PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow

2026-03-26

AI Summary

Existing automated design systems struggle to accurately interpret user intent and generate editable, high-quality design files, often oversimplifying professional workflows at the expense of flexibility and intuitiveness. This work proposes a novel automation approach that emulates the creative process of human designers by leveraging a multimodal large language model to jointly understand natural language instructions, retrieve thematically relevant assets, and autonomously invoke professional design tools to manipulate PSD files. To enable this capability, we introduce CreativePSD—the first large-scale, high-quality dataset of PSD files annotated with detailed operation trajectories—and use it to train models capable of performing complex design tasks such as asset integration and element refinement. Experiments demonstrate that our method significantly outperforms existing approaches across diverse graphic design tasks, empowering non-experts to efficiently produce editable, production-ready designs of high quality.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system that can faithfully translate user intentions into editable design files remains an open challenge. Although recent studies have leveraged powerful text-to-image models and MLLMs to assist graphic design, they typically simplify professional workflows, resulting in limited flexibility and intuitiveness. To address these limitations, we propose PSDesigner, an automated graphic design system that emulates the creative workflow of human designers. Building upon multiple specialized components, PSDesigner collects theme-related assets based on user instructions, and autonomously infers and executes tool calls to manipulate design files, such as integrating new assets or refining inferior elements. 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 annotated with operation traces across a wide range of design scenarios and artistic styles, enabling models to learn expert design procedures. Extensive experiments demonstrate that PSDesigner outperforms existing methods across diverse graphic design tasks, empowering non-specialists to conveniently create production-quality designs.

Problem

• automated graphic design
• user intention translation
• editable design files
• creative workflow
• design flexibility

Innovation

• automated graphic design
• human-like creative workflow
• tool-use learning
• CreativePSD dataset
• design automation