Prompt Engineering for Text-Based Generative Art

Text-based generative art has seen an explosion of interest in 2021. Online communities around text-based generative art as a novel digital medium have quickly emerged. This short paper identifies five types of prompt modifiers used by practitioners in the community of text-based generative art based on a 3-month ethnographic study on Twitter. The novel taxonomy of prompt modifiers provides researchers a conceptual starting point for investigating the practices of text-based generative art, but also may help practitioners of text-based generative art improve their images. The paper concludes with a discussion of research opportunities in the space of text-based generative art and the broader implications of prompt engineering from the perspective of human-AI interaction in future applications beyond the use case of text-based generative art.