AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Stable Diffusion Model
This has been a little bit of a magical past year, as we've seen things come about. The stable diffusion model is useful because it can take a sort of noisy imput and d noise it. And so this could be used both for, like, fixing corrupted images, or up scaling images and that sort of thing. It's the general ideas that you haven't an original output, or original, a set of images that you can kind of corrupt intentionally,. Then train your model to decorrupt those or d noise them.