Recently, most works focus on synthesizing independent images; While for real-world applications, it is common and necessary to generate a series of coherent images for story-telling. In this work, we mainly focus on story visualization and continuation tasks and propose AR-LDM, a latent diffusion model auto-regressively conditioned on history captions and generated images. To my best knowledge, this is the first work successfully leveraging diffusion models for coherent visual story synthesizing.

In this talk, we will explore the use of stable diffusion and diffusion models in Python for generating original stories. We will first introduce the concept of stable diffusion and how it can be used to model the spread of information or ideas. We will then discuss how this can be applied to the task of story generation, and demonstrate how to use Python libraries such as Markovify and OpenAI ChatGPT API.