How to do things with words. Some remarks on generative AI for images
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. Th...
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Artículo revista |
| Lenguaje: | Español |
| Publicado: |
Facultad de Lenguas. Universidad Nacional del Comahue
2023
|
| Materias: | |
| Acceso en línea: | https://revele.uncoma.edu.ar/index.php/lingustica/article/view/5040 |
| Aporte de: |
| id |
I22-R128-article-5040 |
|---|---|
| record_format |
ojs |
| spelling |
I22-R128-article-50402023-11-30T10:14:56Z How to do things with words. Some remarks on generative AI for images Cómo hacer cosas con palabras. Algunas reflexiones en torno a las inteligencias artificiales generativas de imágenes Koza, Walter artificial intelligence images generation prompt linguistic ambiguity natual language inteligencia artificial generativa generación de imágenes prompt ambigüedad lingüística lenguaje natural 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. Actualmente, la inteligencia artificial (IA) se ha convertido en un tema de relevancia y que afecta a diversas disciplinas. Una IA puede pensarse como la capacidad de las máquinas para realizar tareas que normalmente requieren de la inteligencia humana. Dentro de las posibilidades que ofrece el campo, una de las más notables es la IA generativa. Esta se focaliza en la generación de contenido, desde cierta perspectiva, original, como ser texto, imagen, voz, video, entre otras. Para ello, se requiere que el usuario le proporcione a la IA una indicación del producto que desea, mediante un texto escrito, conocido como prompt. Ahora bien, un fenómeno observado es la dificultad de que el resultado generado se corresponda totalmente con lo que el usuario desea, siendo necesario explicitar al máximo la indicación y de la manera menos ambigua posible, lo que en ocasiones se dificulta debido a la naturaleza misma del lenguaje. Aquí presentamos un pantallazo general de lo que son las IA generativas de imágenes y el fenómeno de la ambigüedad lingüística, que incide en la redacción de prompts para la generación de imágenes. Facultad de Lenguas. Universidad Nacional del Comahue 2023-11-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://revele.uncoma.edu.ar/index.php/lingustica/article/view/5040 10.5281/zenodo.10014180 Quintú Quimün. Revista de lingüística; No. 7 (2) jul-dic (2023); Q078 Quintú Quimün. Revista de lingüística; Núm. 7 (2) jul-dic (2023); Q078 2591-541X spa https://revele.uncoma.edu.ar/index.php/lingustica/article/view/5040/62005 https://creativecommons.org/licenses/by-nc-sa/4.0 |
| institution |
Universidad Nacional del Comahue |
| institution_str |
I-22 |
| repository_str |
R-128 |
| container_title_str |
Repositorio de Revistas Electrónicas REVELE (UNComahue) |
| language |
Español |
| format |
Artículo revista |
| topic |
artificial intelligence images generation prompt linguistic ambiguity natual language inteligencia artificial generativa generación de imágenes prompt ambigüedad lingüística lenguaje natural |
| spellingShingle |
artificial intelligence images generation prompt linguistic ambiguity natual language inteligencia artificial generativa generación de imágenes prompt ambigüedad lingüística lenguaje natural Koza, Walter How to do things with words. Some remarks on generative AI for images |
| topic_facet |
artificial intelligence images generation prompt linguistic ambiguity natual language inteligencia artificial generativa generación de imágenes prompt ambigüedad lingüística lenguaje natural |
| author |
Koza, Walter |
| author_facet |
Koza, Walter |
| author_sort |
Koza, Walter |
| title |
How to do things with words. Some remarks on generative AI for images |
| title_short |
How to do things with words. Some remarks on generative AI for images |
| title_full |
How to do things with words. Some remarks on generative AI for images |
| title_fullStr |
How to do things with words. Some remarks on generative AI for images |
| title_full_unstemmed |
How to do things with words. Some remarks on generative AI for images |
| title_sort |
how to do things with words. some remarks on generative ai for images |
| description |
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. |
| publisher |
Facultad de Lenguas. Universidad Nacional del Comahue |
| publishDate |
2023 |
| url |
https://revele.uncoma.edu.ar/index.php/lingustica/article/view/5040 |
| work_keys_str_mv |
AT kozawalter howtodothingswithwordssomeremarksongenerativeaiforimages AT kozawalter comohacercosasconpalabrasalgunasreflexionesentornoalasinteligenciasartificialesgenerativasdeimagenes |
| first_indexed |
2024-08-12T23:05:39Z |
| last_indexed |
2024-08-12T23:05:39Z |
| _version_ |
1807224866458304512 |