Stable Diffusion WebUI 集成 sd-webui-segment-anything sd-webui-inpaint-anything Ubuntu22.04 rtx2060 6G

下载插件

sd-webui-segment-anything

cd /home/yeqiang/Downloads/ai/stable-diffusion-webui/extensions
git clone https://github.com/continue-revolution/sd-webui-segment-anything.git

下载分割模型(segmentation models):

显存只有6G，选择l版本

cd /home/yeqiang/Downloads/ai/stable-diffusion-webui/
mkdir models/sam
cd models/sam
# wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth
wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth
# wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth

sd-webui-inpaint-anything

cd /home/yeqiang/Downloads/ai/stable-diffusion-webui/extensions
git clone https://github.com/Uminosachi/sd-webui-inpaint-anything.git

sd-webui-controlnet

cd /home/yeqiang/Downloads/ai/stable-diffusion-webui/extensions
git clone https://github.com/Mikubill/sd-webui-controlnet.git

lllyasviel/ControlNet-v1-1 at main

下载14个.pth模型文件，yaml文件已经在models目录下了

今天下载的新鲜文件，放阿里云盘了

ControlNet-v1-1-20230706

https://www.aliyundrive.com/s/LtpNFP8stg5 

cp ~/Downloads/ai/ControlNet-v1-1/control*.pth extensions/sd-webui-controlnet/models/

启动后又开始安装各种Python依赖。网络环境不行气死人

漫长时间等待后

yeqiang@yeqiang-MS-7B23:~/Downloads/ai/stable-diffusion-webui$ ./webui.sh 
 
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################
 
################################################################
Running on yeqiang user
################################################################
 
################################################################
Repo already cloned, using it as install directory
################################################################
 
################################################################
Create and activate python venv
################################################################
 
################################################################
Launching launch.py...
################################################################
Using TCMalloc: libtcmalloc_minimal.so.4
Python 3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:36:39) [GCC 10.4.0]
Version: v1.4.0
Commit hash: 394ffa7b0a7fff3ec484bcd084e673a8b301ccc8
Installing requirements
Installing sd-webui-segment-anything requirement: segment_anything
Installing sd-webui-segment-anything requirement: supervision
 
Installing requirements for diffusers
Installing requirements for lama_cleaner
Installing requirements for ultralytics
 
Installing sd-webui-controlnet requirement: mediapipe
Installing sd-webui-controlnet requirement: svglib
Installing sd-webui-controlnet requirement: fvcore
 
Launching Web UI with arguments: 
No module 'xformers'. Proceeding without it.
2023-07-06 14:01:44,629 - ControlNet - INFO - ControlNet v1.1.231
ControlNet preprocessor location: /home/yeqiang/Downloads/ai/stable-diffusion-webui/extensions/sd-webui-controlnet/annotator/downloads
2023-07-06 14:01:44,834 - ControlNet - INFO - ControlNet v1.1.231
Loading weights [6ce0161689] from /home/yeqiang/Downloads/ai/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
preload_extensions_git_metadata for 11 extensions took 1.00s
Running on local URL:  http://127.0.0.1:7860
 
To create a public link, set `share=True` in `launch()`.
Startup time: 16.1s (import torch: 3.6s, import gradio: 1.3s, import ldm: 0.4s, other imports: 1.5s, load scripts: 6.4s, create ui: 1.7s, gradio launch: 0.9s).
Creating model from config: /home/yeqiang/Downloads/ai/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying attention optimization: Doggettx... done.
Textual inversion embeddings loaded(0): 
Model loaded in 99.6s (load weights from disk: 5.3s, create model: 1.2s, apply weights to model: 83.6s, apply half(): 8.6s, move model to device: 0.4s, load textual inversion embeddings: 0.2s, calculate empty prompt: 0.3s).