Running Stable Diffusion

[AlbertDeFusco]

Hi, all. I’ve gotten Stable Diffusion running on a CPU using anaconda-project, which is provided by default when you install the Anaconda Distribution, to automate conda environment setup and launching of the Jupyter Notebook. Here’s my project

• Stable Diffusion Cpu :: Anaconda.org
• https://github.com/albertdefusco/stable-diffusion-cpu

This project will work on Mac, Linux, and Windows. For me it takes between 10-15 minutes to generate one image on my M1 Pro MacBook. I’m curious to know what hardware you have and how long it takes.

[Valerio_Maggio]

@AlbertDeFusco

For me it takes between 10-15 minutes to generate one image on my M1 Pro MacBook.

I was able to save a few extra minutes (i.e. < 10mins) it using torch MPS backend on Apple M1 chip

For anyone interested, It would just need a small update to the installed package, as well as targeting the mps device for the model.
Namely replacing the pipe object with:
pipe=StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", low_cpu_mem_usage=False).to('mps')