Github Domestic AI comic tool Storydiffusion installation and usage tutorial: multi-style control, easily set consistent comic characters manually

Try it online: https://replicate.com/camenduru/story-diffusion

Installation method (do not install if your hardware is weak)

Download Anaconda  https://www.anaconda.com/download/success about 10G

Then open cmd and enter the following to install the CamoFormer environment, and install the specified versions of Python and PyTorch:

conda create --name CamoFormer python=3.8.5
conda activate CamoFormer
conda install pytorch==1.12.1 torchvision==0.13.1 cudatoolkit=11.3 -c pytorch

Install Python libraries in this environment

pip install opencv-python
conda install tensorboard
conda install tensorboardX
pip install timm
pip install matplotlib
pip install scipy
pip install einops

You also need to install NVIDIA's apex library, which is used for deep learning optimization:

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Download the dataset and checkpoints:
You need to manually download the dataset and pretrained checkpoints required by the project, and place them in the folders specified by the project

Run the test and evaluation scripts:
Once the environment is set up and the dataset and checkpoints are ready, you can run the test and evaluation scripts to verify the installation
bash test.sh
bash eval.sh