본문 바로가기
  • Home

A Design and Implementation of Generative AI-based Advertising Image Production Service Application

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(5), pp.31-38
  • DOI : 10.9708/jksci.2024.29.05.031
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : April 19, 2024
  • Accepted : May 16, 2024
  • Published : May 31, 2024

Chang Hee Ok 1 Hyun Sung Lee 2 Min Soo Jeong 3 Yu Jin Jeong 4 Ji An Choi 5 Youngbok Cho 6 Won Joo Lee 7

1서울과학기술대학교
2서강대학교
3대전대학교
4숙명여자대학교
5동국대학교
6안동대학교
7인하공업전문대학

Accredited

ABSTRACT

In this paper, we propose an ASAP(AI-driven Service for Advertisement Production) application that pr ovides a generative AI-based automatic advertising image production service. This application utilizes GP T-3.5 Turbo Instruct to generate suitable background mood and promotional copy based on user-entered k eywords. It utilizes OpenAI's DALL·E 3 model and Stability AI's SDXL model to generate background i mages and text images based on these inputs. Furthermore, OCR technology is employed to improve the accuracy of text images, and all generated outputs are synthesized to create the final advertisement. Addit ionally, using the PILLOW and OpenCV libraries, text boxes are implemented to insert details such as p hone numbers and business hours at the edges of promotional materials. This application offers small busi ness owners who face difficulties in advertising production a simple and cost-effective solution.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.