{"id":11710,"date":"2024-05-30T09:21:36","date_gmt":"2024-05-30T01:21:36","guid":{"rendered":"https:\/\/www.1ai.net\/?p=11710"},"modified":"2024-05-30T09:35:32","modified_gmt":"2024-05-30T01:35:32","slug":"%e5%ae%8c%e6%95%b4%e8%af%a6%e7%bb%86%e7%9a%84stable-diffusion-webui%e6%9c%ac%e5%9c%b0%e9%83%a8%e7%bd%b2%ef%bc%8cai%e7%bb%98%e7%94%bb%e5%88%b6%e4%bd%9c%e5%b1%9e%e4%ba%8e%e8%87%aa%e5%b7%b1%e7%89%88","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/11710.html","title":{"rendered":"Complete and detailed stable diffusion webUI local deployment, AI painting to create pictures with your own copyright"},"content":{"rendered":"
\"get-726\"<\/div>\n

Recently, I spent a week debugging and solving problems encountered during the installation process, and finally completed the startup of stable-diffusion-webui and successfully generated pictures.<\/p>\n

I'll make a note here and share it with everyone, hoping it can help you avoid some pitfalls.<\/p>\n

Next, let's learn stable-difffusion-webui together.<\/p>\n

Preliminary preparation<\/h1>\n

Hardware<\/u><\/strong><\/p>\n

Huawei Matebook 16s<\/p>\n

Processor 13th Gen Intel(R) Core(TM) i9-13900H 2.60 GHz<\/p>\n

Onboard RAM 32.0 GB (31.7 GB available)<\/p>\n

System Type 64-bit operating system, x64-based processor<\/p>\n

Pen and Touch provides touch support for 10 touch points<\/p>\n

Version Windows 11 Home Chinese Edition
\nVersion 23H2
\nInstallation date 2023\/\u200e10\/\u200e12
\nOS version 22631.3593
\nExperience Windows Feature Experience Pack 1000.22700.1003.0<\/p>\n

\"get-725\"<\/div>\n

Procedure<\/u><\/strong><\/p>\n

    \n
  1. Install Python.<\/li>\n
  2. Install Git.<\/li>\n
  3. Install Rust.<\/li>\n
  4. Clone stable-diffusion-webui to your local computer.<\/li>\n
  5. Download the stable-diffusion model.<\/li>\n
  6. Run stable-diffusion-webui.<\/li>\n<\/ol>\n

    Precautions<\/u><\/strong><\/p>\n

    The computer is equipped with Intel(R) Iris(R) Xe Graphics, so the selected stable-diffusion-webui needs to use the version that supports Intel graphics, that is, the OpenVINO version.<\/p>\n

    OpenVINO download link:https:\/\/github.com\/openvinotoolkit\/stable-diffusion-webui<\/u><\/p>\n

    Python version: Python 3.10.11<\/p>\n

    PS: Regarding the Python version, I first downloaded Python 3.12.3, but when I installed the dependency package, it said it was not supported and I needed to download Python 3.8.x. Then I downloaded and installed 3.8.x, but when I installed the dependency package, it said it was not supported again. Finally, I downloaded Python 3.10.11 to install the necessary dependency packages.<\/p>\n

    Install Python<\/h1>\n

    References[AI Learning] Nanny-level tutorial, step-by-step on how to install Python on your computer (Windows users)<\/a>, and complete the Python installation.<\/p>\n

    PS: You need to pay attention to the Python version. Download the latest 3.12.3 version. When installing the dependent package, it will prompt that it is not supported. It is recommended to choose version 3.10.x.<\/p>\n

    Install Git<\/strong><\/p>\n

    References[AI Learning] Nanny-level tutorial, step-by-step on how to install Git on your computer (Windows users)<\/a>, complete the Git installation.<\/p>\n

    Git is installed to make it easier to clone stable-diffusion-webui to your local computer.<\/p>\n

    Install Rust<\/strong><\/p>\n

    References[AI Learning] Nanny-level tutorial! Teach you step by step how to download and install Rust? (AI helps solve problems)<\/a>, and you are done with the Rust installation.<\/p>\n

