SimplePoster：产品海报生成的简单基线
SIMPLEPOSTER: A SIMPLE BASELINE FOR PRODUCT POSTER GENERATION
提出一种极简的图像修复框架，通过全参数微调和字符级位置编码实现主体保持与位置可控的文本渲染，无需 ControlNet 等外部控制器，为可控生成提供了轻量级替代方案。
原文依据 minimalist yet powerful inpainting-based framework that enables faithful subject preservation and position-controllable text rendering--entirely without external controllers like ControlNet
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论产品海报生成提出了超越通用设计的独特挑战：它不仅要求美观的构图和准确的文本渲染，还需要严格保持产品主体，并对密集的多行文本布局进行精确控制。通用图像编辑模型难以处理文本布局控制和主体一致性，而现有的专门方法——通常基于图像修复框架——仍然存在无意识的主体扩展和文本合成不准确的问题。一种常见的解决方案是集成 ControlNet 等辅助模块，以主体结构和文本布局为条件，但这些方法引入了显著的架构复杂性和训练开销。在本工作中，我们质疑这种复杂性的必要性，并证明极简的适配已足够。我们提出 SimplePoster，一个极简而强大的基于图像修复的框架，能够实现忠实的主体保持和位置可控的文本渲染——完全无需 ControlNet 等外部控制器。SimplePoster 基于两个关键见解：(1) 仅全参数微调即可通过将模型内部表示与领域特定先验对齐，有效抑制主体扩展；(2) 轻量级的字符级位置编码策略能够实现端到端的、空间接地的文本生成。实验表明，SimplePoster 实现了近乎完美的主体保持（98.7% 的案例严格保持主体），显著优于最优编辑模型 SeedEdit3.0（55.2%）和专门方法 PosterMaker（85.3%）。它进一步展示了卓越的文本渲染准确性，即使在具有复杂多行布局的挑战性场景中也是如此。我们相信 SimplePoster 为产品海报生成建立了一个简单而强大的基线。我们质疑这种复杂性的必要性，并证明极简设计已足够。我们提出 SimplePoster，一个简单而有效的基于图像修复的框架，无需依赖 ControlNet 等外部控制器即可实现忠实的主体保持和位置可控的文本渲染。SimplePoster 基于两个关键见解：(1) 全参数微调有效抑制主体扩展；(2) 免训练的字符级位置编码策略实现端到端的、几何感知的文本生成。值得注意的是，SimplePoster 实现了近乎完美的主体保持率（98.7%），显著优于最优模型 SeedEdit 3.0（55.2%）和 PosterMaker（85.3%）。它在文本渲染准确性方面也表现出色。我们相信 SimplePoster 为产品海报生成建立了一个简单而强大的基线。代码、模型和基准将在接收后发布。
英文原文摘要 2770 字符
Product poster generation presents unique challenges beyond general-purpose de-sign: it demands not only aesthetic composition and accurate text rendering, butalso strict preservation of the product subject and precise control over dense,multi-line text layouts. While general image editing models struggle with text lay-out control and subject consistency, existing specialized approaches--often builtupon inpainting frameworks--still suffer from unintended subject extension andinaccurate text synthesis. A common solution involves integrating auxiliary mod-ules such as ControlNet to condition on subject structure and text layout, but theseapproaches introduce significant architectural complexity and training overhead.In this work, we challenge the necessity of such complexity and demonstrate thatminimalist adaptation is sufficient. We introduce SimplePoster, a minimalist yetpowerful inpainting-based framework that enables faithful subject preservationand position-controllable text rendering--entirely without external controllers likeControlNet. SimplePoster rests on two key insights: (1) full-parameter fine-tuningalone effectively suppresses subject extension by aligning the model's internalrepresentations with domain-specific priors; and (2) a lightweight character-levelposition encoding strategy enables end-to-end, spatially grounded text generation.Experiments show that SimplePoster achieves near-perfect subject preservation(98.7% of cases with strict subject preservation), significantly outperforming boththe state-of-the-art editing model SeedEdit3.0 (55.2%) and the specialized ap-proach PosterMaker (85.3%). It further demonstrates superior text rendering ac-curacy, even in challenging scenarios with complex multi-line layouts. We believeSimplePoster establishes a simple yet strong baseline for product poster genera-tion. We question the necessity of such complexity and demonstrate that minimalist designs suffice. We propose SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and position-controllable text rendering without relying on external controllers like ControlNet. SimplePoster is based on two key insights: (1) full-parameter fine-tuning effectively suppresses subject extension; and (2) a training-free character-level position encoding strategy enables end-to-end, geometry-aware text generation. Remarkably, SimplePoster achieves a near-perfect subject preservation rate (98.7%), significantly outperforming SOTA models SeedEdit 3.0 (55.2%) and PosterMaker (85.3%). It also excels in text rendering accuracy. We believe SimplePoster establishes a simple yet strong baseline for product poster generation. Code, models and benchmark will be released upon acceptance.