← 研踪 PaperTrailCVF · CVPR 2026:cvf:0f4ea4b8839ae7a4abed46d4760c2027 · 记录 #1
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues
Liu, ZichenYu, YueOuyang, HaoWang, QiuyuMa, ShuaileiCheng, Ka LeongWang, WenBai, QingyanZhang, YuxuanZeng, YanhongLi, YixuanZhu, XingShen, YujunChen, Qifeng 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 01:09
摘要
We propose MagicQuill V2, a novel framework that introduces a layered composition paradigm to generative image editing, bridging the gap between the semantic power of modern diffusion models and the granular control of traditional graphics software. While state-of-the-art diffusion transformers excel at holistic generation, their use of singular, monolithic prompts fails to disentangle distinct user intentions for content, position, and style. To overcome this limitation, our method deconstructs creative intent into a stack of independently controllable visual cues: a content layer for what to create, a spatial layer for where to place it, a structural layer for how it is shaped, and a color layer for its palette. Our technical contributions include a specialized data generation pipeline for context-aware content integration, a unified control module to process all visual cues, and a fine-tuned spatial branch for precise local editing, including object removal. Extensive experiments validate that this layered approach effectively resolves the user intention gap, granting creators direct, intuitive, and powerful control over the generative process.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues
We propose MagicQuill V2, a novel framework that introduces a layered composition paradigm to generative image editing, bridging the gap between the semantic power of modern diffusion models and the granular control of traditional graphics software. While state-of-the-art diffusion transformers excel at holistic generation, their use of singular, monolithic prompts fails to disentangle distinct user intentions for content, position, and style. To overcome this limitation, our method deconstructs creative intent into a stack of independently controllable visual cues: a content layer for what to create, a spatial layer for where to place it, a structural layer for how it is shaped, and a color layer for its palette. Our technical contributions include a specialized data generation pipeline for context-aware content integration, a unified control module to process all visual cues, and a fine-tuned spatial branch for precise local editing, including object removal. Extensive experiments validate that this layered approach effectively resolves the user intention gap, granting creators direct, intuitive, and powerful control over the generative process.
查看此版本解读 →查看此版本原文 ↗