    Rust is installed to resolve an error when building the tokenizers package.<\/p>\n

    Clone the CPU version of stable-diffusion-webui<\/strong><\/p>\n

    Go to the stable-diffusion folder in the D drive of the local computer and create a new folder openvino.<\/p>\n

    \"get-722\"<\/div>\n

    Run the command prompt window as an administrator and enter the openvino folder path.<\/p>\n

    Enter the command line as follows:<\/p>\n

    \"get-723\"<\/div>\n

    Use Git to clone the https:\/\/github.com\/openvinotoolkit\/stable-diffusion-webui.git project.<\/p>\n

    Enter the command line:<\/p>\n

    git clone https:\/\/github.com\/openvinotoolkit\/stable-diffusion-webui.git<\/code><\/pre>\n
    The project was cloned successfully, and the openvino folder had an additional stable-diffusion-webui folder project.<\/p>\n
    \"get-724\"<\/div>\n
    At this point, the stable-diffusion-webui project cloning of the CPU version is completed.<\/p>\n
    downloadStable Diffusion<\/a>Model<\/strong><\/p>\n
    Enter https:\/\/huggingface.co\/runwayml\/stable-diffusion-v1-5\/blob\/main\/v1-5-pruned-emaonly.safetensors in the browser and press Enter to enter the stable diffusion model download page. Click the [download] text in the red box to download the model.<\/p>\n
    \"get-727\"<\/div>\n
    Downloading. With 4G, the download may take some time.<\/p>\n
    \"get-729\"<\/div>\n
    After downloading the model, copy and paste it into the models\/Stable-diffusion folder of the current project.<\/p>\n
    D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\models\\Stable-diffusion<\/p>\n
    \"get-728\"<\/div>\n
    PS: If you need to enable a new model later, just put it in this path.<\/p>\n
    More models can be downloaded from the following two websites:<\/p>\n
    https:\/\/civitai.com\/<\/p>\n
    https:\/\/www.liblib.art\/<\/p>\n
    Create a Python Virtual Environment<\/strong><\/p>\n
    Run the command prompt as an administrator to enter the command prompt window.<\/p>\n
    Enter the D drive and enter the command line: D:<\/p>\n
    Enter the stable-diffusion-webui folder and enter the command line: cd D:\\stable-diffusion\\openvino\\stable-diffusion-webui<\/p>\n
    Create a virtual environment named sd and enter the command line: python -m venv sd<\/p>\n
    \"get-730\"<\/div>\n
    Activate Python Virtual Environment<\/strong><\/p>\n
    Run the command prompt as an administrator to enter the command prompt window.<\/p>\n
    Enter the D drive and enter the command line: D:<\/p>\n
    Go to the folder D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\venv\\Scripts and enter the command line: cd D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\venv\\Scripts.<\/p>\n
    After entering the folder, enter the command line: activate to activate the environment.<\/p>\n
    \"get-731\"<\/div>\n
    Enter the sd virtual environment.<\/p>\n
    \"get-732\"<\/div>\n
    At this point, we have successfully activated the sd virtual environment. Next, we can start stable-diffusion-webui here.<\/p>\n
    Start stable-diffusion-webui<\/strong><\/p>\n
    Upgrade pip version<\/h1>\n
    In the sd virtual environment, before installing dependent packages, upgrade pip to the latest version to avoid subsequent installation failures due to pip versions.<\/p>\n
    command line: python.exe-mip install-upgrad pip<\/p>\n
    \"get-736\"<\/div>\n
    Start stable-diffusion-webui<\/h1>\n
    When you start stable-diffusion-webui for the first time, the missing dependency packages will be automatically downloaded and installed.<\/p>\n
