零样本生成多属性图像，让不同特征自然协同。
Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
- 从条件概率出发建模属性间依赖关系
- 零样本下生成图像属性更一致，效果优于现有方法
- 适合个性化设计与创意生成场景
多属性定制因个性化内容需求日益增长而受到关注。尽管已有模型取得良好实证结果，但不同属性间的上下文一致性仍被忽视。本文认为，后续属性应遵循前序属性生成所建立的多变量条件分布。基于此，我们从条件概率理论重新定义多属性生成，并解决挑战性的零样本设置问题。通过显式建模属性间依赖关系，进一步提升多样属性组合下生成图像的一致性。此外，我们揭示了多属性定制与多任务学习之间的关联，有效缓解多属性合成中的高计算开销。大量实验表明，Z-Magic 在零样本图像生成上优于现有模型，对人工智能驱动的设计与创意应用具有广泛意义。
原文摘要 · Abstract (English)
The customization of multiple attributes has gained popularity with the rising demand for personalized content creation. Despite promising empirical results, the contextual coherence between different attributes has been largely overlooked. In this paper, we argue that subsequent attributes should follow the multivariable conditional distribution introduced by former attribute creation. In light of this, we reformulate multi-attribute creation from a conditional probability theory perspective and tackle the challenging zero-shot setting. By explicitly modeling the dependencies between attributes, we further enhance the coherence of generated images across diverse attribute combinations. Furthermore, we identify connections between multi-attribute customization and multi-task learning, effectively addressing the high computing cost encountered in multi-attribute synthesis. Extensive experiments demonstrate that Z-Magic outperforms existing models in zero-shot image generation, with broad implications for AI-driven design and creative applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。