The purpose of this repository and project is to remake the famous stable-diffusion in only one python script, with the least number of lines and in the least complex way.
- Original Txt2Img
- One click install and run (once you've added your .safetensors model)
- Attention syntax
- NVIDIA GPU only (with xformers)
- Saved state in between starts
- GUI
- DPM Adaptive
Simply clone the repository, add your SD1.5 model in the parent directory and run the run.bat or run.sh file.
git clone https://github.com/Aatrick/LightDiffusion-og.git
cd LightDiffusion-og
.\run.bat