- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes SAATEdit, a training-free and inversion-free framework for image and video editing. Built on FlowEdit, it transfers source-object attention logits to target editing tokens through Attention Reference Transfer (ART). Spatial Adaptive Enhancement (SAE) further scales and clips the transferred logits to strengthen localized editing. Experiments on PIE-Bench and FiVE-Bench demonstrate improved editing performance over FlowEdit and Wan-Edit.
Critical strengths
- The motivation is clear and reasonable. Insufficient editing strength and inaccurate localization are relevant limitations of inversion-free editing.
- The method is evaluated on both images and videos, showing some applicability across modalities.
Critical weaknesses
-
The contribution relative to existing attention-based editing methods is insufficiently established. FlowDirector [1], FlowAnchor [2], and SAM-Flow [3] already explore attention-guided localization, spatial attention modulation, or localized velocity updates. ReFlex [4] also combines source-attention injection and adaptation to improve editing. Although their implementations differ, these works are closely related to the proposed localization and enhancement mechanisms. Direct comparisons with the relevant inversion-free methods, and at least a detailed discussion of ReFlex, are needed to clarify the novelty. The related work about attention manipulation, which only covers Prompt-to-Prompt, is also insufficient.
-
The method is not fully specified for basic editing scenarios. Appendix C allows a null source anchor for object addition and a null target anchor for deletion. However, Eq. 6 requires a non-empty source token set, while Eq. 7 requires target tokens to receive the transferred reference. Neither the equations nor the algorithm explain how these cases are handled. The source-derived reference may also constrain edits involving substantial changes in object shape or spatial extent, as acknowledged in the limitations. These issues leave the claimed applicability to general editing tasks unclear.
-
The experimental comparisons are incomplete, and preservation of unedited content remains a concern. Video experiments omit FlowDirector and FlowAnchor, while image experiments omit representative inversion-free methods such as FlowAlign [5]. Although aggregate preservation metrics improve over FlowEdit, visible unintended changes remain. For example, adding a collar in Figure 6 also changes the dog’s facial expression. Stronger baseline comparisons at matched editing strength would help establish whether the method offers a better editing–preservation trade-off.
-
Generalization across image backbones is not demonstrated. Image experiments are limited to FLUX. Results on other flow-based backbones, such as SD3, would clarify whether the source-attention reference remains reliable and whether the same ART/SAE settings retain their benefits.
-
The video evaluation provides limited evidence for addition and deletion. These categories contain only 10 samples each, compared with 100 for each replacement or attribute category. Deletion achieves only 5% FiVE-Acc, while the reported addition score is based on a very small sample. The overall improvement therefore does not establish effectiveness across editing types, particularly those affected by the missing-anchor issue.
[1] FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing. CVPR 2026.
[2] FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing. ACM MM 2026.
[3] SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing. arXiv 2026.
[4] ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation. ICCV 2025.
[5] FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing. ICLR 2026.
Questions for authors
- How are ART and SAE implemented when either anchor is null?
- Does SAATEdit retain its benefits on SD3 using the same ART window and SAE gains?
4 comments
Q2. Applicability to basic editing types
We thank the reviewer for pointing this out. We have updated the Sec. 4.3 and Appendix D to explicitly specify the null-anchor cases: when (addition) or (deletion), ART (Eqs. 6–7) is skipped and only SAE is applied. Moreover, our per-category comparisons below show that the method improves editing capability across all basic edit types, including cases where the source-derived reference is least direct.
Video editing (FiVE-Bench). As reported in Table 10 and Fig. 8 of the revision, our method improves FiVE-Acc over Wan-Edit across all six basic categories (Table R5)—including Add object, Delete object, and Non-rigid replacement (which involves shape changes)—and also improves LPIPS across these categories (e.g., Rigid replacement and Add object ). Delete remains low for both methods due to the difficulty of this category rather than a failure of the enhancement path.
