说茄子！通过自然语言编辑生成细节保持的人像集合
Say Cheese! Detail-Preserving Portrait Collection Generation via Natural Language Edits
提出基于自然语言指令的人像集合生成任务，并设计自适应特征融合与 ConsistencyNet 来在复杂编辑下保持身份与细节一致性，为可控人像编辑提供了可复用的数据构建流程与一致性保持模块。
原文依据 SCheese employs adaptive feature fusion mechanism to maintain identity consistency, and ConsistencyNet to inject fine-grained features for detail consistency.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着社交媒体平台的激增，用户越来越需要直观的方式来创建多样化、高质量的人像集合。在本工作中，我们引入人像集合生成（PCG），这是一个通过自然语言指令编辑参考人像图像来生成连贯人像集合的新任务。该任务对现有方法提出了两个独特挑战：（1）复杂的多属性修改，如姿态、空间布局和相机视角；（2）高保真细节保持，包括身份、服装和配饰。为应对这些挑战，我们提出 CHEESE，这是首个大规模 PCG 数据集，包含 24K 个人像集合和 573K 个样本，带有高质量的修改文本标注，通过基于大型视觉语言模型的流程并结合基于反演的验证构建而成。我们进一步提出 SCheese，一个将文本引导生成与分层身份和细节保持相结合的框架。SCheese 采用自适应特征融合机制来保持身份一致性，并使用 ConsistencyNet 注入细粒度特征以实现细节一致性。全面的实验验证了 CHEESE 在推进 PCG 方面的有效性，SCheese 在处理具有身份和细粒度细节一致性的复杂编辑方面达到了最优性能。
英文原文摘要 1358 字符
As social media platforms proliferate, users increasingly demand intuitive ways to create diverse, high-quality portrait collections. In this work, we introduce Portrait Collection Generation (PCG), a novel task that generates coherent portrait collections by editing a reference portrait image through natural language instructions. This task poses two unique challenges to existing methods: (1) complex multi-attribute modifications such as pose, spatial layout, and camera viewpoint; and (2) high-fidelity detail preservation including identity, clothing, and accessories. To address these challenges, we propose CHEESE, the first large-scale PCG dataset containing 24K portrait collections and 573K samples with high-quality modification text annotations, constructed through an Large Vison-Language Model-based pipeline with inversion-based verification. We further propose SCheese, a framework that combines text-guided generation with hierarchical identity and detail preservation. SCheese employs adaptive feature fusion mechanism to maintain identity consistency, and ConsistencyNet to inject fine-grained features for detail consistency. Comprehensive experiments validate the effectiveness of CHEESE in advancing PCG, with SCheese achieving state-of-the-art performance in handling complex edits with identity and fine-grained details consistency.