From Text to Image: A Multimodal Linguocultural Analysis of Uzbek and English Fairy-Tale Heroes Created by AI Image Generators

Authors

  • Fayyozjon Azimov Shahrisabz State Pedagogical Institute Author

Keywords:

Keywords: multimodality, text-to-image generation, visual linguocultureme, fairy-tale hero, cultural bias, Orientalism, visual grammar, artificial intelligence, Uzbek, English.

Abstract

For generations, children have pictured fairy-tale heroes in their own minds: Alpomish riding across the steppe, Zumrad in her colourful atlas dress, a fearsome Dev in his mountain cave, Jack climbing the beanstalk, a witch in her dark cottage. Today these pictures are increasingly made by machines. Text-to-image generators such as DALL·E, Midjourney and Stable Diffusion can turn a character’s name into a detailed illustration in seconds, and teachers, illustrators and parents already use them. This raises a question that is both linguistic and cultural: when a verbal sign such as Dev, Pari or Barchinoy is turned into a visual image, which cultural meanings survive the journey from text to picture?

References

1.Afzalov, M. (1964). O’zbek xalq ertaklari haqida [On Uzbek folk tales]. Tashkent: Fan.

2.Barthes, R. (1977). Rhetoric of the image. In Image, music, text (S. Heath, Trans., pp. 32–51). London: Fontana.

3.Basu, A., Babu, R. V., & Pruthi, D. (2023). Inspecting the geographical representativeness of images from text-to-image models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 5136–5147).

4.Bianchi, F., Kalluri, P., Durmus, E., Ladhak, F., Cheng, M., Nozza, D., Hashimoto, T., Jurafsky, D., Zou, J., & Caliskan, A. (2023). Easily accessible text-to-image generation amplifies demographic stereotypes at large scale. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (pp. 1493–1504). https://doi.org/10.1145/3593013.3594095

5.Birhane, A., Prabhu, V. U., & Kahembwe, E. (2021). Multimodal datasets: Misogyny, pornography, and malignant stereotypes. arXiv preprint arXiv:2110.01963.

6.Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa

7.Cho, J., Zala, A., & Bansal, M. (2023). DALL-Eval: Probing the reasoning skills and social biases of text-to-image generation models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 3043–3054).

8.Forceville, C. (1996). Pictorial metaphor in advertising. London: Routledge.

9.Forceville, C., & Urios-Aparisi, E. (Eds.). (2009). Multimodal metaphor. Berlin: Mouton de Gruyter.

10.Imomov, K. (1981). O’zbek xalq prozasi [Uzbek folk prose]. Tashkent: Fan.

11.Karasik, V. I. (2002). Yazykovoy krug: lichnost’, kontsepty, diskurs [The language circle: Personality, concepts, discourse]. Volgograd: Peremena.

12.Krasnykh, V. V. (2002). Etnopsikholingvistika i lingvokul’turologiya [Ethnopsycholinguistics and linguoculturology]. Moscow: Gnozis.

13.Kress, G. (2010). Multimodality: A social semiotic approach to contemporary communication. London: Routledge.

14.Kress, G., & van Leeuwen, T. (2006). Reading images: The grammar of visual design (2nd ed.). London: Routledge.

15.Krippendorff, K. (2018). Content analysis: An introduction to its methodology (4th ed.). Thousand Oaks, CA: SAGE.

16.Luccioni, A. S., Akiki, C., Mitchell, M., & Jernite, Y. (2023). Stable bias: Evaluating societal representations in diffusion models. In Advances in Neural Information Processing Systems 36: Datasets and Benchmarks Track.

17.Nikolajeva, M., & Scott, C. (2001). How picturebooks work. New York: Garland.

18.Nodelman, P. (1988). Words about pictures: The narrative art of children’s picture books. Athens, GA: University of Georgia Press.

19.Painter, C., Martin, J. R., & Unsworth, L. (2013). Reading visual narratives: Image analysis of children’s picture books. Sheffield: Equinox.

20.Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125.

21.Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10684–10695).

22.Said, E. W. (1978). Orientalism. New York: Pantheon Books.

23.Silver, C. G. (1999). Strange and secret peoples: Fairies and Victorian consciousness. New York: Oxford University Press.

24.Ventura, M., Ben-David, E., Korhonen, A., & Reichart, R. (2023). Navigating cultural chasms: Exploring and unlocking the cultural POV of text-to-image models. arXiv preprint arXiv:2310.01929.

25.Venuti, L. (1995). The translator’s invisibility: A history of translation. London: Routledge.

26.Vorob’ev, V. V. (1997). Lingvokul’turologiya: teoriya i metody [Linguoculturology: Theory and methods]. Moscow: RUDN Publishing.

27.Zhirmunsky, V. M., & Zarifov, H. T. (1947). Uzbekskiy narodnyy geroicheskiy epos [The Uzbek folk heroic epic]. Moscow: OGIZ.

Downloads

Published

2026-11-03