ChordEdit: One-Step Low-Energy Transport for Image Editing

Liangsi Lu; Xuhang Chen; Minzhe Guo; Shichu Li; Jingchao Wang; Yang Shi

cs.CVFeb 22, 2026

ChordEdit: One-Step Low-Energy Transport for Image Editing

Authors: Liangsi Lu, Xuhang Chen, Minzhe Guo, Shichu Li, Jingchao Wang, Yang Shi

Organizations: Guangdong University of Technology · Huizhou University · Shenzhen University · Peking University

Abstract

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.

Figures & tables

Figure 2: Comparing ChordEdit (SD-Turbo) against one-step , few-step , and multi-step editing methods on PIE-bench [ 11 ] , evaluating performance on background consistency (PSNR), semantic alignment (CLIP, referring to CLIP-Edited) [ 27 ] , and Runtime. Our method facilitates real-time text-guided editing while yielding highly competitive results.

Figure 3: One-Step Simple drift editing fails. ChordEdit preserves structure. Simple drifts, a direct drift-difference from a one-step model, induce a high-energy, non-smooth vector field, yielding two disqualifying failures: ( i ) severe object distortion and ( ii ) background breakup and spurious structures. Zoomed crops (bottom) highlight the distortions in Simple drifts versus the faithful, photorealistic result of ChordEdit .

Figure 4: Comparison of editing field stability. (a) Multi-step Simple Drift : In conventional multi-step diffusion, the iterative application of the simple drift $\Delta v$ ensures a stable trajectory. (b) One-step Simple Drift : In distilled models, the naive field $\Delta v(x_{t},t)$ is high-energy and volatile. A single, large integration step (solid arrow) accumulates significant error and deviates significantly, as the erratic underlying path (dashed) confirms. (c) Editing by ChordEdit (Ours) : We derive a stable, low-energy Chord Control Field by time-averaging the observable fields $\mathbf{R}(x_{\tau},t)$ and $\mathbf{R}(x_{\tau},t-\delta)$ . This smoothed field facilitates an accurate, single-step transport (red arrow) that faithfully reaches the target $x_{\rm tar}$ .

Figure 5: 2D Toy Example of Distribution transport. Naive residual fields are high-energy and unstable under coarse discretization. ChordEdit computes a low-energy field (Eq. ( 4.5 )) that drives particles straight to the target with minimal deviation, facilitating reliable one-step transport.

Figure 6: Effect of the Proximal Refinement. The refinement step enhances the target editing semantics.

Type	Method	Consistency			CLIP Semantics		Properties		Efficiency
Type	Method	PSNR $\uparrow$	MSE ${}_{\text{10}^{3}}\downarrow$	LPIPS ${}_{\text{10}^{3}}\downarrow$	Whole $\uparrow$	Edited $\uparrow$	T-free	I-free	Step $\downarrow$	NFE $\downarrow$	Runtime(s) $\downarrow$	VRAM(MiB) $\downarrow$
Multi-step ( $\geq$ 30 steps)	DDIM + MasaCtrl [ 30 , 3 ]	21.25	8.58	106.59	24.13	21.13	✓	✗	50	100	55.20	12272
	Direct Inversion + MasaCtrl [ 11 , 3 ]	21.78	7.99	87.38	24.42	21.38	✓	✗	50	100	79.10	12272
	DDIM + PnP [ 30 , 33 ]	21.26	8.42	113.58	25.45	22.54	✓	✗	50	100	28.01	9262
	Direct Inversion + PnP [ 11 , 33 ]	21.43	8.10	106.26	25.48	22.63	✓	✗	50	100	28.03	9262
	FlowEdit (SD3) [ 14 ]	22.17	7.69	104.81	26.64	23.69	✓	✓	33	33	7.22	17140

Table 1: Quantitative comparison on PIE-bench [ 11 ] . T-free : Training-free. I-free : Inversion-free. The best/second/third results in each numeric column are highlighted with yellow / orange / blue backgrounds, respectively. A comprehensive table with extended metrics (e.g., SSIM, Structure Distance) is available in Appendix.

