Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2023
License: CC BY
Data sources: ZENODO
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
CONICET Digital
Article . 2023
License: CC BY NC SA
Data sources: CONICET Digital
ZENODO
Article . 2023
License: CC BY
Data sources: Datacite
ZENODO
Article . 2023
License: CC BY
Data sources: Datacite
versions View all 4 versions
addClaim

Cómo hacer cosas con palabras. Algunas reflexiones en torno a las inteligencias artificiales generativas de imágenes

Authors: Koza, Walter;

Cómo hacer cosas con palabras. Algunas reflexiones en torno a las inteligencias artificiales generativas de imágenes

Abstract

Actualmente, la inteligencia artificial (IA) se ha convertido enun tema de relevancia y que afecta a diversas disciplinas. Una IA puede pensarsecomo la capacidad de las máquinas para realizar tareas que normalmenterequieren de la inteligencia humana. Dentro de las posibilidades que ofreceel campo, una de las más notables es la IA generativa. Esta se focaliza en lageneración de contenido, desde cierta perspectiva, original, como ser texto,imagen, voz, video, entre otras. Para ello, se requiere que el usuario le proporcionea la IA una indicación del producto que desea, mediante un texto escrito,conocido como prompt. Ahora bien, un fenómeno observado es la dificultadde que el resultado generado se corresponda totalmente con lo que el usuariodesea, siendo necesario explicitar al máximo la indicación y de la maneramenos ambigua posible, lo que en ocasiones se dificulta debido a la naturalezamisma del lenguaje. Aquí presentamos un pantallazo general de lo que son lasIA generativas de imágenes y el fenómeno de la ambigüedad lingüística, queincide en la redacción de prompts para la generación de imágenes.

Currently, artificial intelligence (AI) has become a relevant topic that affects various disciplines. AI can be thought of as the ability of machines to perform tasks that typically require human intelligence. Among the possibilities offered by the field, one of the most notable is generative AI. This focuses on generating, form original content, from a certain perspective, such as text, image, voice, video, among others. To do this, the user needs to provide the AI with an indication of the desired product, through a written text known as a prompt. However, an observed phenomenon is the difficulty of generating a result fully corresponding to what the user desires, necessitating the need to explicitly indicate as much as possible and in the least ambiguous way, which is sometimes challenging due to the nature of language itself. This article provides an overview of generative AI for images and the phenomenon of linguistic ambiguity. Subsequently, it reflects on how this affects the formulation of prompts for image generation.

Fil: Koza, Walter Adrián. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de General Sarmiento. Instituto del Desarrollo Humano; Argentina

Country
Argentina
Keywords

LENGUAJE NATURAL, generación de imágenes, https://purl.org/becyt/ford/6.2, inteligencia artificial, ambigüedad lingüística, GENERACIÓN DE IMÁGENES, https://purl.org/becyt/ford/6, INTELIGENCIA ARTIFICIAL GENERATIVA, AMBIGÜEDAD, lingüística, prompt, PROMPT

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green