Table R5. Per-category FiVE-Acc on FiVE-Bench (higher is better).
| Category | Wan-Edit | Wan-Edit + Ours |
|---|---|---|
| Rigid replacement | 53.03 | 54.60 |
| Non-rigid replacement | 48.99 | 55.60 |
| Color | 66.67 | 81.30 |
| Material | 31.82 | 48.00 |
| Add object | 77.78 | 83.30 |
| Delete object | 0.00 | 5.00 |
Image editing (PIE-Bench). Similarly, in Table 12 and Fig. 9 of the revision, adding our method to FlowEdit improves CLIP-Whole across all four basic groups: Add, Delete, Change, and Style (Table R6). For edits with substantial shape or spatial changes, the reference is less informative, which is why Delete shows a larger structure cost. Overall, these results confirm that our method is applicable to general editing scenarios and consistently improves editing capability across them, while the structure cost for large shape changes is acknowledged.
Table R6. Per-category CLIP-Whole on PIE-Bench (higher is better).
| Group | FlowEdit | FlowEdit + Ours |
|---|---|---|
| Add | 27.37 | 27.96 |
| Delete | 25.17 | 25.69 |
| Change | 26.23 | 26.30 |
| Style | 26.10 | 28.41 |
Q3. Experimental comparisons and preservation of unedited content
We thank the reviewer for these suggestions. We have addressed the missing baselines in the revision: FlowDirector and FlowAnchor are now included in the video comparisons (Table 1 and Table 10; summarized in Tables R2 and R3), and FlowAlign is compared on both FLUX and SD3 (Table 2). We also strengthen the matched-strength comparison on SD3 with strong inversion-based and inversion-free baselines, including UniEdit, SNR-Edit, and SplitFlow.
FlowAlign. Table R7 summarizes the comparison. On FLUX, FlowAlign has better structure (Struct 25.39 vs. 27.57) but lower CLIP alignment (CLIP-W 25.28 vs. 26.51; CLIP-E 22.29 vs. 23.14). On SD3, the same pattern holds (Struct 15.17 vs. 33.60; CLIP-W 25.94 vs. 27.68; CLIP-E 22.33 vs. 24.23). FlowAlign therefore occupies the structure-preserving side of the trade-off, while our method occupies the editing side.
Matched editing strength. The FLUX Pareto sweep in Figure 7 compares the methods across the editing-strength sweep , the SD3 Pareto plot in Figure 12 (Appendix I) provides the same comparison on SD3, and the SD3 block of Table 2 includes UniEdit [7], SNR-Edit [8], SplitFlow [9], FlowEdit, and FlowAlign. For all compared methods, the hyperparameters follow the official configurations. This provides a stronger matched-strength comparison than an aggregate number alone.
The collar example in Figure 6. We agree with the reviewer's observation: in that example FlowEdit changes the dog's facial expression when adding the collar, and our method shows the same change. Our method improves editing strength and prevents the enhancement from spreading, but it does not substantially improve the base editor's structural fidelity; when FlowEdit exhibits a structural failure mode, our method often inherits it. We do not claim to be able to fix such local failure modes. The improvement in the aggregate structure-preservation metrics mainly comes from the spatial constraint of the enhancement operation, not from correcting every unintended change. We have made this explicit in the revised limitation.
Table R7. FlowAlign vs. SAATEdit on FLUX and SD3.
| Backbone | Method | Struct ↓ | PSNR ↑ | MSE ↓ | CLIP-W ↑ | CLIP-E ↑ |
|---|---|---|---|---|---|---|
| FLUX | FlowAlign [5] | 25.39 | 22.56 | 8.40 | 25.28 | 22.29 |
| FLUX | Ours | 27.57 | 22.83 | 8.27 | 26.51 | 23.14 |
| SD3 | FlowAlign [5] | 15.17 | 28.03 | 2.42 | 25.94 | 22.33 |
| SD3 | Ours | 33.60 | 21.09 | 10.73 | 27.68 | 24.23 |
Q4. Generalization across image backbones
We thank the reviewer for this suggestion. We have added an SD3 block to Table 2, covering FlowEdit, FlowAlign, UniEdit, SNR-Edit, SplitFlow, and Sam-Flow. SD3 is also a joint-attention MMDiT, so the same image-to-text sub-block is available. We apply ART/SAE with a light SD3-specific setting (, , ); no architectural change or retraining is required.