Figure 7: Comparison of edited results. Real images are in the first column. Prompts are noted under each row.

Figure 8: Qualitative Comparison and Energy Visualization. We compare ChordEdit (Ours) against the naive baseline ( $\delta=0$ , Naive). The naive method’s high-energy field leads to artifacts and background corruption. Our ChordEdit derives a stable, low-energy field, resulting in high-fidelity edits that preserve object identity and non-edited regions. Results shown used SwiftBrush-v2 (first column) and SD-Turbo (second and third columns). Energy plots are computed as $E=\frac{1}{S\,C}\sum_{s=1}^{S}\sum_{\text{channel}}(\hat{u}_{t_{s}})^{2}$ .

Panel of Figure 9 — Figure 9: (top) ChordEdit Stability as a function of Integration Steps. We compare ChordEdit ( $\delta=0.15$ , red) against the naive baseline ( $\delta=0$ , blue). The naive field’s energy spikes as step $S\to 1$ , confirming its unsuitability for large steps. ChordEdit’s energy remains low. Consequently, the naive method’s background consistency (PSNR) collapses, while ChordEdit maintains high PSNR. (bottom) Analysis of the Perceptual-Semantic Trade-off. Our method ( $\delta\neq 0$ , red) strictly Pareto-dominates the naive baseline ( $\delta=0$ , blue), consistently achieving superior semantic alignment for any given level of perceptual distortion.

Figure 10: Effect of the number of noise samples. This figure qualitatively confirms that increasing the number of noise samples yields negligible marginal returns.

Figure 11: Pareto dominance and Seed robustness. Left: LPIPS–CLIP Pareto fronts [ 37 ] comparing ChordEdit (solid) to the naive baseline (dashed). Shaded regions denote the envelope across seeds. Fronts for ChordEdit with

n=1\ldots 4

are nearly overlapping and dominate the naive counterparts, indicating negligible marginal returns from multi-noise. Right: histograms of CLIP-Edited and PSNR across 20 seeds for single-noise (

n{=}1

). Both distributions are tight (CLIP CoV

0.20\%

, PSNR CoV

0.07\%

), confirming that ChordEdit one noise is effectively insensitive to the random seed.

Method	Naive ( $\delta=0$ )		Ours ( $\delta=0.15$ )		NFE
Method	PSNR $\uparrow$	CLIP-Edited $\uparrow$	PSNR $\uparrow$	CLIP-Edited $\uparrow$	NFE
w/o prox	21.89	20.83	23.89	21.87	1
w/ prox	21.38	21.96	22.20	22.96	2

Table 2: Ablation of Chord transport field and refinement. Our Chord field drives consistency (PSNR), while the prox step boosts semantics (CLIP-Edited). Full metrics are in the Appendix.

T2I Method	PSNR $\uparrow$		CLIP-Edited $\uparrow$
T2I Method	Naive	Ours	Naive	Ours
InstaFlow [ 19 ]	22.05	23.05	20.19	21.39
SwiftBrush-v2 [ 5 ]	20.52	22.04	21.06	22.58
SD-Turbo [ 28 ]	21.38	22.20	21.96	22.96

Table 3: Quantitative comparison on different T2I models. Our method (Ours) consistently outperforms the naive baseline across all tested models. Full details are provided in the Appendix.

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 12: Raw hyperparameter sweep distribution for CCF analysis. We compare the naive baseline (

\delta=0

, blue) against ChordEdit (

\delta\neq 0

, red). The plots visualize the trade-off between semantic alignment (CLIP-Edited score) and three standard background preservation metrics: (left) Mean Squared Error (MSE), (center) Peak Signal-to-Noise Ratio (PSNR), and (right) Structural Similarity Index (SSIM). In all three trade-off spaces, the ChordEdit samples (red) occupy a visibly superior region (e.g., lower MSE, higher PSNR/SSIM for a given CLIP score) than the naive baseline, which exhibits a wider, less stable, and inferior performance distribution.

