FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editing

• URL: http://arxiv.org/abs/2602.08725v1
• Date: Mon, 09 Feb 2026 14:34:18 GMT
• Title: FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editing
• Authors: Yongwen Lai, Chaoqun Wang, Shaobo Min,
• Abstract summary: Text-guided image editing aims to modify specific regions according to the target prompt while preserving the identity of the source image.<n>Recent methods exploit explicit binary masks to constrain editing, but hard mask boundaries introduce artifacts and reduce editability.<n>We propose FusionEdit, a training-free image editing framework that achieves precise and controllable edits.
• Score: 7.53296048773288
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-guided image editing aims to modify specific regions according to the target prompt while preserving the identity of the source image. Recent methods exploit explicit binary masks to constrain editing, but hard mask boundaries introduce artifacts and reduce editability. To address these issues, we propose FusionEdit, a training-free image editing framework that achieves precise and controllable edits. First, editing and preserved regions are automatically identified by measuring semantic discrepancies between source and target prompts. To mitigate boundary artifacts, FusionEdit performs distance-aware latent fusion along region boundaries to yield the soft and accurate mask, and employs a total variation loss to enforce smooth transitions, obtaining natural editing results. Second, FusionEdit leverages AdaIN-based modulation within DiT attention layers to perform a statistical attention fusion in the editing region, enhancing editability while preserving global consistency with the source image. Extensive experiments demonstrate that our FusionEdit significantly outperforms state-of-the-art methods. Code is available at \href{https://github.com/Yvan1001/FusionEdit}{https://github.com/Yvan1001/FusionEdit}.

Related papers

• SpotEdit: Selective Region Editing in Diffusion Transformers [66.44912649206553]
  SpotEdit is a training-free diffusion editing framework that selectively updates only the modified regions.<n>By reducing unnecessary computation and maintaining high fidelity in unmodified areas, SpotEdit achieves efficient and precise image editing.
  arXiv  Detail & Related papers  (2025-12-26T14:59:41Z)
• SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder [52.754326452329956]
  We introduce a method for disentangled and continuous editing through token-level manipulation of text embeddings.<n>The edits are applied by manipulating the embeddings along carefully chosen directions, which control the strength of the target attribute.<n>Our method operates directly on text embeddings without modifying the diffusion process, making it model agnostic and broadly applicable to various image backbones.
  arXiv  Detail & Related papers  (2025-10-06T17:51:04Z)
• FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing [75.29825659756351]
  FlashEdit is a novel framework designed to enable high-fidelity, real-time image editing.<n>Its efficiency stems from three key innovations: (1) a One-Step Inversion-and-Editing (OSIE) pipeline that bypasses costly iterative processes; (2) a Background Shield (BG-Shield) technique that guarantees background preservation by selectively modifying features only within the edit region; and (3) a Sparsified Spatial Cross-Attention (SSCA) mechanism that ensures precise, localized edits by suppressing semantic leakage to the background.
  arXiv  Detail & Related papers  (2025-09-26T11:59:30Z)
• FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model [54.693572837423226]
  FireEdit is an innovative Fine-grained Instruction-based image editing framework that exploits a REgion-aware VLM.<n>FireEdit is designed to accurately comprehend user instructions and ensure effective control over the editing process.<n>Our approach surpasses the state-of-the-art instruction-based image editing methods.
  arXiv  Detail & Related papers  (2025-03-25T16:59:42Z)
• Enhancing Text-to-Image Editing via Hybrid Mask-Informed Fusion [61.42732844499658]
  This paper systematically improves the text-guided image editing techniques based on diffusion models. We incorporate human annotation as an external knowledge to confine editing within a Mask-informed'' region.
  arXiv  Detail & Related papers  (2024-05-24T07:53:59Z)
• FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing [3.852667054327356]
  We introduce FlexEdit, a flexible and controllable editing framework for objects.<n>We iteratively adjust latents at each denoising step using our FlexEdit block.<n>Our framework employs an adaptive mask, automatically extracted during denoising, to protect the background.
  arXiv  Detail & Related papers  (2024-03-27T14:24:30Z)
• LayerDiffusion: Layered Controlled Image Editing with Diffusion Models [5.58892860792971]
  LayerDiffusion is a semantic-based layered controlled image editing method. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy. Experimental results demonstrate the effectiveness of our method in generating highly coherent images.
  arXiv  Detail & Related papers  (2023-05-30T01:26:41Z)
• DiffEdit: Diffusion-based semantic image editing with mask guidance [64.555930158319]
  DiffEdit is a method to take advantage of text-conditioned diffusion models for the task of semantic image editing. Our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited.
  arXiv  Detail & Related papers  (2022-10-20T17:16:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.