DecFlowEdit is proposed, which decouples the optimal guidance scales for localization and for editing in flow-based generative models and first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG.
Abstract
Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit's default classifier-free guidance (CFG) configuration, with asymmetric source and target scales, causes substantial background leakage. Matching these guidance scales, for example by removing CFG, improves edit-relevant localization but severely degrades editability. To get the best of both worlds, we propose DecFlowEdit, which decouples the optimal guidance scales for localization and for editing in flow-based generative models. In particular, DecFlowEdit first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG. Our method remains training-free and inversion-free, requiring neither external spatial masks nor attention manipulation. Experiments on PIE-Bench across FLUX, SD3, and SD3.5 show that DecFlowEdit improves background preservation, reducing structure distance by approximately 61 to 73 percent and background LPIPS by 68 to 80 percent relative to FlowEdit at comparable editing fidelity.
Text-guided image editing with diffusion models struggles with spatial edits (e.g. manipulating objects, changing viewpoints, manipulating occlusions) that depend on the 3D structure understanding of a scene. Marigold and follow-up work demonstrate that a pretrained diffusion backbone already harbors strong geometric p...
Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large pretrained model. We study this tension in a 5.01B-parameter text-to-video diffusion transformer. ACROSSVAM2.0 combines a confidence-weighted track...
Attention-Scoped Guidance (ASG), a sampler wrapper that reads a soft support map from the instruction attention that the editor already computes, then weakens text guidance where support is low and strengthens image anchoring where support is high.
Zeyan Li, Wei Zhou, Hadi Amirpour et al.· 1 citation
IAB edited achieves state-of-the-art instruction adherence performance on RealEdit and EMU Edit benchmarks based on embedding-based metrics and shows that gradient-aligned VLM distillation holds up under real-world-like surveillance and occlusion conditions.
Chiranjeev Chiranjeev, Muskan Dosi, M. Vatsa et al.· European Conference on Compu...· 0 citations
Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this be...
We propose MorphSIG, a training-free framework that reformulates subject-driven image generation (SIG) as pseudo-video feature transport. MorphSIG contains two core modules: Progressive Decoupled Anchoring, which uses frequency-domain decoupling and structural scrambling during early denoising to break structural locki...
Hai-Long Yan, Yong-Rui Zhang, Xiang-Tao Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.