Figure 13: Pareto dominance of the Chord Control Field. These frontiers, derived from the data in Figure 12 , confirm the strict Pareto dominance of ChordEdit (

\delta\neq 0

, red) over the naive baseline (

\delta=0

, blue) across all three preservation metrics: (left) MSE vs. CLIP, (center) PSNR vs. CLIP, and (right) SSIM vs. CLIP. In every case, the ChordEdit frontier achieves superior semantic alignment (higher CLIP) for any given level of perceptual fidelity, and vice-versa. This empirically validates that the temporal smoothing induced by

\delta>0

is key to resolving the inferior trade-off inherent in the unstable naive approach.

Figure 14: Noise sample analysis across multiple metrics. This figure expands the analysis in the main paper by plotting the semantic-preservation trade-off (CLIP-Edited vs. MSE/PSNR/SSIM) as a function of the number of noise samples (

n

). The overlapping distributions and tight confidence bands confirm that increasing

n>1

provides negligible marginal returns. ChordEdit’s performance with

n=1

is already highly stable and robust, validating our default setting.

Figure 15: Ablation study on temporal hyperparameters and step scale. We analyze the sensitivity of ChordEdit to key parameters. (Left two panels): Impact of the main chord time

t

. Increasing

t

generally improves semantic alignment (CLIP-Edited

\uparrow

) at the cost of background preservation (LPIPS-Unedit

\downarrow

). (Right two panels): Impact of the proximal refinement time

t_{c}

. Increasing

t_{c}

robustly improves CLIP score, but also monotonically increases LPIPS distortion. This analysis confirms a clear trade-off space, allowing for the principled selection of our default parameters which balance these competing objectives.

Figure 16: Qualitative analysis of the main chord time $t$ .

Figure 17: Qualitative analysis of the proximal refinement time $t_{c}$ .

Panel of Figure 18 — Figure 18: Quantitative joint-analysis of $\delta$ and $\lambda$ . These 3D surface plots show the trade-off between semantic alignment (CLIP) and background preservation (LPIPS, MSE, SSIM, PSNR). The naive baseline ( $\delta=0$ , the front edge of each plot) is Pareto-inferior, suffering from low CLIP scores and high distortion (high LPIPS/MSE). Increasing $\delta$ (our temporal smoothing) robustly and monotonically improves all preservation metrics. Increasing $\lambda$ (step scale) robustly increases semantic strength (CLIP) at the cost of preservation. Our default parameters are chosen from this smooth, well-behaved trade-off space.

Figure 19: Qualitative analysis of the temporal window $\delta$ . We fix other parameters and vary $\delta$ . The naive baseline ( $\delta=0.00$ ) consistently fails, producing severe artifacts, distortions, and structural collapse, especially on complex semantic changes (e.g., ’tiger $\to$ cat’ or ’apple $\to$ cat’). Our Chord Control Field ( $\delta>0$ ) immediately stabilizes the edit, resolving these failures. A value of $\delta=0.15$ demonstrates a robust balance between edit stability and semantic strength, validating its choice as our default.

Figure 20: Qualitative analysis of the step scale $\lambda$ . We vary $\lambda$ while keeping other parameters fixed. $\lambda$ functions as an intuitive ’edit strength’ controller. Small values (e.g., $\lambda=0.8$ ) result in subtle, under-edited images (’mountain’). As $\lambda$ increases, the intensity of the target semantic (’volcano’) becomes progressively stronger. This provides a simple and predictable knob for users to modulate the edit’s impact.

Type	Method	Struct.	Background Preservation				CLIP Semantics		Efficiency
Type	Method	Dist. ${}_{\text{10}^{3}}\downarrow$	PSNR $\uparrow$	MSE ${}_{\text{10}^{3}}\downarrow$	SSIM ${}_{\text{10}^{2}}\uparrow$	LPIPS ${}_{\text{10}^{3}}\downarrow$	Whole $\uparrow$	Edited $\uparrow$	Runtime(s) $\downarrow$	Step $\downarrow$	NFE $\downarrow$	VRAM(MiB) $\downarrow$
Multi-step ( $\geq$ 20 steps)	DDIM + MasaCtrl	28.79	21.25	8.58	80.11	106.59	24.13	21.13	55.19	50	100	12272
	Direct Inversion + MasaCtrl	24.46	21.78	7.99	81.74	87.38	24.42	21.38	79.10	50	100	12272
	DDIM + PnP	28.20	21.26	8.42	78.90	113.58	25.45	22.54	28.01	50	100	9262
	Direct Inversion + PnP	24.27	21.43	8.10	79.52	106.26	25.48	22.63	28.03	50	100	9262
	FlowEdit (SD3)	12.34	22.17	7.69	83.54	104.81	26.64	23.69	7.22	33	33	17140

Appendix

Table 4: Quantitative comparison of our method against other editing methods on PIE Bench.

