s87343472
commented
1 month ago 中文版本
打开Anaconda Powershell Prompt (miniconda3)
创建并激活Conda环境
conda create -n paints_undo python=3.10
预期结果：创建环境成功后，会看到类似以下的输出：
...
done
To activate this environment, use
$ conda activate paints_undo
To deactivate an active environment, use
$ conda deactivate
conda activate paints_undo
预期结果：激活环境成功后，命令行提示符会变成 (paints_undo) 开头。
安装PyTorch和相关库
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
预期结果：安装成功后，会看到类似以下的输出：
...
Proceed ([y]/n)? y
...
done
克隆并进入项目目录
git clone https://github.com/lllyasviel/Paints-UNDO.git cd Paints-UNDO
预期结果：克隆成功后，会看到类似以下的输出：
Cloning into 'Paints-UNDO'...
...
安装项目依赖项
pip install xformers
预期结果：安装成功后，会看到类似以下的输出：
...
Successfully installed xformers-
pip install -r requirements.txt
预期结果：安装成功后，会看到类似以下的输出：
...
Successfully installed
解决依赖冲突
pip uninstall huggingface_hub gradio gradio-client transformers diffusers peft tokenizers httpx httpcore
预期结果：卸载成功后，会看到类似以下的输出：
...
Successfully uninstalled
pip install huggingface_hub==0.23.2 pip install gradio==3.1.4 pip install gradio_client==0.1.3 pip install transformers==4.23.1 pip install diffusers==0.3.0 pip install peft==0.2.0 pip install tokenizers==0.13.2 pip install httpx==0.23.0 pip install httpcore==0.15.0
预期结果：安装成功后，会看到类似以下的输出：
...
Successfully installed
验证CUDA是否可用
python -c "import torch; print(torch.cuda.is_available())"
预期结果：如果CUDA可用，会看到输出 True：
True
运行应用程序
python gradio_app.py
Open Anaconda Powershell Prompt (miniconda3)
Create and activate the Conda environment
Expected result: After successfully creating the environment, you will see output similar to the following:
...
done
To activate this environment, use
$ conda activate paints_undo
To deactivate an active environment, use
$ conda deactivate
Expected result: After successfully activating the environment, the command prompt will start with
(paints_undo).Install PyTorch and related libraries
Expected result: After successful installation, you will see output similar to the following:
...
Proceed ([y]/n)? y
...
done
Clone and enter the project directory
Expected result: After successfully cloning, you will see output similar to the following:
Cloning into 'Paints-UNDO'...
...
Install project dependencies
Expected result: After successful installation, you will see output similar to the following:
...
Successfully installed xformers-
Expected result: After successful installation, you will see output similar to the following:
...
Successfully installed
Resolve dependency conflicts
Expected result: After successful uninstallation, you will see output similar to the following:
...
Successfully uninstalled
Expected result: After successful installation, you will see output similar to the following:
...
Successfully installed
Verify if CUDA is available
Expected result: If CUDA is available, you will see the output
True:True
Run the application
Expected result: If everything is correct, the Gradio application will start, and a local server address such as
http://127.0.0.1:7860will be displayed in the command line, which you can open in a browser to access the application.