CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xie, Weiyan, Gao, Han, Deng, Didan, Li, Kaican, Liu, April Hua, Huang, Yongxiang, Zhang, Nevin L.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912669584326656
author Xie, Weiyan
Gao, Han
Deng, Didan
Li, Kaican
Liu, April Hua
Huang, Yongxiang
Zhang, Nevin L.
author_facet Xie, Weiyan
Gao, Han
Deng, Didan
Li, Kaican
Liu, April Hua
Huang, Yongxiang
Zhang, Nevin L.
contents Recent advances in text-to-image (T2I) models have enabled training-free regional image editing by leveraging the generative priors of foundation models. However, existing methods struggle to balance text adherence in edited regions, context fidelity in unedited areas, and seamless integration of edits. We introduce CannyEdit, a novel training-free framework that addresses this trilemma through two key innovations. First, Selective Canny Control applies structural guidance from a Canny ControlNet only to the unedited regions, preserving the original image's details while allowing for precise, text-driven changes in the specified editable area. Second, Dual-Prompt Guidance utilizes both a local prompt for the specific edit and a global prompt for overall scene coherence. Through this synergistic approach, these components enable controllable local editing for object addition, replacement, and removal, achieving a superior trade-off among text adherence, context fidelity, and editing seamlessness compared to current region-based methods. Beyond this, CannyEdit offers exceptional flexibility: it operates effectively with rough masks or even single-point hints in addition tasks. Furthermore, the framework can seamlessly integrate with vision-language models in a training-free manner for complex instruction-based editing that requires planning and reasoning. Our extensive evaluations demonstrate CannyEdit's strong performance against leading instruction-based editors in complex object addition scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing
Xie, Weiyan
Gao, Han
Deng, Didan
Li, Kaican
Liu, April Hua
Huang, Yongxiang
Zhang, Nevin L.
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advances in text-to-image (T2I) models have enabled training-free regional image editing by leveraging the generative priors of foundation models. However, existing methods struggle to balance text adherence in edited regions, context fidelity in unedited areas, and seamless integration of edits. We introduce CannyEdit, a novel training-free framework that addresses this trilemma through two key innovations. First, Selective Canny Control applies structural guidance from a Canny ControlNet only to the unedited regions, preserving the original image's details while allowing for precise, text-driven changes in the specified editable area. Second, Dual-Prompt Guidance utilizes both a local prompt for the specific edit and a global prompt for overall scene coherence. Through this synergistic approach, these components enable controllable local editing for object addition, replacement, and removal, achieving a superior trade-off among text adherence, context fidelity, and editing seamlessness compared to current region-based methods. Beyond this, CannyEdit offers exceptional flexibility: it operates effectively with rough masks or even single-point hints in addition tasks. Furthermore, the framework can seamlessly integrate with vision-language models in a training-free manner for complex instruction-based editing that requires planning and reasoning. Our extensive evaluations demonstrate CannyEdit's strong performance against leading instruction-based editors in complex object addition scenarios.
title CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.06937