MagicQuillV2: 基于分层视觉提示的精确交互式图像编辑
MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues
AI总结:
MagicQuillV2通过分层视觉提示实现精确交互式图像编辑,解决传统生成模型与图形软件间的控制与语义平衡问题。
摘要:
我们提出了MagicQuill V2,一种引入分层组合范式的新型系统,旨在弥合扩散模型的语义能力与传统图形软件的精细控制之间的差距。尽管扩散变换器在整体生成方面表现优异,但其使用单一、整体的提示无法区分用户对内容、位置和外观的不同意图。为解决这一问题,我们的方法将创作意图分解为一组可控的视觉提示:一个内容层用于创建什么,一个空间层用于放置位置,一个结构层用于形状如何塑造,以及一个颜色层用于调色板。我们的技术贡献包括一个专门的数据生成管道用于上下文感知的内容整合,一个统一的控制模块用于处理所有视觉提示,以及一个微调的空间分支用于精确的局部编辑,包括对象移除。大量实验验证了这种分层方法有效解决了用户意图差距,使创作者能够直接、直观地控制生成过程。
英文摘要:
We propose MagicQuill V2, a novel system that introduces a \textbf{layered composition} paradigm to generative image editing, bridging the gap between the semantic power of diffusion models and the granular control of traditional graphics software. While diffusion transformers excel at holistic generation, their use of singular, monolithic prompts fails to disentangle distinct user intentions for content, position, and appearance. To overcome this, our method deconstructs creative intent into a stack of 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 control over the generative process.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。