让单步图像编辑更稳定，避免变形和失真。
ChordEdit: One-Step Low-Energy Transport for Image Editing
- 将编辑视为源与目标分布间的低能耗传输问题。
- 单步即可完成编辑，非编辑区域保持高度一致。
- 无需训练、无需反演，适合快速部署的图像编辑场景。
单步文本到图像（T2I）模型实现了前所未有的生成速度，但其在文本引导图像编辑中的应用仍受严重制约，因将现有无训练编辑器强制应用于单次推理会导致物体严重失真及未编辑区域的一致性显著下降，根源在于对模型结构化空间中朴素向量算术产生的高能量、不规则轨迹。为此，我们提出ChordEdit，一种模型无关、无训练、无反演的单步编辑方法，将编辑重构为由源和目标文本提示定义的源与目标分布之间的传输问题。基于动态最优传输理论，推导出一种原则性低能量控制策略，生成平滑且方差降低的编辑场，天然稳定，可一次性大步积分完成路径遍历。该方法理论基础扎实，实验验证有效，实现快速、轻量、精准的编辑，最终在这些复杂模型上达成真正的实时编辑。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。