OrionEdit：连接参考图像与源图像以实现泛化的跨图像编辑
OrionEdit: Bridging Reference and Source Images for Generalized Cross-Image Editing
把「参考图→源图」的跨图像编辑形式化为可控生成任务，并用对称正交子空间解耦加反向因果注意力掩码约束潜变量单向依赖，这套解耦与信息流掩码思路可直接迁移到多条件控制、个性化生成与风格迁移中，用来抑制参考信息泄漏到不该改的区域。
原文依据 regulates editing via symmetric orthogonal subspace disentanglement and reverse-causal attention with information-flow masks enforcing unidirectional latent dependencies
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态图像合成已取得显著进展，但大多数编辑方法仍依赖文本指令，其直观性不如视觉引导。近期出现了一种新范式，即用另一张图像作为参考来编辑一张图像，从而通过视觉示例实现更直观的操控。我们将这一设定形式化为跨图像编辑，即在单张或多张视觉参考的引导下修改源图像。我们提出 OrionEdit，一个统一框架，通过对称正交子空间解耦以及带信息流掩码的反向因果注意力来调控编辑过程，后者强制潜变量之间保持单向依赖。OrionEdit 构建于标准扩散骨干之上，支持零样本多参考编辑，性能优于开源基线，在保真度与解耦性上接近专有模型。模型已发布于 https://github.com/cityuhkai/OrionEdit。
英文原文摘要 892 字符
Multimodal image synthesis has made significant progress, yet most editing methods still rely on textual instructions, which are less direct than visual guidance. Recently, a new paradigm edits one image using another as reference, enabling more intuitive manipulation through visual exemplars. We formalize this setting as cross-image editing, where a source image is modified under one or more visual references. We propose OrionEdit, a unified framework that regulates editing via symmetric orthogonal subspace disentanglement and reverse-causal attention with information-flow masks enforcing unidirectional latent dependencies. Built on standard diffusion backbones, OrionEdit enables zero-shot multi-reference editing and outperforms open-source baselines, approaching proprietary models in fidelity and disentanglement. The model is available at https://github.com/cityuhkai/OrionEdit.