Organizations: Sun Yat-sen University · South China University of Technology · Tsinghua University · Shandong University · Nankai University · Hunan University
Text-guided video editing modifies target content while preserving the appearance and temporal coherence of unedited regions. Training-based approaches provide strong control but demand substantial data and computation. Training-free methods fall into inversion-free and inversion-based paradigms. Inversion-free approaches avoid trajectory recovery, but their source-preserving guidance can limit editing strength and leave semantic changes incomplete. Inversion-based approaches recover a latent trajectory before regeneration, where approximation errors can accumulate and cause source-content drift and temporal inconsistency. We introduce Edit-VAR, the first training-free and inversion-free framework for text-guided video editing with a pretrained visual autoregressive video model. Edit-VAR directly encodes the source video into multi-scale discrete tokens and performs probability-guided conditional token replacement for source preservation. Attention-guided token-wise and scale-aware modulation selectively relaxes source constraints over edit-relevant positions and generation stages. Scale-Decoupled Generation, implemented as late-scale constraint release, regenerates motion-consistent details and reduces texture fragmentation. Residual-guided token pruning further exploits redundancy at the final two high-resolution scales to reduce inference cost. Extensive experiments and a blind user study demonstrate that Edit-VAR outperforms existing training-free video editing methods overall in editing fidelity, source preservation, temporal coherence, and inference efficiency.
Figures & tables
Figure 2: Motivation. Comparison between continuous inversion-based editing and our discrete VAR formulation. Inversion and subsequent regeneration can introduce source-content drift, whereas direct VAR encoding provides multi-scale discrete source tokens for reconstruction and conditional replacement without iterative trajectory inversion.
Figure 3: Overview of our framework. In Phase 1, the source video is encoded and a forward pass under the source prompt caches per-token probabilities and cross-attention maps. In Phase 2, a forward pass under the edit prompt performs probability-guided token replacement steered by the attention-guided spatial modulation field, which assigns low γ to edited regions and high γ to preserved regions. Source caching stops at scale Sstop ; beyond that, the editing pass generates freely.
Figure 4: Spatial modulation visualization. Given a source frame and an edit-target word, the cross-attention map localizes the editing region, which is then mapped to a per-token gamma field.
Method
Target Alignment
Video Quality
Non-edit Preservation
Time ↓
CLIP-S full↑
CLIP-S edit↑
Smooth. ↑
Aesth. ↑
PSNR ↑
SSIM ↑
LPIPS ↓
Training-based reference
VACE-V2V
0.957
0.970
0.936
0.605
13.51
0.380
0.618
9 min
Training-free, inversion-based
RAVE
0.962
0.975
0.973
0.552
18.81
0.674
0.437
17 min
FADE
0.966
0.972
0.958
0.533
14.75
0.626
0.211
14 min
Table 1: Main quantitative comparison with wall-clock inference time.
Figure 5: Qualitative comparison. Each example shows two frames for the edits “red boat hull” → “dark blue boat hull” and “tree frog” → “poison dart frog.” Edit-VAR consistently realizes the target appearance across frames while preserving scene geometry and unrelated background content. Competing methods may leave source attributes incompletely edited or introduce unintended changes to the background, lighting, and object appearance.
Variant
Target Alignment
Video Quality
Non-edit Preservation
Time (s)
CLIP-S full↑
CLIP-S edit↑
Smooth. ↑
Aesth. ↑
PSNR ↑
SSIM ↑
LPIPS ↓
Full method (no pruning)
0.979
0.980
0.989
0.611
22.89
0.833
0.172
85s
w/o attention guidance
0.935
0.931
0.975
0.560
19.56
0.563
0.373
85s
w/o scale envelope
0.958
0.933
0.979
0.514
20.43
0.667
0.287
85s
w/o Scale-Decoupled Generation
0.935
0.951
0.980
0.524
21.43
0.612
0.189
130s
AREdit-style uniform γ
0.895
0.913
0.975
0.541
16.30
0.498
0.456
85s
Table 2: Ablation study. The uniform- γ variant is the AREdit-style baseline. K denotes the percentage of retained tokens; random pruning controls for the token budget.
Figure 6: Qualitative ablation. Attention guidance and the scale envelope enable localized token replacement, while Scale-Decoupled Generation reduces fragmented source appearance. Residual pruning with K=50% remains visually close to the full method.
Appendix figures & tables13 assets
Supplementary material from the paper’s appendix.
Appendix
Parameter
Value
γstart
2.00
γendfg / γendbg
1.60 / 1.78
Image / video transition scale
5 / 4
Scale-envelope width wt
0.06
Attention center ca / width wa
0.50 / 0.10
Directly extracted attention layers
First 5 of 36
Appendix
Table 3: Final implementation configuration. The same settings are used for all editing categories.
Figure 7: Effect of the number of attention layers. We compare localization maps obtained by aggregating the first 1, 3, 5, and 10 layers and all layers. Aggregating the first five layers provides a stable and concentrated localization signal, while using additional layers brings limited qualitative change and incurs greater storage cost. We therefore use the first five layers throughout our experiments.
Pipeline
PSNR ↑
SSIM ↑
LPIPS ↓
Wan2.1
25.62
0.898
0.124
InfinityStar
29.93
0.920
0.061
Appendix
Table 4: Source-video reconstruction fidelity of the Wan2.1 and InfinityStar pipelines. Wan2.1 uses VAE encoding followed by inversion-based reconstruction and decoding, whereas InfinityStar directly reconstructs the video from its encoded multi-scale tokens.
Figure 8: Qualitative source-video reconstruction comparison. We show representative source frames together with reconstructions from the inversion-based Wan2.1 pipeline and the direct token-based InfinityStar pipeline, highlighting differences in structural preservation, appearance fidelity, and fine visual details.