    Enter the start-up command line under (sd) D:\\stable-diffusion\\openvino\\stable-diffusion-webui> path: py launch.py \u2013skip-torch-cuda-test \u2013precision full-no-half<\/p>\n
    \"get-734\"<\/div>\n
    PS: Since my computer does not have a NVIDIA graphic card, add \"jumping PyTorch CUDA test, using full precision and prohibiting half-accuracy\" to run launch.py \u2013skip-torch-cuda-test \u2013precision full-no-half<\/p>\n
    It takes a long time to download and install the dependency packages for the first startup. The network speed of Guotou is about 1M\/S, and it takes about 1 hour and 20 minutes.<\/p>\n
    (sd) D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\sd\\Scripts>python.exe -m pip install --upgrade pip\r\nRequirement already satisfied: pip in d:\\stable-diffusion\\openvino\\stable-diffusion-webui\\sd\\lib\\site-packages (23.0.1)\r\nCollecting pip\r\n  Downloading pip-24.0-py3-none-any.whl (2.1 MB)\r\n     ---------------------------------------- 2.1\/2.1 MB 940.0 kB\/s eta 0:00:00\r\nInstalling collected packages: pip\r\n  Attempting uninstall: pip\r\n    Found existing installation: pip 23.0.1\r\n    Uninstalling pip-23.0.1:\r\n      Successfully uninstalled pip-23.0.1\r\nSuccessfully installed pip-24.0\r\n\r\n(sd) D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\sd\\Scripts>py launch.py --skip-torch-cuda-test --precision full --no-half\r\nD:\\Program Files\\python310\\python.exe: can't open file 'D:\\\\stable-diffusion\\\\openvino\\\\stable-diffusion-webui\\\\sd\\\\Scripts\\\\launch.py': [Errno 2] No such file or directory\r\n\r\n\r\n\r\n\r\n(sd) D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\sd\\Scripts>cd ..\r\n\r\n\r\n\r\n\r\n(sd) D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\sd>cd ..\r\n\r\n\r\n\r\n\r\n(sd) D:\\stable-diffusion\\openvino\\stable-diffusion-webui>py launch.py --skip-torch-cuda-test --precision full --no-half\r\nfatal: No names found, cannot describe anything.\r\nPython 3.10.11 (tags\/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]\r\nVersion: 1.6.0\r\nCommit hash: e5a634da06c62d72dbdc764b16c65ef3408aa588\r\nInstalling torch and torchvision\r\nLooking in indexes: https:\/\/pypi.org\/simple, https:\/\/download.pytorch.org\/whl\/cu118\r\nCollecting torch==2.0.1\r\n  Downloading https:\/\/download.pytorch.org\/whl\/cu118\/torch-2.0.1%2Bcu118-cp310-cp310-win_amd64.whl (2619.1 MB)\r\n     ---------------------------------------- 2.6\/2.6 GB 581.4 kB\/s eta 0:00:00\r\nCollecting torchvision==0.15.2\r\n  Downloading https:\/\/download.pytorch.org\/whl\/cu118\/torchvision-0.15.2%2Bcu118-cp310-cp310-win_amd64.whl (4.9 MB)\r\n     ---------------------------------------- 4.9\/4.9 MB 792.0 kB\/s eta 0:00:00\r\nCollecting filelock (from torch==2.0.1)\r\n  Downloading filelock-3.14.0-py3-none-any.whl.metadata (2.8 kB)\r\nCollecting typing-extensions (from torch==2.0.1)\r\n  Downloading typing_extensions-4.11.0-py3-none-any.whl.metadata (3.0 kB)\r\nCollecting sympy (from torch==2.0.1)\r\n  Downloading https:\/\/download.pytorch.org\/whl\/sympy-1.12-py3-none-any.whl (5.7 MB)\r\n     ---------------------------------------- 5.7\/5.7 MB 531.7 kB\/s eta 0:00:00\r\nCollecting networkx (from torch==2.0.1)\r\n  Downloading networkx-3.3-py3-none-any.whl.metadata (5.1 kB)\r\nCollecting jinja2 (from torch==2.0.1)\r\n  Downloading jinja2-3.1.4-py3-none-any.whl.metadata (2.6 kB)\r\nCollecting numpy (from torchvision==0.15.2)\r\n  Downloading numpy-1.26.4-cp310-cp310-win_amd64.whl.metadata (61 kB)\r\n     ---------------------------------------- 61.0\/61.0 kB 1.6 MB\/s eta 0:00:00\r\nCollecting requests (from torchvision==0.15.2)\r\n  Downloading requests-2.32.2-py3-none-any.whl.metadata (4.6 kB)\r\nCollecting pillow!