Mimesis, Poiesis, and Imagination: Exploring Text-to-Image Generation of Biblical Narratives

TL;DR

This paper examines how AI-generated images of biblical stories, specifically Exodus, reflect artistic, theological, and cultural aspects, highlighting AI's creative potential and inherent biases.

Contribution

It analyzes the stylistic and theological implications of AI-generated biblical imagery, integrating classical concepts of mimesis and poiesis with modern text-to-image models.

Findings

AI produces aesthetically rich visuals

AI reflects biases of training data

AI can augment human imagination in sacred art

Abstract

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.