PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable Typography

TL;DR

PosterVerse delivers a full-end-to-end, prompt-driven poster generation pipeline with HTML-based scalable typography, addressing the lack of editable, commercial-grade outputs in prior work. It comprises DIPR-based blueprint creation, LoRA-augmented graphical background generation across four styles, and an MLLM-powered unified layout-text rendering that outputs editable HTML with guaranteed text fidelity. The PosterDNA dataset provides 167k structurally annotated, HTML-enabled samples for training and validation, paving the way for modular and scalable poster design models. Experimental results show PosterVerse achieves superior text accuracy, layout fidelity, and visual appeal compared with existing approaches, while enabling edits and multilingual typography via HTML rendering. This framework has strong practical potential for automating commercial-grade poster creation in marketing and creative industries.

Abstract

Commercial-grade poster design demands the seamless integration of aesthetic appeal with precise, informative content delivery. Current automated poster generation systems face significant limitations, including incomplete design workflows, poor text rendering accuracy, and insufficient flexibility for commercial applications. To address these challenges, we propose PosterVerse, a full-workflow, commercial-grade poster generation method that seamlessly automates the entire design process while delivering high-density and scalable text rendering. PosterVerse replicates professional design through three key stages: (1) blueprint creation using fine-tuned LLMs to extract key design elements from user requirements, (2) graphical background generation via customized diffusion models to create visually appealing imagery, and (3) unified layout-text rendering with an MLLM-powered HTML engine to guarantee high text accuracy and flexible customization. In addition, we introduce PosterDNA, a commercial-grade, HTML-based dataset tailored for training and validating poster design models. To the best of our knowledge, PosterDNA is the first Chinese poster generation dataset to introduce HTML typography files, enabling scalable text rendering and fundamentally solving the challenges of rendering small and high-density text. Experimental results demonstrate that PosterVerse consistently produces commercial-grade posters with appealing visuals, accurate text alignment, and customizable layouts, making it a promising solution for automating commercial poster design. The code and model are available at https://github.com/wuhaer/PosterVerse.

Figures (15)

• Figure 1: Comparison between existing poster generation methods (top) and the proposed PosterVerse (bottom).
• Figure 2: The overview of PosterVerse: A full-workflow method integrating blueprint creation, graphical background generation, and unified layout-text rendering to produce commercial-grade, aesthetically appealing, and text-rich posters.
• Figure 3: Overview of the three core components in the PosterDNA dataset generation pipeline.
• Figure 4: Visual comparison of PosterVerse with state-of-the-art models. The inputs for all methods are aligned with user requirements at the detailed level on the testing set.
• Figure 5: Radar chart of the user study in four dimensions.