Stable Diffusion Implemented Using TensorFlow and Keras
twitter.com
1 thread
I have made a Stable Diffusion implementation using Tensorflow / Keras. The weights have been ported from the original pytorch code.
This code runs about 4x faster compared to the original Torch implementation on my 8GB M1 MacBook Air. The speedup is on devices with less memory. Still gotta figure out why.
Hey, thanks! Both of my M1 Macs only have 8G of ram, so your work is appreciated.
EDIT: I just followed you on Twitter
How much GPU memory does this version require? Apparently more than 8 GB.