Brief2Design: A Multi-phased, Compositional Approach to Prompt-based Graphic Design

• URL: http://arxiv.org/abs/2604.11019v1
• Date: Mon, 13 Apr 2026 05:34:24 GMT
• Title: Brief2Design: A Multi-phased, Compositional Approach to Prompt-based Graphic Design
• Abstract summary: Designers work from client briefs that specify goals and constraints but often lack concrete details.<n>We identified how designers address this challenge: first structuring ambiguous requirements, then exploring individual elements, and finally recombining alternatives.<n>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.
• Score: 7.882054267714632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow [80.29423400249944]
  PSDesigner is an automated graphic design system that emulates the creative workflow of human designers.<n>PSDesigner collects theme-related assets based on user instructions, and autonomously infers and executes tool calls to manipulate design files.<n>To endow the system with strong tool-use capabilities, we construct a design dataset, CreativePSD, which contains a large amount of high-quality PSD design files.
  arXiv  Detail & Related papers  (2026-03-26T17:59:51Z)
• Attention is also needed for form design [0.0]
  This research introduces a novel, attention-aware framework that integrates two systems: EURIA, an immersive Virtual Reality environment using eye-tracking, and RETina, an agentic AI pipeline.<n>The proposed framework elevates the designer's role to that of a creative director, synergizing human intuition with the generative power of agentic AI to produce higher-quality designs more efficiently.
  arXiv  Detail & Related papers  (2025-08-27T09:15:21Z)
• DesignLab: Designing Slides Through Iterative Detection and Correction [32.29179295296639]
  We propose DesignLab, which separates the design process into two roles, the design reviewer and the design contributor.<n>This decomposition enables an iterative loop where the reviewer continuously detects issues and the contributor corrects them.<n>Our experiments show that DesignLab outperforms existing design-generation methods, including a commercial tool.
  arXiv  Detail & Related papers  (2025-07-23T04:49:48Z)
• Rethinking Layered Graphic Design Generation with a Top-Down Approach [76.33538798060326]
  Graphic design is crucial for conveying ideas and messages. Designers usually organize their work into objects, backgrounds, and vectorized text layers to simplify editing.<n>With the rise of GenAI methods, an endless supply of high-quality graphic designs in pixel format has become more accessible.<n>Despite this, non-layered designs still inspire human designers, influencing their choices in layouts and text styles, ultimately guiding the creation of layered designs.<n>Motivated by this observation, we propose Accordion, a graphic design generation framework taking the first attempt to convert AI-generated designs into editable layered designs.
  arXiv  Detail & Related papers  (2025-07-08T02:26:08Z)
• From Fragment to One Piece: A Survey on AI-Driven Graphic Design [19.042522345775193]
  The survey covers various subtasks, including visual element perception and generation, aesthetic and semantic understanding, layout analysis, and generation.<n>Despite significant progress, challenges remain to understanding human intent, ensuring interpretability, and maintaining control over multilayered compositions.
  arXiv  Detail & Related papers  (2025-03-24T13:05:09Z)
• From Elements to Design: A Layered Approach for Automatic Graphic Design Composition [16.262338090888342]
  We introduce the layered design principle into Large Multimodal Models (LMMs)<n>LaDeCo performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents.<n>It subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context.
  arXiv  Detail & Related papers  (2024-12-27T16:13:08Z)
• GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts [53.568057283934714]
  We propose a Vision-Language Model (VLM)-based framework that generates content-aware text logo layouts.<n>We introduce two model techniques that reduce the computational cost for processing multiple glyph images simultaneously.<n>To support instruction tuning of our model, we construct two extensive text logo datasets that are five times larger than existing public datasets.
  arXiv  Detail & Related papers  (2024-11-18T10:04:10Z)
• MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis [65.78359025027457]
  MetaDesigner introduces a transformative framework for artistic typography, powered by Large Language Models (LLMs)<n>Its foundation is a multi-agent system comprising the Pipeline, Glyph, and Texture agents, which collectively orchestrate the creation of customizable WordArt.
  arXiv  Detail & Related papers  (2024-06-28T11:58:26Z)
• Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Models [81.6240188672294]
  In graphic design, non-professional users often struggle to create visually appealing layouts due to limited skills and resources. We introduce a novel multimodal instruction-following framework for layout planning, allowing users to easily arrange visual elements into tailored layouts. Our method not only simplifies the design process for non-professionals but also surpasses the performance of few-shot GPT-4V models, with mIoU higher by 12% on Crello.
  arXiv  Detail & Related papers  (2024-04-23T17:58:33Z)
• I-Design: Personalized LLM Interior Designer [57.00412237555167]
  I-Design is a personalized interior designer that allows users to generate and visualize their design goals through natural language communication. I-Design starts with a team of large language model agents that engage in dialogues and logical reasoning with one another. The final design is then constructed in 3D by retrieving and integrating assets from an existing object database.
  arXiv  Detail & Related papers  (2024-04-03T16:17:53Z)
• COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design [39.809852329070466]
  This paper introduces the COLE system - a hierarchical generation framework designed to address these challenges. This COLE system can transform a vague intention prompt into a high-quality multi-layered graphic design, while also supporting flexible editing based on user input.
  arXiv  Detail & Related papers  (2023-11-28T17:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.