绘画教程 | vol.1 绘画软件Stable Diffusion安装
-1 更新
在最新版的启动器中，开发者秋叶已经将启动器设置python/git路径放到了新的位置，如图所示：
stable diffusion webui 启动器
0 前言
stable diffusion是一种基于深度学习的图像生成技术，它有很多应用，比如人脸生成、风格迁移、动漫画等。如果你想尝试stable diffusion来创作你自己的AI画图，那么你需要先安装它。在这篇文章中，我将向你介绍如何在Win10/Win11上安装stable diffusion，并给出一些使用技巧和注意事项。
这里我提供了一份整合包，里面包含了
- git安装包
- python3.10安装包
- 启动器运行依赖
- stable diffusion WebUI整合包
- 自带dalcefo模型
- 整合Easynegative
整合包下载地址：
链接: https://pan.baidu.com/s/1nNNXH7rxCavcPAZ421D9gw?pwd=aigc
提取码: aigc
如果你是刚接触AI绘画领域的新手，也不用担心，按照我的步骤来，我会教你如何实现像我一样的效果。
0 录屏教程
1 必备环境安装
解压整合包，先打开第一个文件夹
1.1 安装git
git安装很简单，全部按照默认，一步步点“next”即可。
1.2 安装python
这里需要注意！一定要勾上"Add python.exe to PATH", 然后点击Install Now
1.3 安装【启动器运行依赖】
这个没什么好说的，直接点下去就行。
2. Stable Diffusion安装
第一步里的三个软件安装完，我们就进入正式环节了。由于stable diffusion放在github上，大家的网络或多或少会访问不了，因此我这边做了一个整合包，并把国内大佬做的启动器、模型等整合在其中，大家开箱即用。
2.1 解压整合包，放到任意位置
2.2 运行启动器
进入解压好的文件夹，双击打开A启动器.exe
2.3 配置启动器，仔细！
这一步很重要，请大家务必仔细操作。
第一步选择【高级选项】，第二步点击下边红色的【配置按钮】
在这里，我们分别要把第一步骤里安装好的python和git，配置到这里。
更新
在最新版的启动器中，开发者秋叶已经将启动器设置python/git路径放到了新的位置，如图所示：
stable diffusion webui 启动器
python路径
打开C盘 > 用户 > (你的用户名) > AppData > Local > Programs > Python > Python310
选择python.exe，然后确认
python安装路径
git路径
打开C盘 > Program Files > Git > Bin
选择git.exe，然后确认
git位置
找不到你说的这些文件夹怎么办？
不要着急，这些文件夹有可能是隐藏的，windows默认不显示隐藏文件夹，百度一下“win10显示隐藏文件”或者“win11显示隐藏文件”，然后再回来操作就行。
2.4 一键启动
配置完后，关闭窗口，点击右下角的【一键启动】
注：第一次启动，启动器会自动更新和拉取所需文件，如下图所示↓
我这边测试过多台全新电脑，平均时间在10~15分钟左右，请大家一定要保持耐心等待！
2.5 启动成功的标志
当出现这一行字的时候：
Running on local URL: http://0.0.0.0:7860
就说明stable diffusion已经成功在你的电脑上运行起来了，恭喜！
3. 启动成功，第一次绘画测试
随着启动完成，我们在浏览器输入“http://127.0.0.1:7860”，进入操作界面，如下图所示。
我的整合包暂时已经自带了一个绘画模型，可以这么测试：
在prompt里输入
realistic, intricate details, portrait of a girl, purple hair, the fallen, depressed, dark series,Close-up photo,1girl
在negative prompt里输入：
EasyNegative
其他什么都不用改，点击Generate的大按钮，即可生成这样的图片：
到此为止，可以庆祝一下第一篇教程顺利完成了！恭喜你，已经进入充满无穷未知和乐趣的AI绘画领域！
相关文章
这样的报错了，求解决
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb 7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: 0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8
Installing torch and torchvision
Looking in indexes: https://mirrors.bfsu.edu.cn/pypi/web/simple, https://pypi.tuna.tsinghua.edu.cn/simple, https://pypi.doubanio.com/simple, https://download.pytorch.org/whl/cu117
Looking in links: https://mirror.sjtu.edu.cn/pytorch-wheels/torch_stable.html
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', TimeoutError('_ssl.c:980: The handshake operation timed out'))': /pytorch-wheels/torch_stable.html
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProxyError('Cannot connect to proxy.', TimeoutError('_ssl.c:980: The handshake operation timed out'))': /whl/cu117/torch/
Collecting torch==1.13.1+cu117
Downloading https://download.pytorch.org/whl/cu117/torch-1.13.1%2Bcu117-cp310-cp310-win_amd64.whl (2255.4 MB)
求问这个怎么解决的？等待吗
可以了，补充一下，原来第一次打开需要等大概10-15分钟就好了
可以不装C盘嘛
你好，我今晚下载后，版本更新了变为绘世2.0.5 然后高级选项哪里，左下角的红色框框不见了！请问应该去哪里改路径？
最下面的设置，配置模式改成专家，环境设置
第一次进入了，后面重启一直卡在DiffusionWrapper has 859.52 M params有什么办法解决么
可以看看下面这个链接：
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/7901" rel="noopener" target="_blank">github
全都是错误，下载不来
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /pytorch-wheels/torch_stable.html
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /pypi/web/simple/numpy/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /simple/numpy/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /simple/numpy/
Collecting numpy
Downloading https://download.pytorch.org/whl/numpy-1.24.1-cp310-cp310-win_amd64.whl (14.8 MB)
---------------------------------------- 14.8/14.8 MB 8.2 MB/s eta 0:00:00
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /pytorch-wheels/torch_stable.html
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /pypi/web/simple/requests/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /simple/requests/
WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'NewConnectionError(': Failed to establish a new connection: [Errno 11001] getaddrinfo failed')': /simple/requests/
Collecting requests
