Exploring 12 Million of the 2.3 Billion Images Used to Train Stable Diffusion's Image Generator - Waxy.org

- Billions of images are scraped from the internet. These images, along with their text descriptions, are saved in a database. - The AI model uses this database to train through reverse diffusion. - Diffusion adds noise to an image (from the dog to random pixels). - Reverse diffusion turns noise back into an image.

By 2014, there were almost 400 million CC-licensed photos on Flickr. That year, researchers from Yahoo Labs, Lawrence Livermore National Laboratory, Snapchat and In-Q-Tel used a quarter of all these photos to create YFCC100M, a dataset of 100 million photographs of people created for computer vision applications. Until today, this dataset remains o... See more