Sustained Context-Aware Image Generation for the Dungeons & Dragons Domain

Dungeons & Dragons (D&D) is a fantasy tabletop role-playing game which has become a subculture phenomenon due to its immense popularity. In a D&D adventure images play a major role in guiding the players emotions and providing additional information regarding the setting. The proposed research attempts to use text extracted from pre-made adventure to generate cohesive and contextually accurate images according to the given setting. We attempt three tactics to reach the goal, by identifying the context behind the text we hope to develop a Natural Language Processing (NLP) model to generate precise prompts to be fed into a diffusion model, then generated images can be filtered and enhanced according to D&D style and finally specific context will be maintained throughout to generate consistent images.