境
conda env list
python -m pip install --upgrade pip
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
四、也可以直接升级到python3.10.6
1、从官网下载源文件
wget https://www.python.org/ftp/python/3.10.6/Python-3.10.6.tgz
2、安装
先安装依靠文件
sudo apt update
sudo apt install build-essential zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libreadline-dev libffi-dev libsqlite3-dev wget libbz2-dev
tar -zvxf Python-3.10.6.tgz
cd Python-3.10.6
./configure --enable-optimizations
make
sudo make install
如果上面不成功则可以，输入以下下令安装Python二进制文件
sudo make altinstall
3、验证安装是否成功
python3.10 --version
4、设置python的环境变量
#查找路径
which python3.10
sd@sd:~/tools/Python-3.10.6$ which python3.10
/usr/local/bin/python3.10
# 编辑
sudo vi ~/.bashrc
添加
alias python='/usr/local/bin/python3.10'
source ~/.bashrc
sd@sd:~$ python -V
Python 3.10.6
5、更新pip默认指向
rm /usr/bin/pip #如果原来有pip的链接先删除，没有的话，这步不消管。
sudo ln -s /usr/local/bin/pip3.10 /usr/bin/pip
pip -V
python -m pip install --upgrade pip
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
五、通过仓库直接安装cuda （不消安装）
conda search cudatoolkit
conda install cudatoolkit==11.8.0
六、安装cudnn（不消安装）
conda search cudnn
conda install cudnn==8.9.2.26
七、安装pytorch
不装，sd运行是会安装
八、安装 Stable Diffusionn
下载stable-diffusion-webui
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
下载模型
cd stable-diffusion-webui/models/Stable-diffusion/
模型放在这里
https://i-blog.csdnimg.cn/direct/f6ff09c8c7a34657b24d4faf44659ae8.png
启动sd
nohup ./webui.sh --listen --enable-insecure-extension-access --xformers --no-half-vae &
tail -f nohup.out
错误：Cannot locate TCMalloc. Do you have tcmalloc or google-perftool installed on your system? (improves CPU memory usage)
ps -aux | grep "webui.sh"
先安装这个
sudo apt-get install google-perftools
修改到国内镜像 sudo vi launch_utils.py
def prepare_environment():
# torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu121")
# torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.1.2 torchvision==0.16.2 --extra-index-url {torch_index_url}")
torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://mirrors.aliyun.com/pytorch-wheels/cu121")
torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.1.2 torchvision==0.16.2 -f {torch_index_url}")
https://i-blog.csdnimg.cn/direct/ddb1673013784a638c22018609f145e0.png
模型下载
用迅雷下载
磁力地址：
magnet:?xt=urn:btih:2daef5b5f63a16a9af9169a529b1a773fc452637&dn=v1-5-pruned-emaonly.ckpt&tr=udp%3a%2f%2ftracker.opentrackr.org%3a1337%2fannounce&tr=udp%3a%2f%2f9.rarbg.com%3a2810%2fannounce&tr=udp%3a%2f%2ftracker.openbittorrent.com%3a6969%2fannounce&tr=udp%3a%2f%2fopentracker.i2p.rocks%3a6969%2fannounce&tr=https%3a%2f%2fopentracker.i2p.rocks%3a443%2fannounce&tr=http%3a%2f%2ftracker.openbittorrent.com%3a80%2fannounce&tr=udp%3a%2f%2ftracker.torrent.eu.org%3a451%2fannounce&tr=udp%3a%2f%2fopen.stealth.si%3a80%2fannounce&tr=udp%3a%2f%2fvibe.sleepyinternetfun.xyz%3a1738%2fannounce&tr=udp%3a%2f%2ftracker2.dler.org%3a80%2fannounce&tr=udp%3a%2f%2ftracker1.bt.moack.co.kr%3a80%2fannounce&tr=udp%3a%2f%2ftracker.zemoj.com%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.tiny-vps.com%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.theoks.net%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.publictracker.xyz%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.monitorit4.me%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.moeking.me%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.lelux.fi%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.dler.org%3a6969%2fannounce&tr=udp%3a%2f%2ftracker.army%3a6969%2fannounce
免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。
页:
[1]