Editing the content of an image with a pretrained text-to-image model remains challenging. Existing methods often distort fine details or introduce unintended artifacts. We propose using \emph{coupled stochastic differential equations} (coupled SDEs) to guide the sampling process of any pre-trained generative model that can be sampled by solving an SDE, including diffusion and rectified flow models. By driving both the source image and the edited image with the same correlated noise, our approach steers new samples toward the desired semantics while preserving visual similarity to the source. The method works out-of-the-box, without retraining or auxiliary networks, and achieves high prompt fidelity along with near-pixel-level consistency. These results position coupled SDEs as a simple yet powerful tool for controlled generative AI. Project page: https://z-jianxin.github.io/syncSDE-release/. Code: https://github.com/Z-Jianxin/syncSDE-release.

翻译：利用预训练的文本到图像模型编辑图像内容仍具挑战性。现有方法常会扭曲精细细节或引入非预期伪影。我们提出使用耦合随机微分方程（coupled SDEs）引导任意可通过求解SDE进行采样的预训练生成模型（包括扩散模型和矫正流模型）的采样过程。通过使用相同的相关噪声驱动源图像与编辑图像，该方法在保持与源图像视觉相似性的同时，将新样本导向目标语义。本方法无需重新训练或辅助网络即可开箱即用，在实现近像素级一致性的同时保持高提示忠实度。这些结果表明耦合SDEs可作为可控生成式AI的简洁而强大的工具。项目页面：https://z-jianxin.github.io/syncSDE-release/。代码：https://github.com/Z-Jianxin/syncSDE-release。