PosterOmni：通过任务蒸馏与统一奖励反馈实现泛化艺术海报创作
PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback
把局部编辑（ID 驱动、缩放、填充、外扩）与全局创作（布局/风格驱动）统一进一个基础编辑模型，并用「数据蒸馏 + 统一奖励反馈」的流水线做多任务对齐，这套任务蒸馏与奖励联合对齐的做法可直接迁移到其他多任务可控生成场景。
原文依据 distilling knowledge between local and global experts for supervised fine-tuning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像到海报生成是一项高需求任务，不仅需要局部调整，还需要高层次的设计理解。模型必须在生成文字、布局、风格与视觉元素的同时，保持语义保真度与美学一致性。该过程横跨两种范式：局部编辑，其中 ID 驱动生成、缩放、填充与外扩必须保留具体的视觉实体；以及全局创作，其中布局驱动与风格驱动任务依赖于对抽象设计概念的理解。这些交织的需求使图像到海报生成成为一个多维过程，在图像提示控制下将实体保持型编辑与概念驱动型创作耦合在一起。为应对这些挑战，我们提出 PosterOmni，一个泛化艺术海报创作框架，它释放了基础编辑模型在多任务图像到海报生成上的潜力。PosterOmni 通过一条高效的数据—蒸馏—奖励流水线，将局部编辑与全局创作这两种范式整合进单一系统：(i) 构建覆盖基于实体与基于概念创作的六类任务的多场景图像到海报数据集；(ii) 在局部专家与全局专家之间进行知识蒸馏以完成监督微调；(iii) 应用统一的 PosterOmni 奖励反馈，在所有任务上联合对齐视觉实体保持与美学偏好。此外，我们建立了 PosterOmni-Bench，一个用于评估局部编辑与全局创作的统一基准。大量实验表明，PosterOmni 显著提升了参考遵循度、全局构图质量与美学和谐度，优于所有开源基线，甚至超越若干专有系统。
英文原文摘要 1724 字符
Image-to-poster generation is a high-demand task requiring not only local adjustments but also high-level design understanding. Models must generate text, layout, style, and visual elements while preserving semantic fidelity and aesthetic coherence. The process spans two regimes: local editing, where ID-driven generation, rescaling, filling, and extending must preserve concrete visual entities; and global creation, where layout- and style-driven tasks rely on understanding abstract design concepts. These intertwined demands make image-to-poster a multi-dimensional process coupling entity-preserving editing with concept-driven creation under image-prompt control. To address these challenges, we propose PosterOmni, a generalized artistic poster creation framework that unlocks the potential of a base edit model for multi-task image-to-poster generation. PosterOmni integrates the two regimes, namely local editing and global creation, within a single system through an efficient data-distillation-reward pipeline: (i) constructing multi-scenario image-to-poster datasets covering six task types across entity-based and concept-based creation; (ii) distilling knowledge between local and global experts for supervised fine-tuning; and (iii) applying unified PosterOmni Reward Feedback to jointly align visual entity-preserving and aesthetic preference across all tasks. Additionally, we establish PosterOmni-Bench, a unified benchmark for evaluating both local editing and global creation. Extensive experiments show that PosterOmni significantly enhances reference adherence, global composition quality, and aesthetic harmony, outperforming all open-source baselines and even surpassing several proprietary systems.