继续压榨主机生产力，在wsl Ubuntu中部署ai绘图，安装过程中需要代理，系统版本如下:

wsl 2
windows 11
ubuntu 24.04

安装python

  • 安装pyenv ubuntu 24.04自带的python版本是3.12，sd-webui要求3.10或者3.11这里先安装python，可以参考sd-webui github文档直接apt安装，这里为了方便管理多版本安装pyenv
$ curl https://pyenv.run | bash
  • 安装编译依赖 pyenv安装成功后，执行pyenv install报错，安装编译python需要的依赖
# 安装依赖
$ sudo apt-get update
$ sudo apt-get install make build-essential libssl-dev zlib1g-dev \
libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm \
libncursesw5-dev xz-utils tk-dev libxml2-dev libxmlsec1-dev libffi-dev liblzma-dev

再次安装成功

# 安装python
$ pyenv install 3.11.10
# 切换至3.11.10版本
$ pyenv global 3.11.10

安装cuda

参考nvida官网安装wsl cuda

$ wget https://developer.download.nvidia.com/compute/cuda/repos/wsl-ubuntu/x86_64/cuda-wsl-ubuntu.pin
$ sudo mv cuda-wsl-ubuntu.pin /etc/apt/preferences.d/cuda-repository-pin-600
$ wget https://developer.download.nvidia.com/compute/cuda/12.6.2/local_installers/cuda-repo-wsl-ubuntu-12-6-local_12.6.2-1_amd64.deb
$ sudo dpkg -i cuda-repo-wsl-ubuntu-12-6-local_12.6.2-1_amd64.deb
$ sudo cp /var/cuda-repo-wsl-ubuntu-12-6-local/cuda-*-keyring.gpg /usr/share/keyrings/
$ sudo apt-get update
$ sudo apt-get -y install cuda-toolkit-12-6

安装后可以执行nvidia-smi查看安装情况

$ nvidia-smi
Sat Oct 19 22:41:42 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.51.01              Driver Version: 565.90         CUDA Version: 12.7     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 4060 Ti     On  |   00000000:01:00.0  On |                  N/A |
|  0%   37C    P8              8W /  165W |    1050MiB /  16380MiB |      1%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A        23      G   /Xwayland                                   N/A      |
+-----------------------------------------------------------------------------------------+

安装sd-webui

直接按照sd-webui GitHub 文档安装，安装完成后将模型放置**stable-diffusion-webui/models/Stable-diffusion/**目录，模型去c站下载，直接执行webui.sh启动

# 安装
$ git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
# 启动
$ ./webui.sh

启动成功会提示访问http://127.0.0.1:7860， sd-webui

问题

  • 代理导致http://127.0.0.1:7860访问不通，可以增加 –listen 启动参数，会在0.0.0.0:7860地址启动
urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='192.168.1.11', port=1081): Max retries exceeded with url: http://127.0.0.1:7860/startup-events (Caused by ProxyError('Unable to connect to proxy', RemoteDisconnected('Remote end closed connection without response')))

$ ./webui.sh --listen
  • 启动过程中还可能会报如下问题，提示安装TCMalloc，优化CPU、内存使用，不安装也不影响使用
Cannot locate TCMalloc. Do you have tcmalloc or google-perftool installed on your system? (improves CPU memory usage)

# 安装TCMallocls
$ sudo apt-get install libtcmalloc-minimal4 -y

整个安装下来需要下载很多软件包，国内的话需要代理，没有代理就要找其他离线包安装的方式了。