统一框架生成高审美海报，突破传统模块化设计限制
PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
- 采用级联式流程，端到端优化文本渲染与布局协调
- 在HQ-Poster100K上实现接近商用顶尖系统的视觉质量
- 支持自由构图，适合需要高质量海报生成的创意应用
生成高审美海报比普通设计图像更具挑战性，需兼顾精准文本呈现、抽象艺术内容融合、醒目排版与整体风格和谐。为此，我们提出PosterCraft，一个摒弃传统模块化流水线和固定布局的统一框架，使模型可自由探索连贯且具视觉冲击力的组合。该框架包含四个阶段：(i) 在新构建的Text-Render-2M数据集上进行大规模文本渲染优化；(ii) 在HQ-Poster100K数据集上进行区域感知的监督微调；(iii) 通过最佳n选一偏好优化实现美学-文本强化学习；(iv) 联合视觉-语言反馈精炼。每个阶段均配备自动化数据构建管道，无需复杂结构改动即可实现稳健训练。多组实验表明，PosterCraft在文本渲染准确率、布局连贯性与整体视觉吸引力方面显著优于开源基线，逼近当前最先进商业系统水平。代码、模型与数据集详见项目主页：https://ephemeral182.github.io/PosterCraft
原文摘要 · Abstract (English)
Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To address this, we propose PosterCraft, a unified framework that abandons prior modular pipelines and rigid, predefined layouts, allowing the model to freely explore coherent, visually compelling compositions. PosterCraft employs a carefully designed, cascaded workflow to optimize the generation of high-aesthetic posters: (i) large-scale text-rendering optimization on our newly introduced Text-Render-2M dataset; (ii) region-aware supervised fine-tuning on HQ-Poster100K; (iii) aesthetic-text-reinforcement learning via best-of-n preference optimization; and (iv) joint vision-language feedback refinement. Each stage is supported by a fully automated data-construction pipeline tailored to its specific needs, enabling robust training without complex architectural modifications. Evaluated on multiple experiments, PosterCraft significantly outperforms open-source baselines in rendering accuracy, layout coherence, and overall visual appeal-approaching the quality of SOTA commercial systems. Our code, models, and datasets can be found in the Project page: https://ephemeral182.github.io/PosterCraft
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。