0
0

【本地化部署Stable Diffusion WebUI（MACOS安装）】

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

文章目录

前言

随着人工智能的不断发展，AI绘图热兴起，我也想加入到AI绘图大潮中。

一、Stable Diffusion WebUI适配三类芯片

此模型支持三类GPU芯片

  1. NVidia (recommended)
  2. AMD GPUs.
  3. Intel CPUs, Intel GPUs (bothintegrated and discrete) （我的mac属于此情况）

二、安装

说明：期间需要访问外网，自行实现巧妙上网

1.安装git、conda等

  1. brew install cmake protobuf rust python@3.10 git wget miniconda

2.选定目录及下载Github远程仓库文件

  1. mkdir SDW
  2. cd SDW
  3. git clone git@github.com:openvinotoolkit/stable-diffusion-webui.git

3.创建conda虚拟环境

创建虚拟环境

  1. conda env create -p /Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/automatic -f /Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/environment-wsl2.yaml

最后创建完成后显示如下：

  1. # To activate this environment, use                                                                                                                                                                                                 
  2. #                                                                                                                                                                                                                                   
  3. #     $ conda activate /Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/automatic                                                                                                                                                
  4. #                                                                                                                                                                                                                                   
  5. # To deactivate an active environment, use                                                                                                                                                                                          
  6. #                                                                                                                                                                                                                                   
  7. #     $ conda deactivate

激活环境

  1. conda activate /Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/automatic

4.安装依赖

  1. cd stable-diffusion-webui
  2. pip install -r requirements.txt

pip速度慢需添加国内pip源

  1. cd ~
  2. mkdir .pip
  4. cd .pip
  5. touch pip.conf
  7. 在pip.conf文件中，添加以下内容：
  9. [global]
  10. index-url = https://pypi.doubanio.com/simple/
  11. trusted-host = pypi.doubanio.com

5.运行

还有未安装的依赖在此步骤执行中会一次安装，当然有报错需要一次解决。

英特尔CPU+GPU的场景执行前环境要生效如下内容：

  1. export PYTORCH_TRACING_MODE=TORCHFX
  2. export COMMANDLINE_ARGS="--skip-torch-cuda-test --precision full --no-half" 
  3. ./webui.sh

6.问题处理

运行./webui.sh会有很多报错

缺openai模块等

  1. OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'openai/clip-vit-large-patch14' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer.
手动git clone

在这里插入图片描述
可直接git clone
可以指定git代理实现

  1. #指定git代理
  2. git config --global https.proxy socks5://127.0.0.1:1088
  3. 或
  4. git config --global https.proxy https://127.0.0.1:1088
  5. #取消git代理
  6. git config --global --unset https.proxy

在这里插入图片描述
在这里插入图片描述

  1. 例如：
  2. git clone https://huggingface.co/openai/clip-vit-large-patch14
  3. 或
  4. git clone git@hf.co:openai/clip-vit-large-patch14
类似的v1-5-pruned-emaonly.safetensors模型获取失败

在这里插入图片描述

  1. https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors

此文件较大有4G多，建议通过从源网站下载到云盘，再从云盘下载到本地，然后让入目标文件夹如：stable-diffusion-uebul/models/Stable-diffusion/

RuntimeError: “LayerNormKernelImpl” not implemented for 'Half’等

  1. RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'
  2. /Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/functional.py", line 2515, in layer_norm
  4. RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'
  5. /Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 114, in forward

那么执行时添加如下参数：

  1. ./webui.sh --precision full --no-half

正常运行sdw的的话会自动访问http://127.0.0.1:7860/

命令行显示类似如下：

在这里插入图片描述

浏览器显示如下：

注意选择支持intel GPU的script，OpenVINO™ Acceleration Script
在这里插入图片描述

绘图时报错

类似如下报错
报错显示如下：

  1. OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like CompVis/stable-diffusion-safety-checker is not the path to a directory containing a file named config.json. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.

以及

  1.    Traceback (most recent call last):
  2.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connection.py", line 198, in _new_conn
  3.         sock = connection.create_connection(
  4.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/util/connection.py", line 85, in create_connection
  5.         raise err
  6.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/util/connection.py", line 73, in create_connection
  7.         sock.connect(sa)
  8.     TimeoutError: timed out
  10.     The above exception was the direct cause of the following exception:
  12.     Traceback (most recent call last):
  13.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 793, in urlopen
  14.         response = self._make_request(
  15.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 491, in _make_request
  16.         raise new_e
  17.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 467, in _make_request
  18.         self._validate_conn(conn)
  19.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1099, in _validate_conn
  20.         conn.connect()
  21.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connection.py", line 616, in connect
  22.         self.sock = sock = self._new_conn()
  23.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connection.py", line 207, in _new_conn
  24.         raise ConnectTimeoutError(
  25.     urllib3.exceptions.ConnectTimeoutError: (<urllib3.connection.HTTPSConnection object at 0x7ff2fbebe290>, 'Connection to huggingface.co timed out. (connect timeout=10)')
  27.     The above exception was the direct cause of the following exception:
  29.     Traceback (most recent call last):
  30.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
  31.         resp = conn.urlopen(
  32.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 847, in urlopen
  33.         retries = retries.increment(
  34.       File "/Users/zhaoyao/Downloads/SDW/stable-diffusion-webui/venv/lib/python3.10/site-packages/urllib3/util/retry.py", line 515, in increment
  35.         raise MaxRetryError(_pool, url, reason) from reason  # type: ignore[arg-type]
  36.     urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /CompVis/stable-diffusion-safety-checker/resolve/main/config.json (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x7ff2fbebe290>, 'Connection to huggingface.co timed out. (connect timeout=10)'))

在这里插入图片描述

很显然是绘图时需要访问huggingface.co下载模块

考虑直接添加代理的方式，因为不可能每次画图每次需要下载模块的时候每次手动下载

修改webu.sh

在此文件后追加代理

  1. proxy='socks5://127.0.0.1:1088'
  2. export http_proxy=$proxy
  3. export https_proxy=$proxy
  4. export no_proxy="localhost, *.local, 127.0.0.1, ::1, 192.168.*.*, 10.*.*.*, 172.16-31.*.*, *.baidu.com*, *.bilibili.com*, *.cn*, *.com.cn*, *.csdn.net*, *.51cto*, *tencent*, *qq.com*, *weixin*, *ali*, *dingding*, *huawei*, *xunlei*, *tonghuashun*, *dongfangcaifu*, *i4tool*, *163.com*, *doubanio.com*, *douban*, *youku*"

在这里插入图片描述

绘图时会有如下显示：

在这里插入图片描述

绘图结束显示

在这里插入图片描述
在这里插入图片描述

总结

参考于https://github.com/openvinotoolkit/stable-diffusion-webui
https://openai.wiki/stable-diffusion-webui-localization.html。

标签： stable diffusion macos AI作画
本文转载自: https://blog.csdn.net/z781174454/article/details/136598518
版权归原作者 大漠新人 所有， 如有侵权，请联系我们删除。
登录后发布评论

“【本地化部署Stable Diffusion WebUI（MACOS安装）】”的评论:

还没有评论
关于作者
...
overfit同步小助手
文章同步
相关阅读

网络安全法-网络运行安全

使用selenium/drissionpage时如何阻止chrome自动跳转http到https

docker desktop 里部署的Open WebUI 管理员密码忘记了的处理方法

在ubuntu20.04中搭建onsite比赛运行环境

利用开源的低代码表单设计器FcDesigner高效管理和渲染复杂表单结构

Kafka学习笔记

【前端】浏览器输入url到页面呈现发生了什么？