Downloading https://download.pytorch.org/whl/requests-2.28.1-py3-none-any.whl (62 kB)
---------------------------------------- 62.8/62.8 kB 3.3 MB/s eta 0:00:00
是我网络问题，已经启动了
报错了，都是connection broken网络错误，你需要一个更好的网络环境
已退出进程，代码为 1 (0x00000001)]
提示：检测到 SD-WebUI 进程退出状态不正常，建议前往疑难解答页面扫描错误记录或寻求其他帮助。
RuntimeError: Couldn't install gfpgan.怎么解决
网上看日志，有没有connection timeout
求解决，启动器打开失败。进度条走一会自己就消失了，怎么解决
下载文件.launcher StableDiffusionWebUILauncher.dll 时发生错误:无法成功完成操作，因为文件包含病毒或潜在的垃圾软件。'C:UsersUH\AppData Local Templauncher-a84cbe8a01fc93bc\596592db19128e29cdaa1142096c11488209794f3c9daad80b0cb88f3e1e2f810a29b123b6560fb663de5501e91c1e8f9cda389838d3bae93def5cd22992c23请稍后再次尝试更新
启动器无法打开一直提示这个
4090全天满负荷运转
I don't think the title of your enticle matches the content lol. Just kidding, mainly because I had some doubts after reading the enticle. https://www.binance.com/en/register?ref=P9L9FQKY
The point of view of your article has taught me a lot, and I already know how to improve the paper on gate.oi, thank you. https://www.gate.io/de/signup/XwNAU
Can you be more specific about the content of your article? After reading it, I still have some doubts. Hope you can help me. https://www.binance.com/ro/register?ref=P9L9FQKY
ImportError: cannot import name '_compare_version' from 'torchmetrics.utilities.imports' (C:\Users\67742\AppData\Local\Programs\Python\Python310\lib\site-packages\torchmetrics\utilities\imports.py)
提示：Python 运行时抛出了一个异常。请检查疑难解答页面。
Your article gave me a lot of inspiration, I hope you can explain your point of view in more detail, because I have some doubts, thank you.
有人和我一样的吗？怎么解决啊
Traceback (most recent call last):
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\launch.py", line 361, in
start()
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\launch.py", line 352, in start
import webui
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\webui.py", line 15, in
from modules import import_hook, errors, extra_networks, ui_extra_networks_checkpoints
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\modules\ui_extra_networks_checkpoints.py", line 6, in
from modules import shared, ui_extra_networks, sd_models
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\.launcher\pyinterop.hfkx1kkk0g4q7.zip\swlutils\hook.py", line 188, in exec_module
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\modules\sd_models.py", line 17, in
from modules.sd_hijack_inpainting import do_inpainting_hijack
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\modules\sd_hijack_inpainting.py", line 7, in
import ldm.models.diffusion.ddpm
File "C:\Users\hp\Desktop\AIGC WTF教学\2 解压\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 12, in
import pytorch_lightning as pl
File "C:\Users\hp\AppData\Local\Programs\Python\Python310\lib\site-packages\pytorch_lightning\__init__.py", line 34, in
from pytorch_lightning.callbacks import Callback # noqa: E402
File "C:\Users\hp\AppData\Local\Programs\Python\Python310\lib\site-packages\pytorch_lightning\callbacks\__init__.py", line 25, in
from pytorch_lightning.callbacks.progress import ProgressBarBase, RichProgressBar, TQDMProgressBar
File "C:\Users\hp\AppData\Local\Programs\Python\Python310\lib\site-packages\pytorch_lightning\callbacks\progress\__init__.py", line 22, in
from pytorch_lightning.callbacks.progress.rich_progress import RichProgressBar # noqa: F401
File "C:\Users\hp\AppData\Local\Programs\Python\Python310\lib\site-packages\pytorch_lightning\callbacks\progress\rich_progress.py", line 20, in
from torchmetrics.utilities.imports import _compare_version
ImportError: cannot import name '_compare_version' from 'torchmetrics.utilities.imports' (C:\Users\hp\AppData\Local\Programs\Python\Python310\lib\site-packages\torchmetrics\utilities\imports.py)
提示：Python 运行时抛出了一个异常。请检查疑难解答页面。
Your point of view caught my eye and was very interesting. Thanks. I have a question for you. https://www.binance.info/en/join?ref=RQUR4BEO
Can you be more specific about the content of your article? After reading it, I still have some doubts. Hope you can help me.