=8.3.*,>=5.3.0 (from torchvision==0.15.2)\r\n  Downloading pillow-10.3.0-cp310-cp310-win_amd64.whl.metadata (9.4 kB)\r\nCollecting MarkupSafe>=2.0 (from jinja2->torch==2.0.1)\r\n  Downloading https:\/\/download.pytorch.org\/whl\/MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl (17 kB)\r\nCollecting charset-normalizer<4,>=2 (from requests->torchvision==0.15.2)\r\n  Downloading charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl.metadata (34 kB)\r\nCollecting idna<4,>=2.5 (from requests->torchvision==0.15.2)\r\n  Downloading idna-3.7-py3-none-any.whl.metadata (9.9 kB)\r\nCollecting urllib3<3,>=1.21.1 (from requests->torchvision==0.15.2)\r\n  Downloading urllib3-2.2.1-py3-none-any.whl.metadata (6.4 kB)\r\nCollecting certifi>=2017.4.17 (from requests->torchvision==0.15.2)\r\n  Downloading certifi-2024.2.2-py3-none-any.whl.metadata (2.2 kB)\r\nCollecting mpmath>=0.19 (from sympy->torch==2.0.1)\r\n  Downloading https:\/\/download.pytorch.org\/whl\/mpmath-1.3.0-py3-none-any.whl (536 kB)\r\n     ---------------------------------------- 536.2\/536.2 kB 560.7 kB\/s eta 0:00:00\r\nDownloading pillow-10.3.0-cp310-cp310-win_amd64.whl (2.5 MB)\r\n   ---------------------------------------- 2.5\/2.5 MB 938.3 kB\/s eta 0:00:00\r\nDownloading filelock-3.14.0-py3-none-any.whl (12 kB)\r\nDownloading jinja2-3.1.4-py3-none-any.whl (133 kB)\r\n   ---------------------------------------- 133.3\/133.3 kB 984.2 kB\/s eta 0:00:00\r\nDownloading networkx-3.3-py3-none-any.whl (1.7 MB)\r\n   ---------------------------------------- 1.7\/1.7 MB 820.2 kB\/s eta 0:00:00\r\nDownloading numpy-1.26.4-cp310-cp310-win_amd64.whl (15.8 MB)\r\n   ---------------------------------------- 15.8\/15.8 MB 904.1 kB\/s eta 0:00:00\r\nDownloading requests-2.32.2-py3-none-any.whl (63 kB)\r\n   ---------------------------------------- 63.9\/63.9 kB 383.3 kB\/s eta 0:00:00\r\nDownloading typing_extensions-4.11.0-py3-none-any.whl (34 kB)\r\nDownloading certifi-2024.2.2-py3-none-any.whl (163 kB)\r\n   ---------------------------------------- 163.8\/163.8 kB 1.1 MB\/s eta 0:00:00\r\nDownloading charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl (100 kB)\r\n   ---------------------------------------- 100.3\/100.3 kB 1.2 MB\/s eta 0:00:00\r\nDownloading idna-3.7-py3-none-any.whl (66 kB)\r\n   ---------------------------------------- 66.8\/66.8 kB 898.3 kB\/s eta 0:00:00\r\nDownloading urllib3-2.2.1-py3-none-any.whl (121 kB)\r\n   ---------------------------------------- 121.1\/121.1 kB 786.0 kB\/s eta 0:00:00\r\nInstalling collected packages: mpmath, urllib3, typing-extensions, sympy, pillow, numpy, networkx, MarkupSafe, idna, filelock, charset-normalizer, certifi, requests, jinja2, torch, torchvision\r\nSuccessfully installed MarkupSafe-2.1.5 certifi-2024.2.2 charset-normalizer-3.3.2 filelock-3.14.0 idna-3.7 jinja2-3.1.4 mpmath-1.3.0 networkx-3.3 numpy-1.26.4 pillow-10.3.0 requests-2.32.2 sympy-1.12 torch-2.0.1+cu118 torchvision-0.15.2+cu118 typing-extensions-4.11.0 urllib3-2.2.1\r\nInstalling clip\r\nInstalling open_clip\r\nInstalling requirements for CodeFormer\r\nInstalling requirements\r\nLaunching Web UI with arguments: --skip-torch-cuda-test --precision full --no-half\r\nno module 'xformers'. Processing without...\r\nno module 'xformers'. Processing without...\r\nNo module 'xformers'. Proceeding without it.\r\nWarning: caught exception 'Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http:\/\/www.nvidia.com\/Download\/index.aspx', memory monitor disabled\r\nCalculating sha256 for D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\models\\Stable-diffusion\\stableDiffusionXL_v10Roundeyes.safetensors: Running on local URL:  http:\/\/127.0.0.1:7860\r\n\r\n\r\n\r\n\r\nTo create a public link, set `share=True` in `launch()`.\r\nStartup time: 4703.9s (prepare environment: 4677.7s, import torch: 10.2s, import gradio: 3.8s, setup paths: 4.1s, initialize shared: 0.6s, other imports: 3.2s, setup codeformer: 0.2s, load scripts: 2.8s, create ui: 1.0s, gradio launch: 0.2s).\r\n8744a0dc449420be1ef1cc51588fe4388b395ce1c17166e67edccfa7d4a3c40a\r\nLoading weights [8744a0dc44] from D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\models\\Stable-diffusion\\stableDiffusionXL_v10Roundeyes.safetensors\r\nCreating model from config: D:\\stable-diffusion\\openvino\\stable-diffusion-webui\\repositories\\generative-models\\configs\\inference\\sd_xl_base.yaml\r\nApplying attention optimization: InvokeAI... done.\r\nModel loaded in 16.5s (calculate hash: 8.4s, load weights from disk: 0.9s, create model: 0.7s, apply weights to model: 3.3s, apply float(): 2.3s, calculate empty prompt: 0.9s).<\/code><\/pre>\n
    Successfully opened stable-diffusion-webui.<\/p>\n
    \"get-733\"<\/div>\n
    \"get-735\"<\/div>\n
    Try to generate a graph.<\/p>\n
    Prompt word: a dog smile.<\/p>\n
    \"get-737\"<\/div>\n
    Switching models can also generate images normally.<\/p>\n
    \"get-738\"<\/div>\n
    \"get-739\"<\/div>\n
    But the memory was suddenly increased to 27.7G, which was almost used up.<\/p>\n
    \"get-740\"<\/div>\n
    CPU: 13th Gen Intel(R) Core(TM) i9-13900H, much higher performance.<\/p>\n
    \"get-741\"<\/div>\n
    GPU: Intel(R) Iris(R) Xe Graphics, not used.<\/p>\n
    \"get-742\"<\/div>\n
    At this point, we have completed the installation and operation of stable-diffusion-webui and successfully drawn pictures on the local computer.<\/p>\n
    However, due to limited hardware conditions and the lack of NVIDIA graphics cards, Vincent Image still takes a long time to run, and this computer still has difficulty running Vincent Image.<\/p>\n
     <\/p>","protected":false},"excerpt":{"rendered":"
    Recently, after spending a week, debugging off and on to solve the problems encountered during the installation process, I finally finished starting stable-diffusion-webui and successfully generated images. Here to make a note, but also by the way to share with you, I hope to help less step on some pits. Here, let's learn stable-diffusion-webui together. Preparation Hardware Devices Huawei Matebook 16s Processor 13th Gen Intel(R) Core(TM) i9-13900H 2.60 GHz Carrying capacity RAM 32.0 GB (31.7 GB available) System type 64-bit operating system, x64-based processor<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[144],"tags":[491,197,2852],"collection":[],"class_list":["post-11710","post","type-post","status-publish","format-standard","hentry","category-baike","tag-ai","tag-stable-diffusion","tag-2852"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/11710","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=11710"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/11710\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=11710"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=11710"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=11710"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=11710"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}