MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908688235626496 |
|---|---|
| author | Liu, Zichen Yu, Yue Ouyang, Hao Wang, Qiuyu Ma, Shuailei Cheng, Ka Leong Wang, Wen Bai, Qingyan Zhang, Yuxuan Zeng, Yanhong Li, Yixuan Zhu, Xing Shen, Yujun Chen, Qifeng |
| author_facet | Liu, Zichen Yu, Yue Ouyang, Hao Wang, Qiuyu Ma, Shuailei Cheng, Ka Leong Wang, Wen Bai, Qingyan Zhang, Yuxuan Zeng, Yanhong Li, Yixuan Zhu, Xing Shen, Yujun Chen, Qifeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03046 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues Liu, Zichen Yu, Yue Ouyang, Hao Wang, Qiuyu Ma, Shuailei Cheng, Ka Leong Wang, Wen Bai, Qingyan Zhang, Yuxuan Zeng, Yanhong Li, Yixuan Zhu, Xing Shen, Yujun Chen, Qifeng Computer Vision and Pattern Recognition 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. |
| title | MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.03046 |