CannyEdit：选择性Canny控制与双提示引导的无训练图像编辑

摘要

近期，文本到圖像（T2I）模型的進展使得無需訓練的區域圖像編輯成為可能，這主要依賴於基礎模型的生成先驗。然而，現有方法在平衡編輯區域的文本依從性、未編輯區域的上下文保真度以及編輯的無縫整合方面仍面臨挑戰。我們提出了CannyEdit，這是一種新穎的無訓練框架，通過兩項關鍵創新來應對這些挑戰：（1）選擇性Canny控制，該技術在用戶指定的可編輯區域內屏蔽Canny ControlNet的結構引導，同時通過反轉階段的ControlNet信息保留嚴格保護源圖像在未編輯區域的細節。這使得精確的、文本驅動的編輯成為可能，而不損害上下文的完整性。（2）雙提示引導，結合用於對象特定編輯的局部提示與全局目標提示，以維持場景交互的連貫性。在真實世界的圖像編輯任務（添加、替換、移除）中，CannyEdit超越了如KV-Edit等先前方法，在文本依從性和上下文保真度的平衡上實現了2.93%至10.49%的提升。在編輯無縫性方面，用戶研究顯示，當與未經編輯的真實圖像配對時，僅有49.2%的普通用戶和42.0%的AIGC專家能識別出CannyEdit的結果為AI編輯，而競爭對手方法的識別率則在76.08%至89.09%之間。

English

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 these challenges through two key innovations: (1) Selective Canny Control, which masks the structural guidance of Canny ControlNet in user-specified editable regions while strictly preserving details of the source images in unedited areas via inversion-phase ControlNet information retention. This enables precise, text-driven edits without compromising contextual integrity. (2) Dual-Prompt Guidance, which combines local prompts for object-specific edits with a global target prompt to maintain coherent scene interactions. On real-world image editing tasks (addition, replacement, removal), CannyEdit outperforms prior methods like KV-Edit, achieving a 2.93 to 10.49 percent improvement in the balance of text adherence and context fidelity. In terms of editing seamlessness, user studies reveal only 49.2 percent of general users and 42.0 percent of AIGC experts identified CannyEdit's results as AI-edited when paired with real images without edits, versus 76.08 to 89.09 percent for competitor methods.

CannyEdit：选择性Canny控制与双提示引导的无训练图像编辑

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

摘要

Support