TensorX
返回文献探索

Paper · arXiv 2502.17363

KV-Edit: Training-Free Image Editing for Precise Background Preservation

Tianrui Zhu, Shiyi Zhang, Jiawei Shao, Yansong Tang

37 upvotesFebruary 24, 2025arXiv 预印本
AI 摘要

KV-Edit uses the KV cache in DiT-based models to preserve background tokens, enabling high-quality image editing with seamless background consistency and low memory usage.

KV-EditKV cacheDiTsbackground tokensmemory consumptionspace complexityinversion-free methodDiT-based generative modelimage editing

Abstract

Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to O(1) using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
KV-Edit: Training-Free Image Editing for Precise Background Preservation | TensorX