Seeing The Words: Evaluating AI-generated Biblical Art
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916705124483072 |
|---|---|
| author | Makimei, Hidde Wang, Shuai van Peursen, Willem |
| author_facet | Makimei, Hidde Wang, Shuai van Peursen, Willem |
| contents | The past years witnessed a significant amount of Artificial Intelligence (AI) tools that can generate images from texts. This triggers the discussion of whether AI can generate accurate images using text from the Bible with respect to the corresponding biblical contexts and backgrounds. Despite some existing attempts at a small scale, little work has been done to systematically evaluate these generated images. In this work, we provide a large dataset of over 7K images using biblical text as prompts. These images were evaluated with multiple neural network-based tools on various aspects. We provide an assessment of accuracy and some analysis from the perspective of religion and aesthetics. Finally, we discuss the use of the generated images and reflect on the performance of the AI generators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16974 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Seeing The Words: Evaluating AI-generated Biblical Art Makimei, Hidde Wang, Shuai van Peursen, Willem Computers and Society Computer Vision and Pattern Recognition Multimedia I.4.8; I.4.0; I.3.3; I.3.0 The past years witnessed a significant amount of Artificial Intelligence (AI) tools that can generate images from texts. This triggers the discussion of whether AI can generate accurate images using text from the Bible with respect to the corresponding biblical contexts and backgrounds. Despite some existing attempts at a small scale, little work has been done to systematically evaluate these generated images. In this work, we provide a large dataset of over 7K images using biblical text as prompts. These images were evaluated with multiple neural network-based tools on various aspects. We provide an assessment of accuracy and some analysis from the perspective of religion and aesthetics. Finally, we discuss the use of the generated images and reflect on the performance of the AI generators. |
| title | Seeing The Words: Evaluating AI-generated Biblical Art |
| topic | Computers and Society Computer Vision and Pattern Recognition Multimedia I.4.8; I.4.0; I.3.3; I.3.0 |
| url | https://arxiv.org/abs/2504.16974 |