Language as Reality: A Co-Creative Storytelling Game Experience in 1001 Nights using Generative AI

TL;DR

This paper introduces '1001 Nights', an AI-driven storytelling game where players co-create narratives with AI characters, using language to influence the game world, blending interactive storytelling with AI-generated visual content.

Contribution

The paper presents a novel AI-native game that integrates large language models and text-to-image tools to enable dynamic, player-driven storytelling and world-building.

Findings

Players can steer narratives using keywords that influence game elements.

The game demonstrates how AI can expand narrative and visual creativity in interactive experiences.

The approach challenges traditional boundaries between game reality and actual reality.

Abstract

In this paper, we present "1001 Nights", an AI-native game that allows players lead in-game reality through co-created storytelling with the character driven by large language model. The concept is inspired by Wittgenstein's idea of the limits of one's world being determined by the bounds of their language. Using advanced AI tools like GPT-4 and Stable Diffusion, the second iteration of the game enables the protagonist, Shahrzad, to realize words and stories in her world. The player can steer the conversation with the AI King towards specific keywords, which then become battle equipment in the game. This blend of interactive narrative and text-to-image transformation challenges the conventional border between the game world and reality through a dual perspective. We focus on Shahrzad, who seeks to alter her fate compared to the original folklore, and the player, who collaborates with AI to craft narratives and shape the game world. We explore the technical and design elements of implementing such a game with an objective to enhance the narrative game genre with AI-generated content and to delve into AI-native gameplay possibilities.