Table R8 reports the full SD3 comparison. On SD3, our method improves CLIP-Whole from 27.41 to 27.68 and CLIP-Edit from 23.92 to 24.23, at a structure cost (Struct 30.26→33.60; PSNR 21.64→21.09; MSE 9.87→10.73). Among all SD3 methods in Table 2, ours attains the highest CLIP-Whole and CLIP-Edit, confirming that the source-attention reference remains reliable on a different backbone and that ART/SAE retain their editing benefits with a light setting adjustment.
Figure 12 (Appendix I) reports the corresponding Pareto sweep on SD3: our method consistently improves over FlowEdit across the editing-strength sweep and occupies the high-editability side of the trade-off. It does not dominate the strongest SD3 methods, which is consistent with the trade-off discussed in Q1 and Q3.
Table R8. Full SD3 comparison on PIE-Bench.
| Method (SD3) | Struct ↓ | PSNR ↑ | MSE ↓ | CLIP-W ↑ | CLIP-E ↑ | Time (s) ↓ |
|---|---|---|---|---|---|---|
| FlowAlign | 15.17 | 28.03 | 2.42 | 25.94 | 22.33 | 2.98 |
| UniEdit | 25.83 | 24.33 | 5.56 | 26.46 | 23.08 | 1.07 |
| Sam-Flow | 14.90 | 26.87 | 3.71 | 26.93 | 23.47 | 52.79 |
| SNR-Edit | 26.85 | 22.12 | 8.80 | 27.30 | 23.77 | 5.03 |
| SplitFlow | 25.56 | 22.53 | 8.10 | 27.40 | 23.95 | 7.50 |
| FlowEdit [3] | 30.26 | 21.64 | 9.87 | 27.41 | 23.92 | 4.11 |
| FlowEdit+Ours | 33.60 | 21.09 | 10.73 | 27.68 | 24.23 | 4.39 |
Q5. Limited samples for addition and deletion on FiVE-Bench
We thank the reviewer for this concern. FiVE-Bench [6] is a widely used benchmark for training-free video editing; its core focus is fine-grained video editing, with a particular emphasis on object-level local edits. It therefore provides sufficient discriminative power for the training-free methods compared in this paper. FlowAnchor [2] itself also adopts FiVE-Bench as its evaluation benchmark, which further supports its relevance for this comparison. We report the complete per-category results in Table 10 and the corresponding radar plots in Figure 8, rather than relying only on the aggregate number.
Table R9 isolates the Add and Delete categories and compares our method with the base editor Wan-Edit [6]. On Add, FiVE-Acc improves from 77.78 to 83.30 and LPIPS from 101.60 to 93.40; on Delete, FiVE-Acc improves from 0.00 to 5.00 and LPIPS from 79.40 to 75.00. The corresponding radar plots in Fig. 8 (Appendix) show the same trend across all categories.
The small sample sizes of the Add and Delete subsets are defined by FiVE-Bench itself [6], not reduced by us. The Delete category is intrinsically difficult: the object must disappear while the background remains consistent. All methods obtain low FiVE-Acc (0.00–15.00), and our method improves over Wan-Edit. We therefore do not claim a large absolute gain on Delete; instead, we report it separately so that the reader can see the per-category behavior.
Table R9. Add and Delete categories on FiVE-Bench (base editor vs. ours).
| Method | Add FiVE-Acc ↑ | Add LPIPS ↓ | Delete FiVE-Acc ↑ | Delete LPIPS ↓ |
|---|---|---|---|---|
| Wan-Edit [6] | 77.78 | 101.60 | 0.00 | 79.40 |
| Wan-Edit + Ours | 83.30 | 93.40 | 5.00 | 75.00 |
[1] FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
[2] FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing
[3] SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing
[4] ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
[5] FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
[6] FiVE-Bench: A Fine-Grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models
[7] UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
[8] SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing
[9] SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
I thank the authors for their substantial effort in adding the missing baselines, SD3 experiments, and further explanations. These additions strengthen the empirical evaluation.
