ChordEdit: One-Step Low-Energy Transport for Image Editing
This addresses the challenge of enabling fast, precise image editing for users of one-step text-to-image models, though it appears incremental as it builds on existing transport theory for a specific bottleneck.
The paper tackled the problem of severe object distortion and loss of consistency in one-step text-guided image editing with existing methods, and introduced ChordEdit, a model-agnostic, training-free approach that recasts editing as a transport problem using dynamic optimal transport theory, achieving high-fidelity real-time editing.
The advent of one-step text-to-image (T2I) models offers unprecedented synthesis speed. However, their application to text-guided image editing remains severely hampered, as forcing existing training-free editors into a single inference step fails. This failure manifests as severe object distortion and a critical loss of consistency in non-edited regions, resulting from the high-energy, erratic trajectories produced by naive vector arithmetic on the models' structured fields. To address this problem, we introduce ChordEdit, a model agnostic, training-free, and inversion-free method that facilitates high-fidelity one-step editing. We recast editing as a transport problem between the source and target distributions defined by the source and target text prompts. Leveraging dynamic optimal transport theory, we derive a principled, low-energy control strategy. This strategy yields a smoothed, variance-reduced editing field that is inherently stable, facilitating the field to be traversed in a single, large integration step. A theoretically grounded and experimentally validated approach allows ChordEdit to deliver fast, lightweight and precise edits, finally achieving true real-time editing on these challenging models.