Figure 21: User Study Results. Aggregated human preference rates from a four-way blind comparison, matching the data cited in the main paper. ChordEdit was the clear winner in both Semantic Alignment (42.5%) and Preservation Quality (48.3%), demonstrating its superior overall performance.

Symbol	Description
$t\in[0,1]$	Time variable for the probability flow. $t=1$ corresponds to the source data distribution, and $t=0$ to the target noise distribution.
$x_{t}$	The image state at time $t$ .
$c$	The text condition (prompt).
$c_{\rm src},c_{\rm tar}$	The source and target text prompts, respectively.
$x_{\rm src},x_{\rm tar}$	The source image ( $x_{1}$ ) and the desired target image ( $x_{0}$ ), respectively.
$p_{t}(x\mid c)$	The probability distribution of $x_{t}$ at time $t$ conditioned on $c$ .

Appendix

Table 5: Symbols Table

Text-Guided Image Editing

Text-guided image editing changes selected image content from natural-language instructions while aiming to preserve everything else.

See all 158 papers

PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing
Oct 16, 2026Jingyi Wang, Xiao LuImage Editing Text-Guided Image Editing
Hainan University School of Computer Science and Technology Haikou, China · Shanghai University School of Mechatronic Engineering and Automation Shanghai, China
Rethinking One-Step Image Editing through ChordEdit: Reproduction, Simplification, and New Insights
Jun 12, 2026Minghan Li, Jeremy Moebel, Mengyu WangText-Guided Image Editing One-Step Generative Modeling
Harvard AI and Robotics Lab
WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing
Jul 23, 2026Ming Hu, Mingyu Dou, Jianfu Yin +5Text-Guided Image Editing One-Step Generative Modeling
Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Zhongnan Hospital of Wuhan University +1

Oct 16, 2026J/K move · Enter open · S save

PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing

Jingyi Wang, Xiao Lu

Hainan University School of Computer Science and Technology Haikou, China · Shanghai University School of Mechatronic Engineering and Automation Shanghai, China

Image Editing Text-Guided Image Editing Diffusion-Based Image Editing Training-Free Image Editing

Open paper AskPDF arXiv

Recent one-step text-to-image (T2I) models enable efficient image synthesis, opening up new possibilities for interactive Web-based image editing. However, existing one-step editing methods often construct a global transport field through simple vector operations between conditional predictions. While such strong transport can effectively drive the image toward the target semantics, it may be released along unreliable directions or over non-edited regions, leading to structural distortions within the editing region and background drift elsewhere. More importantly, stabilizing the editing process through global smoothing or uniformly weakening the transport field often makes large semantic changes overly conservative. In this work, we revisit one-step image editing from the perspective of the tension between semantic strength and transport stability, and identify a key insight: strong semantic transport is not inherently unstable. What matters is whether it is applied along reliable directions and at reliable spatial locations. Motivated by this insight, we introduce PreciseEdit, a model-agnostic, training-free and inversion-free one-step editing framework that strengthens target-semantic alignment while preserving background fidelity and structural consistency. We further propose a dual-noise-scale role decomposition strategy: a higher-noise scale produces the strong target-directed transport used for actual editing, whereas a lower-noise scale jointly serves as a probe for directional agreement and spatial structure. Extensive experiments on PIE-Bench demonstrate that PreciseEdit achieves state-of-the-art performance and effectiveness on various editing tasks.

Abstract

Text-Guided Image Editing

Explore similar work

PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing

Rethinking One-Step Image Editing through ChordEdit: Reproduction, Simplification, and New Insights

WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing