Brief2Design: A Multi-phased, Compositional Approach to Prompt-based Graphic Design
Professional designers work from client briefs that specify goals and constraints but often lack concrete design details. Translating these abstract requirements into visual designs poses a central challenge, yet existing tools address specific aspects or induce fixation through complete outputs. Through interviews with six professional designers, we identified how designers address this challenge: first structuring ambiguous requirements, then exploring individual elements, and finally recombining alternatives. We developed Brief2Design, supporting this workflow through requirement extraction and recommendation, element-level exploration for objects, backgrounds, text, typography, and composition, and flexible recombination of selected elements. A within-subjects study with twelve designers compared Brief2Design against a conversational baseline. The structured approach increased prompt diversity and received high ratings for requirement extraction and recommendation, but required longer generation time and achieved comparable image diversity. These findings reveal that structured workflows benefit requirement clarification at the cost of efficiency, informing design trade-offs for AI-assisted graphic design tools.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
While recent text-to-image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, their performance significantly degrades when confronted with long, detail-intensive prompts required i…
AttributeSpatial ReasoningReconfigurable Holographic Surface-aided Distributed MIMO Radar Systems
Distributed phased Multiple-Input Multiple-Output (phased-MIMO) radar systems have attracted wide attention in target detection and tracking. However, the phase-shifting circuits in phased subarrays contribute to high po…
DiversityGIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning
Pre-trained vision-language models (VLMs) have achieved promising success in many fields, especially with prompt learning paradigm. In this work, we propose GIP-COL (Graph-Injected Soft Prompting for COmpositional Learni…
AttributeCompositional Zero-Shot LearningPrompt LearningZero-Shot LearningMulti-target Detection for Reconfigurable Holographic Surfaces Enabled Radar
Multi-target detection is one of the primary tasks in radar-based localization and sensing, typically built on phased array antennas. However, the bulky hardware in the phased array restricts its potential for enhancing …
A Near-Field Focused Phased-Array Antenna Design Using the Time-Reversal Concept for Weed Control Purpose
Near-field focus (NFF) antennas have been recently used in several applications for different purposes. In this work, the time-reversal (TR) concept is used to shape the phase distribution of the phased array elements fo…