Text-to-image technologies. The Aesthetic implications of AI-generated images.

Autori/Autrici

DOI:

https://doi.org/10.54103/2039-9251/27839

Abstract

Synthography, a term that describes images generated by Text-to-Image (TTI) technologies such as DALL·E, Midjourney, and Stable Diffusion, enables the creation of images generated through software that involve linguistic prompts. Such prompts are processed by encoded semantic systems, able to capture compositional aspects of arbitrary language text inputs. By drawing on the emerging aesthetic theories on AI-generated images, this contribution aims at discussing the European AI-Act, published in March 2024.

Firstly, it analyzes the Act's perspective on synthographies, highlighting how it interprets generative AI within the paradigm of copying and technical reproducibility. Secondly, the paper discusses the regulatory challenges posed by AI-generated content, which blurs the line between original works and replicas, raising concerns about copyright and the authenticity of creative outputs. Third, the study explores the Act's paragraph regarding AI systems that produce content resembling existing images, as it concerns the testimonial value of images. Finally, this contribution examines the possible contribution offered by AI-generated images in the field of the visual art.

Downloads

I dati di download non sono ancora disponibili.

Riferimenti bibliografici

Arielli, E., Manovich, L. AI-aesthetics and the Anthropocentric Myth of Creativity, in “Nodes Journal of Art and Neuroscience”, 19(1), 2022.

Bajohr, H., Operative ekphrasis: The collapse of the text/image distinction in multimodal AI, in “Word & Imag”, 40(2), 2024, pp. 77-90.

Barthes, R, La chambre claire. Note sur la photographie, Gallimard, Paris, 1980, p. 49.

Bazin, A., Ontologie de l’image photographique (1944, in “Qu’est-ce que le cinéma”, Cerf, Paris, 1990, pp. 12-13.

Benjamin, W., Kleine Geschichte der Photographie (1931), Alexander Verlag, Berlin, 2023.

Bolter, J. D., AI Generative Art as Algorithmic Remediation, in „IMAGE. Zeitschrift für interdisziplinäre Bildwissenschaft“, 19(1), 2023, pp. 195-207.

Chatonsky, G., Somaini, A., Sortir du paradigme de la copie, in “Numérique”, 2024.

D’Isa, F., La rivoluzione algoritmica delle immagini. Arte e intelligenza artificiale, Sossella editore, 2024.

Esser, P., et al., Scaling Rectified Flow Transformers for High-Resolution Image Synthesis, in “arXiv”, 2024.

European Parliament. Artificial Intelligence Act, 105. https://www.europarl.europa.eu/doceo/document/TA-9-2024-0138_EN.pdf

Fineman, M., Faking it: Manipulated photography before Photoshop, Metropolitan Museum of Art, New York, 2012.

Goodman, N., Languages of arts. An approach to a theory of symbols, Indianapolis-New York, The Bobbs-Merrill Company, 1968.

Golatkar, A., et al., Mixed Differential Privacy in Computer Vision, CVPR, 2022.

Greenberg, C., Modernist Painting (1960), in J. O’Brian, The Collected Essays and Criticism, IV: 1957-1969, University of Chicago Press, Chicago, 1993, p. 86.

Gunthert, A., L’image partagée. La photographie numérique, Éditions Textuel, Paris, 2015.

Hausken, L., Photorealism versus photography. AI-generated depiction in the age of visual disinformation, in “Journal of Aesthetics & Culture”, 16(1), 2024, pp. 1-13.

Ho, J., et al., Denoising Diffusion Probabilistic Models, NeurIPS, 2020.

Kelly, J., Photographic Reality and French Literary Realism. Nineteenth-Century Synchronism and Symbiosis, in “French Review”, LXV(2), 1991, pp. 195-205.

Krauss, R., Notes on the Index: Seventies Art in America, in “October”, Vol. 3, 1977, pp. 68-81.

Levin, T. Y., Frohne, U., Weibel, P. (Eds), CTRL (Space) – Rhetorics of Surveillance from Bentham to Big Brother, MIT Press, Chicago, 2002.

Manovich, L., Defining AI arts: three proposals, in AI and dialogue of cultures exhibition catalog, http://manovich.net/index.php/projects/defining-ai-arts-three-proposals, 2019.

L. Manovich, Separate and Reassemble: Generative AI Through the Lens of Art and Media Histories, in L. Manovich, E. Arielli, Artificial Aesthetics, 2019. Available at: https://manovich.net/content/04-projects/170-artificial-aesthetics/manovich-artificial-aesthetics-ch7.pdf.

Maynial, E. ,L'Epoque realiste, Les CEuvres representatives, Paris, 1931.

Maynard, P., Talbot's Technologies: Photographic Depiction, Detection, and Reproduction, in “The Journal of Aesthetics and Art Criticism”, 1989, 47 (1), pp. 263-276.

Perini, L. , Depiction, detection, and the epistemic value of photography, in “The Journal of Aesthetics and Art Criticism”, 70(1), 2012, pp. 151-160.

Ramesh, A., et al., Hierarchical text-conditional image generation with CLIP latents, in “arXiv”, 2022.

Rini, R., Deepfakes and the Epistemic Backstop, in “Philosophers' Imprint”, 20(24), 1–16, 2020.

Rubinstein, D., How photography changed philosophy, Routledge, New York, 2023.

Schramowski, P., et al., Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models, CVPR, 2023.

Somaini, A., Algorithmic Images: Artificial Intelligence and Visual Culture, in “Grey Room”, 93, 2023, pp. 74-115.

Talbot, W.H. Fox, The Pencil of Nature. Longman, Brown, Green and Longmans, London, 1844.

Yin, T., et al., One-step diffusion with distribution matching distillation, CVPR, 2024.

Pubblicato

2024-12-31

Come citare

Manera, L. (2024). Text-to-image technologies. The Aesthetic implications of AI-generated images . Itinera, (28). https://doi.org/10.54103/2039-9251/27839