Cleaned up version of https://gist.github.com/mrsteyk/74ad3ec2f6f823111ae4c90e168505ac,
which is in turn based on the public_diff_vae.ConvUNetVAE from https://github.com/openai/consistencydecoder.
Install the consistency decoder code (for the inference logic) and download the extracted weights:
| """ | |
| stable diffusion dreaming | |
| creates hypnotic moving videos by smoothly walking randomly through the sample space | |
| example way to run this script: | |
| $ python stablediffusionwalk.py --prompt "blueberry spaghetti" --name blueberry | |
| to stitch together the images, e.g.: | |
| $ ffmpeg -r 10 -f image2 -s 512x512 -i blueberry/frame%06d.jpg -vcodec libx264 -crf 10 -pix_fmt yuv420p blueberry.mp4 |