The setup was created by Daniel Gross.
Have a look at Videobook, a neat AI-powered setup created by Developer and AI enthusiast Daniel Gross and released a month ago. According to the creator, Videobook can turn any text into an audiobook and provide Stable Diffusion-generated images taken from Lexica, an online Stable Diffusion search engine, that depict what's being described in the text. The book/audio pairing, commented Daniel, is done via transcript. You can learn more and try the setup yourself by clicking this link.