Parameter
Value
CLIP-S edit↑
PSNR ↑
LPIPS ↓
Smooth. ↑
γendfg
1.40
0.980
19.75
0.189
0.985
1.50
0.977
21.06
0.183
0.984
1.55
0.981
22.37
0.178
0.983
1.60 †
0.980
22.89
0.172
0.989
1.65
0.971
22.97
0.175
0.981
1.70
0.954
23.01
0.177
0.980
Appendix
Table 5: Hyperparameter sensitivity analysis. We vary one parameter at a time while keeping the others fixed. † denotes the default configuration.
Figure 9: Additional qualitative comparisons with the baselines evaluated in the main paper. All methods use the same source video and target editing prompt for each case, with matched temporal sampling and output resolution.
Figure 10: User study results. Distributions of the four ordinal ratings ( Fail , Pass , Good , and Excellent ) assigned independently to each method. From left to right, the three panels report editing quality, background preservation, and temporal consistency.
Selection
Kept K
Phase 2
Two-Phase Total
Quality
Time (s) ↓
Speedup ↑
Time (s) ↓
Speedup ↑
CLIP-S full↑
CLIP-S edit↑
Smooth. ↑
Aesth. ↑
LPIPS ↓
No pruning
100%
65.0
1.00 ×
84.8
1.00 ×
.979
.980
.989
.611
.172
Residual-guided
90%
61.2
1.06 ×
81.0
1.05 ×
.979
.978
.989
.610
.175
Residual-guided
70%
51.2
1.27 ×
70.9
1.19 ×
.975
.977
.989
.608
.175
Residual-guided
50%
43.9
1.48 ×
63.7
1.33 ×
.972
.976
.988
.609
.176
Residual-guided
30%
39.4
1.65 ×
59.2
1.43 ×
.965
.970
.975
.593
.204
Appendix
Table 6: Quality–efficiency trade-off of residual-guided token pruning. Pruning is applied to the final two generation scales. Runtime is measured on a single NVIDIA A800 GPU with 81 frames. Phase 2 speedup is relative to its 65.0 s unpruned runtime; two-phase speedup is relative to the 84.8 s pipeline with Scale-Decoupled Generation and no pruning.
Edit Type
Method
Target Alignment
Video Quality
Non-edit Preservation
CLIP-S full↑
CLIP-S edit↑
Smooth. ↑
Aesth. ↑
PSNR ↑
SSIM ↑
LPIPS ↓
Object Replacement
Best Baseline
0.941
0.957
0.988
0.611
20.76
0.801
0.190
Ours
0.957
0.970
0.991
0.613
21.87
0.815
0.176
Object Addition
Best Baseline
0.976
0.984
0.970
0.581
20.07
0.788
0.199
Ours
0.979
0.985
0.988
0.603
22.59
0.823
0.174
Background Replacement
Best Baseline
0.956
0.963
0.977
0.580
19.73
0.781
0.209
Appendix
Table 7: Per-edit-type quantitative comparison. Results broken down by editing category.
Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to-fine prediction. However, their potential for text-guided image editing remains largely underexplored. Existing training-free VAR editing approaches often formulate editing as target-conditioned regeneration guided or constrained by the source image, and may rely on inversion, test-time optimization, attention control, or user-provided masks. This generation-centric formulation does not fully exploit the multiscale source representations provided by VARs and may introduce additional computation or intervention. We instead take a source-centric perspective on VAR editing, in which the encoded source image tokens serve as the primary visual state and the editing process focuses on condition-induced changes. Based on this perspective, we propose EditMod, which compares source- and target-conditioned predictions under a shared autoregressive context, treats their difference as a scale-wise editing direction, and applies it as a residual update to source tokens at selected scales. Experiments show that EditMod achieves leading source-image fidelity while maintaining strong text alignment, and completes end-to-end editing of a 1K image in only 1.57 seconds on a single A100 GPU without per-image preparation.
Hongyi Fang, Chuwen Xie, Benjia Zhou +6
Beijing Institute of Technology, Zhuhai · Zhejiang University · Tencent +1
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal memory for local coherence, correspondence-based post-attention token injection for long-range identity preservation, and soft latent blending for edit locality. The same framework supports instruction-guided and reference-guided edits, including style transfer, attribute modification, object insertion, part-level editing, and subject replacement. On FiVE, EditVid achieves 78.16 FiVE-Acc, compared with 58.95 for the strongest evaluated training-free baseline, while obtaining competitive results on IVEBench. A user study further shows a 51.8% overall preference for EditVid over 7 competing methods.
Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen +6
Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise manipulation in diffusion-based methods to token-level operations, VAR-based approaches achieve better background preservation and significantly faster inference. However, existing VAR-based editing methods still face two key challenges: accurately localizing editable tokens and maintaining structural consistency in the edited results. In this work, we propose a novel text-guided image editing framework rooted in an analysis of intermediate feature distributions within VAR models. First, we introduce a coarse-to-fine token localization strategy that can refine editable regions, balancing editing fidelity and background preservation. Second, we analyze the intermediate representations of VAR models and identify structure-related features, by which we design a simple yet effective feature injection mechanism to enhance structural consistency between the edited and source images. Third, we develop a reinforcement learning-based adaptive feature injection scheme that automatically learns scale- and layer-specific injection ratios to jointly optimize editing fidelity and structure preservation. Extensive experiments demonstrate that our method achieves superior structural consistency and editing quality compared with state-of-the-art approaches, across both local and global editing scenarios.
Tao Xia, Jiawei Liu, Yukun Zhang +3
Beijing Institute of Technology, Beijing, China · Shenyang Institute of Automation, CAS, Shenyang, China · Meitu Inc, MTLab, Beijing, China