ChordEdit：面向图像编辑的单步低能量传输
ChordEdit: One-Step Low-Energy Transport for Image Editing
把文本引导编辑重构成源/目标提示分布之间的动态最优传输问题，得到低能量、方差缩减的平滑编辑场，使单步大积分即可完成编辑；对做单步 T2I 模型（如单步扩散/流匹配）上做免训练编辑的人，这是一个可直接复用的控制场构造思路。
原文依据 We recast editing as a transport problem between the source and target distributions defined by the source and target text prompts.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单步文本到图像（T2I）模型的出现带来了前所未有的合成速度。然而，将其应用于文本引导的图像编辑仍严重受阻，因为把现有免训练编辑器强行压缩到单步推理会失败。这种失败表现为严重的物体畸变以及非编辑区域一致性的关键性丧失，其根源在于对模型结构化场做朴素向量算术所产生的高能量、不规则的轨迹。为解决该问题，我们提出 ChordEdit，一种与模型无关、免训练且免反演的方法，可实现高保真单步编辑。我们将编辑重新表述为由源文本提示与目标文本提示所定义的源分布与目标分布之间的传输问题。借助动态最优传输理论，我们推导出一种有原则的低能量控制策略。该策略产生一个平滑、方差缩减的编辑场，其本身具有内在稳定性，使得该场可通过单个大积分步完成穿越。一种有理论依据并经实验验证的方法使 ChordEdit 能够提供快速、轻量且精确的编辑，最终在这些具有挑战性的模型上实现真正的实时编辑。
英文原文摘要 1232 字符
The advent of one-step text-to-image (T2I) models offers unprecedented synthesis speed. However, their application to text-guided image editing remains severely hampered, as forcing existing training-free editors into a single inference step fails. This failure manifests as severe object distortion and a critical loss of consistency in non-edited regions, resulting from the high-energy, erratic trajectories produced by naive vector arithmetic on the models' structured fields. To address this problem, we introduce ChordEdit, a model agnostic, training-free, and inversion-free method that facilitates high-fidelity one-step editing. We recast editing as a transport problem between the source and target distributions defined by the source and target text prompts. Leveraging dynamic optimal transport theory, we derive a principled, low-energy control strategy. This strategy yields a smoothed, variance-reduced editing field that is inherently stable, facilitating the field to be traversed in a single, large integration step. A theoretically grounded and experimentally validated approach allows ChordEdit to deliver fast, lightweight and precise edits, finally achieving true real-time editing on these challenging models.