A comparison of running Stable Diffusion Automatic1111 on
a Macbook Pro M1 Max, 10 CPU / 32 GPU cores, 32 GB Unified Memory
a PC with a Ryzen 9 and an NVIDIA RTX 4090, 24 GB VRAM, 64 GB RAM
a PC with a Ryzen 5 and an NVIDIA RTX 3060, 12 GB VRAM, 32 GB RAM
Google Colab on a NVIDIA Tesla T4 , 16 GB VRAM, 12 GB RAM
Going through a variety of reallife test cases on each system, comparing their performance price and power usage. Also giving you my personal experiences and conclusions.
Some useful links:
===============
Google Colab Notebook for Automatic1111:
https://colab.research.google.com/git...
Install Automatic1111:
https://github.com/AUTOMATIC1111/stab...
Install Vlad Stable Diffusion:
https://github.com/vladmandic/automatic
00:00 Intro
01:15 Comparing the systems
02:22 Benchmarks
07:33 Ratings
08:19 Conclusion
#benchmark #stablediffusion #automatic1111 #rtx3060 #rtx4090 #macm1 #googlecolab