Digital storytelling, essential in entertainment, education, and marketing, faces challenges in production scalability and flexibility. The StoryAgent framework, introduced in this paper, utilizes Large Language Models and generative tools to automate and refine digital storytelling. Employing a top-down story drafting and bottom-up asset generation approach, StoryAgent tackles key issues such as manual intervention, interactive scene orchestration, and narrative consistency. This framework enables efficient production of interactive and consistent narratives across multiple modalities, democratizing content creation and enhancing engagement. Our results demonstrate the framework's capability to produce coherent digital stories without reference videos, marking a significant advancement in automated digital storytelling.

HBO's take on the video game property finally answers the question: What if a big-budget TV or film adaptation stayed faithful to the source material, even repeating the same scenes, lines and big story beats? Because that's exactly what the show does. There are scenes throughout the first season that are direct line reads of key scenes from the game. The nine episodes follow the exact same story beats and almost the same locations as the original game too. People who know the game by heart will likely be able to recite some lines right as they're being spoken in the show.