Teknik Prompt ANVS Progresif untuk Bing Image Creator dan Interpretasi Kesenjangan Gambar AI
DOI:
https://doi.org/10.34010/visualita.v13i1.13967Keywords:
AI Image Generator, Bing Image Creator, Prompt Engineering.Abstract
In the increasingly developing digital era, the mastery of artificial intelligence (AI) image generator technology has become a popular tool for designers, artists, and general users to create images that suit user needs. However, many users still face difficulties in getting image results that meet user expectations. This research is qualitative, trying to gradually create prompts by evaluating the results in order to understand the image creation process from Bing Image Creator. The author developed and tested a formula called ANVS; namely: Adjective, Noun, Verb, and Style, which is designed to help users design effective prompt engineering. This formula is gradually used in developing prompts, starting from simple to quite complex, to explore how each component in ANVS can affect the image results produced by Bing Image Creator. The results of the research are in the form of recording the use of prompts and image results from Bing Image Creator. It is hoped that this research can help in creating the right prompt to produce images that suit user needs, especially for users of the Bing Image Creator platform and/or other similar AI image generators.
Downloads
Downloads
Published
Issue
Section
License
Authors who publish with Visualita agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive public distribution and display of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors wishing to include items (such as images or other media, or any creative works of others whether previously published or not) must contact the original copyright holder to obtain explicit permission to publish these items in Visualital. Writing permission should include: the title(s) of any copyrighted work, original place of publication if applicable, and an acknowledgement of having read Visualita copyright notice. Authors are responsible for obtaining this permission and keeping it in their own records for later verification.
