Search papers, labs, and topics across Lattice.
This paper introduces a frequency-aware semantic compensation strategy for inversion-free image editing, addressing limitations in existing frameworks like FlowEdit that struggle with global modifications under certain conditions. By enhancing the effective signal during the early stages of image generation, the method ensures that substantial semantic changes can be achieved while preserving background structures. The results demonstrate improved global editing capacity without compromising the fidelity of the background, marking a significant advancement in text-guided image editing techniques.
Early-stage signal enhancement can unlock powerful global modifications in image editing while keeping backgrounds intact.
Text-guided image editing aims to modify visual content according to a target prompt while preserving the background. Recent inversion-free image editing frameworks such as FlowEdit have demonstrated strong editing capability without requiring inversion. Empirically, FlowEdit can achieve substantial semantic changes under appropriate hyperparameter settings. However, we observe that under certain global attribute shifts, the editing trajectory may not effectively move away from the source distribution in the early timesteps. Our analysis suggests that in the high-noise regime, the dominant manifold-seeking flow toward the data manifold can reduce the influence of the text-conditioned direction, leading to limited global modification while background structures remain only moderately preserved. Inspired by this observation, we propose an inversion-free, frequency-aware semantic compensation strategy that strengthens the effective signal in the early stage of generation, while maintaining structural consistency in the background. The proposed method improves global editing capacity without sacrificing background fidelity.
