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.
@article{arxiv.2512.03046,
title = {MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues},
author = {Zichen Liu and Yue Yu and Hao Ouyang and Qiuyu Wang and Shuailei Ma and Ka Leong Cheng and Wen Wang and Qingyan Bai and Yuxuan Zhang and Yanhong Zeng and Yixuan Li and Xing Zhu and Yujun Shen and Qifeng Chen},
journal= {arXiv preprint arXiv:2512.03046},
year = {2025}
}
Comments
Code and demo available at https://magicquill.art/v2/