FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editing

ICLR 2026 Conference Submission4104 Authors

Keywords: Zero-order optimization, Image inversion, Image editing, Flow Matching, Diffusion models

TL;DR: A new zero-order optimization method through the whole flow processes for zero-shot image inversion and image editing

Abstract:

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. In this work we introduce FlowOpt - a zero-order (gradient-free) optimization framework that treats the entire diffusion/flow process as a black box, enabling optimization through the whole process 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 the effectiveness of FlowOpt in the context of image editing, showcasing two use cases: (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 the target text prompt.
In both settings, our method achieves state-of-the-art results while using roughly the same number of neural function evaluations (NFEs) as existing methods.

Primary Area: generative models

Submission Number: 4104