This approach combines local editing and background preservation without external or user-provided spatial masks and without model fine-tuning, and achieves the strongest reported preservation metrics, including 27.44~dB PSNR and 0.055 LPIPS.
Abstract
Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, na\"ively switching the text condition during sampling often causes global drift, as denoising dynamics propagate changes across tokens and can disrupt unedited regions. To address this issue, we propose \textbf{A}synchronous \textbf{T}oken \textbf{D}ecoding \textbf{Edit} (ATDEdit), an inference-time framework that views each sampler step as a parallel update of a globally coupled token matrix and enables token-indexed condition switching with differentiated update policies. Instead of applying synchronous target-conditioned updates to all tokens, ATDEdit estimates editable locations using token-wise conditional surprisal and applies target-conditioned corrections to the selected token set. It supplies source key/value memory at keep-token positions and projects selected keep-token latent rows back to their source values; these operations promote background preservation but do not constitute a pixel-level invariance guarantee. This approach combines local editing and background preservation without external or user-provided spatial masks and without model fine-tuning. On PIE-Bench, ATDEdit achieves the strongest reported preservation metrics, including 27.44~dB PSNR and 0.055 LPIPS, while retaining competitive semantic alignment.
AnchorSteer is proposed, a training-free framework that exerts fine-grained control over both initialization and denoising trajectory that consistently outperforms existing baselines in text--image alignment while preserving high visual quality.
Xinyi Wang, Yuyang Huang, Yalin Su et al.· arXiv.org· 0 citations
This paper proposes ElasticTTT, a novel framework that preserves the prior generative distribution and rescues generative elasticity in standard TTT, achieving state-of-the-art performance on one-shot video editing.
Yueyi Liu, Chi Zhang, Sen Cui et al.· arXiv.org· 1 citation
This work revisits one-step image editing from a spatially controlled perspective and proposes WhereEdit, a framework that reformulates one-step editing as localized adaptive editing that consistently outperforms existing one-step image editing methods, achieving superior editing quality while maintaining the efficiency of one-step generation.
Ming Hu, Ming-Yu Dou, Jianfu Yin et al.· arXiv.org· 1 citation
This study proposes an automated discrete "Latent Space Exploration" framework utilizing random search to optimize seed selection and concludes that discrete seed optimization offers a robust and practical solution for personalized generation.
Yu Yamamoto, Qiu Chen· International Conference on...· 0 citations
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 \textbf{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 et al.· 0 citations
A causal interpretability framework is introduced that reveals that the tokens encoding semantics at the input need not be those that maintain them during generation, but also provides a causal view of internal mechanisms in diffusion transformers.
