安装stable-diffusion

安装流程：

1. 下载stable-diffusion源码

   <https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.2.1>
   

2. 安装python

   <https://www.python.org/ftp/python/3.10.6/python-3.10.6-amd64.exe>
   

3. 添加host

   1. 打开C:\Windows\System32\drivers\etc\host

   2. 添加

      199.232.69.194 github.global-ssl.fastly.net
      140.82.112.3 github.com
      

4. 修改launch.py

   将所有
   <https://github.com>
   替换成
   <https://ghproxy.com/https://github.com>
   

5. 运行stable-diffusion-webui-1.2.1目录下webui-user.bat

   安装时长较长，耐心等待

6. 安装成功日志，主要是出现了地址“http://127.0.0.1:7860”

   venv "G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\venv\\Scripts\\Python.exe"
   Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
   Version: <none>
   Commit hash: <none>
   Cloning Stable Diffusion into G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\repositories\\stable-diffusion-stability-ai...
   Cloning Taming Transformers into G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\repositories\\taming-transformers...
   Cloning K-diffusion into G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\repositories\\k-diffusion...
   Cloning CodeFormer into G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\repositories\\CodeFormer...
   Cloning BLIP into G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\repositories\\BLIP...
   Installing requirements for CodeFormer
   Installing requirements
   Launching Web UI with arguments:
   No module 'xformers'. Proceeding without it.
   Downloading: "" to G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\models\\Stable-diffusion\\v1-5-pruned-emaonly.safetensors
    
   100%|█████████████████████████████████████████████████████████████████████████████| 3.97G/3.97G [15:04<00:00, 4.72MB/s]
   Calculating sha256 for G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\models\\Stable-diffusion\\v1-5-pruned-emaonly.safetensors: Running on local URL:  <http://127.0.0.1:7860>
    
   To create a public link, set `share=True` in `launch()`.
   Startup time: 922.7s (import torch: 1.5s, import gradio: 1.5s, import ldm: 0.5s, other imports: 1.1s, list SD models: 916.2s, load scripts: 1.3s, create ui: 0.4s).
   6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa
   Loading weights [6ce0161689] from G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\models\\Stable-diffusion\\v1-5-pruned-emaonly.safetensors
   Creating model from config: G:\\funny\\stable_diffusion\\tmp\\stable-diffusion-webui-1.2.1\\configs\\v1-inference.yaml
   LatentDiffusion: Running in eps-prediction mode
   DiffusionWrapper has 859.52 M params.
   Downloading (…)olve/main/vocab.json: 100%|███████████████████████████████████████████| 961k/961k [00:02<00:00, 428kB/s]
   Downloading (…)olve/main/merges.txt: 100%|███████████████████████████████████████████| 525k/525k [00:00<00:00, 788kB/s]
   Downloading (…)cial_tokens_map.json: 100%|████████████████████████████████████████████████████| 389/389 [00:00<?, ?B/s]
   Downloading (…)okenizer_config.json: 100%|████████████████████████████████████████████████████| 905/905 [00:00<?, ?B/s]
   Downloading (…)lve/main/config.json: 100%|████████████████████████████████████████████████| 4.52k/4.52k [00:00<?, ?B/s]
   Applying cross attention optimization (Doggettx).
   Textual inversion embeddings loaded(0):
   Model loaded in 17.2s (calculate hash: 3.5s, load weights from disk: 0.2s, create model: 9.0s, apply weights to model: 1.5s, apply half(): 1.0s, move model to device: 0.5s, load textual inversion embeddings: 1.3s).
   

7. 打开chrome，输入http://127.0.0.1:7860

   1. 

注意事项

1. python版本要为3.10.6版本，不然会出现奇怪报错
2. 主要解决的问题就是github下载一些开源工程会超时，只要按照教程修改host和lanch.py就能解决