Mimesis, Poiesis, and Imagination: Exploring Text-to-Image Generation of Biblical Narratives
This work addresses the problem of AI's role in sacred art for theologians and AI researchers, but it is incremental as it applies existing methods to a new domain without major technical advances.
The study analyzed AI-generated images of a Biblical narrative using MidJourney, finding that while AI produces aesthetically rich visuals, it reflects biases from training data and lacks genuine creativity or theological depth.
This study explores the intersection of artificial intelligence and the visualization of Biblical narratives by analyzing AI-generated images of Exodus 2:5-9 (Moses found in River Nile) using MidJourney. Drawing on the classical concepts of mimesis (imitation) and poiesis (creative generation), the authors investigate how text-to-image (T2I) models reproduce or reimagine sacred narratives. Through comparative visual analysis, including Google image results and classical paintings, the research evaluates the stylistic, theological, and cultural dimensions of AI-generated depictions. Findings show that while AI excels in producing aesthetically rich and imaginative visuals, it also reflects the biases and limitations of its training data. The study highlights AI's potential to augment human imagination but questions its capacity for genuine creativity, authorial intent, and theological depth. It concludes by suggesting that AI can serve as a creative partner in reinterpreting biblical texts, though its role in sacred art remains complex and contested.