Simple and fast Colab version, fast-stable-diffusion, +25% speed increase + memory efficient #1267
TheLastBen
started this conversation in
Show and tell
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Colab adaptation for hlky Webui version of stable diffusion implementing the optimization suggested by https://github.com/MatthieuTPHR : huggingface/diffusers#532, using the MemoryEfficientAttention implementation from xformers (cc. @fmassa, @danthe3rd, @blefaudeux) to both speedup the cross-attention speed and decrease its GPU memory requirements.
All you have to do is enter your huggingface token only once and you're all set, the colabs will install the repos and the models inside Gdrive, so the loading will be fast everytime you use it, enjoy !!
from : https://github.com/TheLastBen/fast-stable-diffusion
Beta Was this translation helpful? Give feedback.
All reactions