How to train Stable Diffusion on your photos on a remote GPU using RunPod and Dreambooth
This is the helper to accompany the video tutorial.
!git clone https://github.com/JoePenna/Dreambooth-Stable-Diffusion/
To resize: https://www.birme.net/ - to resize all files in one click (512 x 512)
To convert JPGs to PNGs: https://www.iloveimg.com/jpg-to-image
Easiest way: doesn’t work anymore because Google limited number of downloads from my GoogleDrive
Harder way:
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original
%pip install gdown
!gdown https://drive.google.com/uc?id=
TROUBLESHOOTING:
Make sure you have 120 GB of memory on your RunPod
Make sure it’s an even number of photographs you’re using (16, 18 or 20 photographs are good amount)
If you use community GPU sometimes, you may lose GPU; in that case, stop and rent another one and start over
CUDA out of memory: Run Terminal
ps aux
then look which processes have launcher and webgui and kill them
kill 11 25 26
Fix the path with your new model name
HELPFUL WEBSITES:
Which Celebrity Look Alike Application: