FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing

arXiv:2604.22586v1 Announce Type: new Abstract: We propose FlowAnchor, a training-free framework for stable and efficient inversion-free, flow-based video editing. Inversion-free editing methods have recently shown impressive efficiency and structure preservation in images by directly steering the sampling trajectory with an editing signal. However, extending this paradigm to videos remains challenging, often failing in multi-object scenes or with increased frame counts. We identify the root cause as the instability of the editing signal in high-dimensional video latent spaces, which arises from imprecise spatial localization and length-induced magnitude attenuation. To overcome this challenge, FlowAnchor explicitly anchors both where to edit and how strongly to edit. It introduces Spatial-aware Attention Refinement, which enforces consistent alignment between textual guidance and spatial regions, and Adaptive Magnitude Modulation, which adaptively preserves sufficient editing strength. Together, these mechanisms stabilize the editing signal and guide the flow-based evolution toward the desired target distribution. Extensive experiments demonstrate that FlowAnchor achieves more faithful, temporally coherent, and computationally efficient video editing across challenging multi-object and fast-motion scenarios. The project page is available at https://cuc-mipg.github.io/FlowAnchor.github.io/.

Related

• RewardFlow: Generate Images by Optimizing What You Reward
• Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing
• AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing
• Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
• Controllable Video Object Insertion via Multiview Priors

Source: arXiv cs.CV | 2026-04-27