MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues
This work addresses the need for more granular control in image editing for creators, offering a novel method that bridges diffusion models and traditional graphics software.
The paper tackles the problem of limited control in generative image editing by introducing a layered composition paradigm that disentangles user intentions into content, spatial, structural, and color cues, resulting in a system that effectively resolves the user intention gap and provides direct, intuitive control.
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.