Research map / Image generation / Text-to-image diffusion
PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable Typography
Junle Liu, Peirong Zhang, Yuyi Zhang, Pengyu Yan, Hui Zhou, Xinyue Zhou, Fengjun Guo, Lianwen Jin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add hierarchical dynamic prompt sampling (basic, medium, detailed) in background training (ablation) | Flux.1-dev LoRA · Background generation | FID: 136.72 -> 62.54 | Improved |
| add hierarchical dynamic prompt sampling in background training (ablation) | Flux.1-dev LoRA · Background generation | IS: 62.39 -> 77.85 | Improved |
| add DIPR fine-tuned blueprint model, basic requirement input (ablation) | PosterVerse vs Seedream3.0 · User study | average score: 4.92 -> 6.76 | Improved |
| add DIPR fine-tuned blueprint model, basic requirement input (ablation) | PosterVerse vs GPT-4o · User study | average score: 4.52 -> 6.76 | Improved |
| use detailed instead of basic requirement input | Seedream3.0 · User study | average score: 4.92 -> 6.12 | Improved |
| use detailed instead of basic requirement input | PosterVerse · User study | average score: 6.76 -> 6.85 | No clear effect |
| use PosterVerse instead of GPT-4o | full poster pipeline · PosterDNA test set | Correct Rate (CR): 49.73% -> 92.33% | Improved |
| use PosterVerse instead of GPT-4o | full poster pipeline · PosterDNA test set | F1: 48.49% -> 78.58% | Improved |
| use PosterVerse HTML layout rendering instead of GPT-4o static image output | full poster pipeline · PosterDNA test set | Overlap: 0.0106 -> 0.0027 | Improved |
| use PosterVerse instead of Seedream3.0 | full poster pipeline · PosterDNA test set | GPT-4o evaluation average: 7.82 -> 8.02 | Improved |
| use fine-tuned Qwen2.5-14B blueprint model instead of Claude 3.7 Sonnet | blueprint creation · Blueprint stage | Edit Distance: 22.32 -> 12.00 | Improved |
| use LoRA-tuned Flux.1 with hierarchical prompts instead of Flux.1 dev | background generation · Background stage | FID: 40.65 -> 26.8 | Improved |
Closest papers by meaning
- P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark (ICLR 2026 · similarity 0.89)
- POSTA: A Go-to Framework for Customized Artistic Poster Generation (CVPR 2025 · similarity 0.89)
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025 · similarity 0.88)
- PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering (CVPR 2025 · similarity 0.88)
- Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers (NeurIPS 2025 · similarity 0.87)
- PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
