Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JURNAL TEKNOLOGI DAN OPEN SOURCE
Shermay
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Optimizing Prompt Engineering for AI-Based Logo Generation Using Response Surface Methodology Shermay; Aklani, Syaeful Anas; Firmansyah, Muhamad Dody
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4959

Abstract

This research developed an optimized prompt engineering framework for AI-based logo generation using Response Surface Methodology (RSM) with Central Composite Design (CCD). Despite rapid AI adoption, users face challenges in communicating design intent effectively, leading to inconsistent outputs. This study systematically tested 47 prompt combinations across five variables: prompt clarity, detail level, thematic description, visual elements, and color specification. The optimization identified eight critical components forming a structured template: Main Design Focus, Detail Elements, Thematic Style, Primary Colors, Complementary Colors, Rewording, Layout Size, and Element Limit. Experimental validation with 30 graphic designers demonstrated substantial improvements over unstructured prompts: visual consistency increased from 65% to 87%, iteration efficiency improved by 48.5% (from 6.6 to 3.4 attempts), and user satisfaction rose from 58% to 82%. Both manual designers and AI-experienced users successfully applied the framework with comparable effectiveness. This research contributes a systematic, optimization-based approach to prompt engineering in creative AI applications and provides a practical framework enhancing accessibility for non-technical users while maintaining professional quality standards in logo desin.
Co-Authors Aklani, Syaeful Anas Firmansyah, Muhamad Dody