FlowOpt：通过全流程快速优化实现免训练编辑
FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editing
AI总结：
FlowOpt提出零阶优化框架，将扩散模型全流程视为黑盒，无需反向传播即可实现免训练图像编辑，支持反演和文本引导编辑，保证收敛且NFE次数与现有方法相当。
摘要：
扩散模型和流匹配模型的显著成功，激发了大量在测试时对其进行适配以完成受控生成任务的研究工作。这些任务涵盖从图像编辑到图像恢复、压缩和个性化等各个方面。然而，由于这些模型在采样过程中的迭代特性，直接使用基于梯度的优化来控制在过程结束时生成的图像在计算上是不切实际的。因此，现有方法通常采取对每个时间步分别进行操控的策略。在此，我们引入了FlowOpt——一种零阶（无梯度）优化框架，它将整个流程视为一个黑盒，从而无需通过模型进行反向传播即可实现对整个采样过程的优化。我们的方法不仅高效，而且允许用户监控中间优化结果，并在需要时提前停止。我们证明了FlowOpt步长的一个充分条件，在该条件下可保证收敛到全局最优。我们还展示了如何通过经验估计这一上界，以选择合适的步长。我们演示了FlowOpt在图像编辑中的应用，展示了两种选项：（i）反演（确定生成给定图像的初始噪声），以及（ii）直接引导编辑后的图像与源图像相似，同时符合目标文本提示。在两种情况下，FlowOpt均取得了最先进的结果，同时使用的神经函数评估（NFE）次数与现有方法大致相同。代码和示例可在项目网页上获取。
英文摘要：
The remarkable success of diffusion and flow-matching models has ignited a surge of works on adapting them at test time for controlled generation tasks. Examples range from image editing to restoration, compression and personalization. However, due to the iterative nature of the sampling process in those models, it is computationally impractical to use gradient-based optimization to directly control the image generated at the end of the process. As a result, existing methods typically resort to manipulating each timestep separately. Here we introduce FlowOpt - a zero-order (gradient-free) optimization framework that treats the entire flow process as a black box, enabling optimization through the whole sampling path without backpropagation through the model. Our method is both highly efficient and allows users to monitor the intermediate optimization results and perform early stopping if desired. We prove a sufficient condition on FlowOpt's step-size, under which convergence to the global optimum is guaranteed. We further show how to empirically estimate this upper bound so as to choose an appropriate step-size. We demonstrate how FlowOpt can be used for image editing, showcasing two options: (i) inversion (determining the initial noise that generates a given image), and (ii) directly steering the edited image to be similar to the source image while conforming to a target text prompt. In both cases, FlowOpt achieves state-of-the-art results while using roughly the same number of neural function evaluations (NFEs) as existing methods. Code and examples are available on the project's webpage.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
