PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 70 of its 76 references that are in the map. First posted on arXiv 26 Mar 2026.
Builds on
70 of 76 references.
References · 70
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
- 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
- 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
- 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
- 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
- 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
- 2023TextDiffuser: Diffusion Models as Text Painterscited by 229
- 2023AnyText: Multilingual Visual Text Generation And Editingcited by 170
38 more
- 2025Seedream 3.0 Technical Reportcited by 154
- 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 143
- 2023TextDiffuser-2: Unleashing the Power of Language Models for Text Renderingcited by 140
- 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 131
- 2023GlyphControl: Glyph Conditional Control for Visual Text Generationcited by 131
- 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 123
- 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
- 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 95
- 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
- 2024Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Renderingcited by 81
- 2021BLT: Bidirectional Layout Transformer for Controllable Layout Generationcited by 69
- 2023PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layoutcited by 61
- 2022Composition-aware Graphic Layout GAN for Visual-textual Presentation Designscited by 59
- 2024AnyText2: Visual Text Generation and Editing With Customizable Attributescited by 53
- 2024A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Modelscited by 52
- 2023LayoutPrompter: Awaken the Design Ability of Large Language Modelscited by 48
- 2024Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Renderingcited by 48
- 2025PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Renderingcited by 46
- 2023COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Designcited by 43
- 2023Unifying Layout Generation with a Decoupled Diffusion Modelcited by 41
- 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Modelscited by 41
- 2023AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generationcited by 41
- 2024PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLMcited by 41
- 2024Graphic Design with Large Multimodal Modelcited by 40
- 2025DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Modelscited by 40
- 2025PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Frameworkcited by 40
- 2023Relation-Aware Diffusion Model for Controllable Poster Layout Generationcited by 37
- 2024OpenCOLE: Towards Reproducible Automatic Graphic Design Generationcited by 37
- 2025POSTA: A Go-to Framework for Customized Artistic Poster Generationcited by 36
- 2025CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Designcited by 36
- 2023Retrieval-Augmented Layout Transformer for Content-Aware Layout Generationcited by 35
- 2024PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generationcited by 35
- 2023GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generationcited by 34
- 2022Geometry Aligned Variational Transformer for Image-conditioned Layout Generationcited by 33
- 2023Towards Flexible Multi-modal Document Modelscited by 31
- 2024GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Modelscited by 29
- 2024Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraintscited by 26
- 2024LayoutFlow: Flow Matching for Layout Generationcited by 21
50 most cited of 70 All 70 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks
- 2025GraphicBench: A Planning Benchmark for Graphic Design with Language Agents
- 2025PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs
- 2026FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows
- 2026Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
- 2025UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images
- 2026PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation
- 2025SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches