This repository is a customized fork of the original Stable Diffusion Web UI created by AUTOMATIC1111. It has been tailored for use by TAMU-AI with specific modifications to simplify installation and usage.
For the original repository, please visit: AUTOMATIC1111/stable-diffusion-webui.
Follow the steps below to set up and run the customized Stable Diffusion Web UI:
- Create a Conda environment with Python 3.11:
conda create -n python3.11 python=3.11 -y
- Activate the Conda environment:
conda activate python3.11
- Install
pip
:conda install pip -y pip install --upgrade pip
- Clone the customized repository:
git clone https://github.com/tamu-edu/TAMUAI-stable-diffusion.git
- Navigate to the repository directory:
cd TAMUAI-stable-diffusion
-
Install the required Python packages:
pip install -r requirements.txt
-
Place your model files in the appropriate directory:
- For example,
v2-1_768-ema-pruned.ckpt
andv2-1_512-ema-pruned.ckpt
should be placed in:models/Stable-diffusion/
- For example,
- Run the application:
python launch.py
- If running without a GPU, use the following command:
python launch.py --no-half --api --listen --skip-torch-cuda-test
-
Replace the default
webui-user.sh
with the Conda-specific version:mv webui-user.sh webui-user.sh-bak mv webui-user.sh-conda webui-user.sh
-
Edit
webui-user.sh
and update the Python path:python_cmd="/path/to/conda/env/python"
Replace
/path/to/conda/env/python
with your Python executable path. -
Start the Web UI:
./webui.sh
This fork includes adjustments for TAMU-AI usage, including:
- Simplified installation and setup instructions.
- Added commands for CPU-only usage.
- Conda environment configuration.
This project is a fork of the original Stable Diffusion Web UI created by AUTOMATIC1111. For full documentation and features, please refer to the original repository.
Additional features and improvements are under development. Stay tuned for future updates!
Created by Chuck Zuo, Ph.D. - Let's make TAMU-AI great together!