OTHER License
⚠️ NOTICE: This project is no longer maintained. ⚠️
This repository is no longer actively maintained or updated. Users are advised to find alternative solutions or fork the project if they wish to continue development.
Welcome to Deforum Stable Diffusion!
We are a community of programmers and artists who are passionate about making stable diffusion machine learning image synthesis accessible to everyone. Our open source project is designed to be free to use and easy to modify for custom needs and pipelines. We believe in the power of collaboration and are constantly working together to improve and evolve our implementation of stable diffusion. Whether you are an experienced developer or just getting started, we invite you to join us and be a part of this exciting project.
You can now also run Deforum Stable Diffusion easily on Replicate, check out the web demo and the API here
Before you start installing and using Deforum Stable Diffusion, there are a few things you need to do:
ffmpeg -h
in your terminal. If you don't get an error message, you're good to go. A guide for windows (https://phoenixnap.com/kb/ffmpeg-windows).conda install -c anaconda git -y
in your terminal. If you have trouble installing Git via Anaconda, you can use the following links instead:
Once you have completed these steps, you will be ready to install Deforum Stable Diffusion.
To install Deforum Stable Diffusion, follow these steps:
conda create -n dsd python=3.10 -y
conda activate dsd
git clone https://github.com/deforum-art/deforum-stable-diffusion.git
cd deforum-stable-diffusion
python install_requirements.py
python Deforum_Stable_Diffusion.py
There are four ways to run Deforum Stable Diffusion: locally with the .py
file, locally with Jupyter, locally through Colab, and on Colab servers.
To run Deforum Stable Diffusion locally, make sure the dsd
conda environment is active:
conda activate dsd
Then navigate to the stable-diffusion
folder and run either the Deforum_Stable_Diffusion.py
or the Deforum_Stable_Diffusion.ipynb
file. Running the .py
file is the quickest and easiest way to check that your installation is working, however, it is not the best environment for tinkering with prompts and settings.
python Deforum_Stable_Diffusion.py
If you prefer a more Colab-like experience, you can run the .ipynb
file in Jupyter Lab or Jupyter Notebook. To activate Jupyter Lab or Jupyter Notebook from within the stable-diffusion
folder, use either of the following commands:
jupyter-lab
or
jupyter notebook
To run Deforum Stable Diffusion using Colab Local Runtime, make sure the dsd
conda environment is active:
conda activate dsd
Then, open Google Colab, select File > Upload notebook
, and choose the .ipynb
file in the stable-diffusion
folder. Enable the Jupyter extension by running the following command:
jupyter serverextension enable --py jupyter_http_over_ws
Start the server by running the following command:
jupyter notebook --NotebookApp.allow_origin='https://colab.research.google.com' --port=8888 --NotebookApp.port_retries=0
Copy and paste the URL and token provided into the browser to access the Jupyter notebook.
If you need to start over from scratch, you can delete the stable-diffusion
folder and remove the dsd
conda environment with the following set of commands:
conda deactivate
conda env remove -n dsd
With the dsd
environment removed, you can start over with a fresh installation.
Deforum Stable Diffusion provides a wide range of customization and configuration options that allow you to easily tailor the output to your specific needs and preferences. With over 100 different settings available in the main inference notebook, the possibilities are endless.
For more detailed information on how to customize and configure Deforum Stable Diffusion, check out the guide and stay tuned for the upcoming wiki. If you run into any issues while using Deforum Stable Diffusion, here are a few things you can try:
We welcome contributions to Deforum Stable Diffusion from anyone, regardless of experience level. If you are interested in contributing, please reach out to the developers of the Deforum Discord for more information.
All contributions are managed through GitHub, and we maintain branches for work in progress features. We follow the GitFlow branching model, with the dev
branch serving as the main integration branch.
Before submitting a pull request, please make sure to:
Deforum Stable Diffusion is a community-driven, open source project that is free to use and modify. We rely on the support of our users to keep the project going and help us improve it. If you would like to support us, you can make a donation on our Patreon page. Any amount, big or small, is greatly appreciated!
Your support helps us cover the costs of hosting, development, and maintenance, and allows us to allocate more time and resources to improving Deforum Stable Diffusion. Thank you for your support!
this readme was written in collaboration with chat-gpt