I fine tuned a version of Stable Diffusion 1.4 for the task of super-resolution, you can find the
trained model on huggingface hub and can run a gradio demo as follows:
1git clone https://github.com/justinpinkney/stable-diffusion.git
2cd stable-diffusion
3python -m venv .venv --prompt sd
4. .venv/bin/activate
5pip install -U pip
6pip install -r requirements.txt
7python scripts/gradio_superres.py
Note since I trained this model there is now an 'official' super res model for Stable Diffusion 2 which you might prefer to use.
