用简单方法实现高保真商品海报生成，无需复杂模块
simpleposter: A simple baseline for product poster generation
- 全参数微调基础模型抑制主体延伸，替代复杂控制模块
- 零成本字符级位置编码实现精准多行文本布局
- 适合需要快速部署的电商海报生成场景
商品海报生成面临超越通用海报设计的独特挑战，需在保持商品外观真实性的前提下精确控制密集多行文本布局。现有方法通常采用引入ControlNet和OCR编码器等辅助模块的图像修复框架，但这类方法增加架构复杂度与计算开销，仍存在文本错误和主体延伸问题。本文提出SimplePoster，一种基于图像修复的简洁有效框架，在不依赖外部控制器的前提下，实现了主体高保真保留与可定位的文本精准渲染。核心思路基于两点观察：(1) 对基础模型进行全参数微调能有效抑制主体延伸，性能优于基于ControlNet的方案；(2) 采用零成本的字符级位置编码，实现无需专用布局模块的几何感知文本生成。实验表明，SimplePoster在主体保留率上达到98.7%，显著高于SeedEdit 3.0的55.2%和PosterMaker的85.3%，同时提升文本渲染准确性。代码、模型、基准数据及部分训练数据将开源于https://github.com/Alibaba-YuFeng/SIMPLEPOSTER。
原文摘要 · Abstract (English)
Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-line text layouts. Prior methods typically adopt inpainting frameworks augmented with auxiliary modules such as ControlNet and OCR encoders. However, these approaches introduce architectural complexity and computational overhead while still suffering from text errors and subject extension artifacts. We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers. Our approach builds on two observations: (1) full-parameter fine-tuning of the base model effectively suppresses subject extension, outperforming ControlNet-based alternatives; and (2) a zero-cost character-level position encoding enables geometry-aware text generation without dedicated layout modules. Experiments show that SimplePoster achieves a $98.7\%$ subject preservation rate, compared to $55.2\%$ for SeedEdit 3.0 and $85.3\%$ for PosterMaker, while also improving text rendering accuracy. Code, models, benchmark and a part of training data will be available at https://github.com/Alibaba-YuFeng/SIMPLEPOSTER
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。