Creating Art with AI - Ep. 2.1 - Steps
Stable Diffusion was actually trained to remove noise from very noisy images, using a description of the original image to help it out.
To generate art with it, we give it an image that’s actually just pure random noise, and tell it that it’s actually a cat wearing a space helmet.
Then SD does its best to “recover” the original artwork that it assumes is buried in there somewhere.
It does this by repeatedly removing a little noise at a time, for some total number of steps (e.g., 25). This video explains what those “steps” are, and the impacts of your choice in step count.
Watch video Creating Art with AI - Ep. 2.1 - Steps online without registration, duration hours minute second in high quality. This video was added by user ChrisMcCormickAI 30 May 2023, don't forget to share it with your friends and acquaintances, it has been viewed on our site 242 once and liked it 3 people.