Abstract
Creativity, both in human and diffusion models, remains an inherently abstract concept; thus, simply adding "creative" to a prompt does not yield reliable semantic recognition by the model. In this work, we concretize the abstract notion of "creative" through the TP2O task, which aims to merge two unrelated concepts, and introduce CreTok, redefining "creative" as the token $\texttt{<CreTok>}$. This redefinition offers a more concrete and universally adaptable representation for concept blending. This redefinition occurs continuously, involving the repeated random sampling of text pairs with different concepts and optimizing cosine similarity between target and constant prompts. This approach enables $\texttt{<CreTok>}$ to learn a method for creative concept fusion. Extensive experiments demonstrate that the creative capability enabled by $\texttt{<CreTok>}$ substantially surpasses recent SOTA diffusion models and achieves superior creative generation. CreTok exhibits greater flexibility and reduced time overhead, as $\texttt{<CreTok>}$ can function as a universal token for any concept, facilitating creative generation without retraining.
Abstract (translated)
创造力，无论是对于人类还是扩散模型而言，始终是一个抽象的概念；因此，仅仅在提示中添加“创意”一词并不能使模型可靠地识别其语义。在这项工作中，我们通过TP2O任务具体化了“创意”的抽象概念，该任务旨在融合两个不相关的概念，并引入了CreTok，将“创意”重新定义为标记$\texttt{<CreTok>}$. 这种重新定义提供了一种更具体且普遍适用的概念融合表示。这种重新定义是持续进行的，涉及对具有不同概念的文本对重复随机采样，并优化目标提示与常量提示之间的余弦相似度。这种方法使$\texttt{<CreTok>}$能够学习一种创意性概念融合的方法。广泛的实验表明，由$\texttt{<CreTok>}$启用的创造性能力大大超越了最近的SOTA扩散模型，并实现了更优质的创意生成。CreTok展示了更大的灵活性和减少的时间开销，因为$\texttt{<CreTok>}$可以作为任何概念的通用标记，在无需重新训练的情况下促进创意生成。
URL
https://arxiv.org/abs/2410.24160