However, my concern about the incremental methodological novelty remains. More importantly, the undefined handling of addition and deletion was a fundamental omission in the original formulation, independently identified by all three reviewers. The revised explanation partially addresses this issue, but does not fully restore my confidence in the method’s completeness and soundness. It is still unclear how “all entity tokens” are extracted. Besides, the reliance on per-sample LLM processing limits the method’s practical applicability. Some editing gains also come with reduced preservation.
In recognition of the additional experiments and clarifications, I will raise my score from 1 to 2 (Weak rejection), while maintaining my rejection recommendation.
Q1. Contribution relative to FlowDirector, FlowAnchor, SAM-Flow, and ReFlex
We thank the reviewer for pointing out these related works. In the revision, we have expanded the Related Work section to discuss attention manipulation methods beyond P2P, added FlowDirector [1], FlowAnchor [2], SAM-Flow [3], and ReFlex [4] to our comparison tables, and added the corresponding qualitative comparisons in Appendix J. Below we clarify our mechanism differences and empirical advantages over each method.
Comparison with ReFlex [4]. As detailed in our response to Reviewer 2, ReFlex is an inversion-based method (requiring noised inversion, mid-step residual injection, top-k I2I-SA replacement, and mask blending). In I2T-CA, ReFlex mainly replaces unrelated background tokens to preserve image structure and scales target tokens with a fixed weight (α=4). In contrast, SAATEdit is strictly inversion-free and does not process background tokens: it extracts the structural prior from source object tokens, transfers this prior to target editing tokens, and applies a per-patch spatially adaptive gain. On PIE-Bench (FLUX) (Table R1), SAATEdit matches ReFlex on CLIP-E, but achieves much better structure preservation (Struct 27.57 vs. 42.60) and is 1.55× faster (14.10 s vs. 21.80 s). Fig. 14 (Appendix J) further corroborates this global-structure deficiency: ReFlex also modifies regions beyond the target—e.g., it changes the clothing color in the first row, the global saturation in the third row, and the overall image style in the eighth row—consistent with its much larger Structure Distance.
Table R1. ReFlex vs. SAATEdit on PIE-Bench.
Comparison with FlowDirector [1] and FlowAnchor [2]. FlowDirector builds a soft spatial mask M~ from cross-attention maps to gate the editing velocity (V^edit=V~edit⊙M~). In contrast, SAATEdit does not build a mask; it directly modulates the I2T-CA attention scores with a spatially adaptive gain. On FiVE-Bench (Table R2), our method outperforms FlowDirector on all five metrics and is 3.1× faster (4.70 min vs. 14.40 min). Meanwhile, FlowAnchor requires an external mask (GT, hand-drawn, or bounding box) to separate edit and non-edit regions, which increases user cost and fails when no source mask applies. Fig. 13 (Appendix J, top-right and bottom-right examples) also corroborates this on the Add category. While this mask stabilization gives FlowAnchor better structure scores, our method achieves a much higher overall FiVE-Acc (59.04 vs. 37.35, Table R2). As shown in Table R3, FlowAnchor fails on Add (0.00 vs. 83.30) due to its mask dependency, and our method also leads across all replacement, color, and material categories.
Table R2. Video comparison on FiVE-Bench.
Table R3. Per-category FiVE-Acc of FlowAnchor and our method.
Comparison with SAM-Flow [3]. Similar to FlowDirector, SAM-Flow extracts a soft mask from cross-attention to restrict differential velocity updates without modifying attention, whereas SAATEdit directly modifies the I2T-CA score sub-block at the attention level. On PIE-Bench (SD3) (Table R4 and the Pareto plot in Fig. 12), the two methods sit at different ends of the structure–edit trade-off: SAM-Flow leans toward structure preservation, while SAATEdit achieves stronger editing quality and is 12× faster (4.39 s vs. 52.72 s). Table R4. SAM-Flow vs. Ours on PIE-Bench(SD3) .
In summary, these four methods are related to ours, but differ clearly in core mechanism, editing scope, and efficiency. All the above discussions have been added to the revised manuscript.