Skoči na glavni sadržaj

Izvorni znanstveni članak

Exploring the photorealistic capabilities of AI image generators: Stable Diffusion, DALL-E mini and dream by WOMBO

Aleksandra Bernašek Petrinec ; Tehničko veleučilište u Zagrebu, Zagreb, Hrvatska *
Ivan Papiga ; Tehničko veleučilište u Zagrebu, Zagreb, Hrvatska
Katja Milković orcid id orcid.org/0009-0005-8874-9482 ; 3Europapier Adria d.o.o., Zagreb, Hrvatska
Silvio Plehati

* Autor za dopisivanje.


Puni tekst: engleski pdf 1.741 Kb

str. 98-107

preuzimanja: 3

citiraj


Sažetak

In today’s digital age, artificial intelligence plays a key role in transforming the way we create and perceive art and photography. Now it is possible to generate imagined visual content with input of just a few words of text. Rapid technological advancement has led to significant progress in the field of artificial intelligence, which is increasingly being used in various aspects of human life. For recent years, AI tools have become progressively popular in academic circles, particularly for testing various algorithms in the creation of scientific and professional experiments. This paper explores the artificial intelligence generators Stable Diffusion, DALL-E mini, and Dream by WOMBO to study the hypothesis whether high-quality photorealistic images can be created with simple input, without additional iterations.

Ključne riječi

artificial intelligence, photography, Stable Diffusion, DALL-E mini, Dream by WOMBO

Hrčak ID:

320970

URI

https://hrcak.srce.hr/320970

Datum izdavanja:

30.9.2024.

Posjeta: 7 *