The diffusion-based text-to-image model harbors immense potential in
transferring reference style. However, current encoder-based approaches
significantly impair the text controllability of text-to-image models while
transferring styles. In this paper, we introduce \textit{DEADiff} to address
this issue using the following two strategies: 1) a mechanism to decouple the
style and semantics of reference images. The decoupled feature representations
are first extracted by Q-Formers which are instructed by different text
descriptions. Then they are injected into mutually exclusive subsets of
cross-attention layers for better disentanglement. 2) A non-reconstructive
learning method. The Q-Formers are trained using paired images rather than the
identical target, in which the reference image and the ground-truth image are
with the same style or semantics. We show that DEADiff attains the best visual
stylization results and optimal balance between the text controllability
inherent in the text-to-image model and style similarity to the reference
image, as demonstrated both quantitatively and qualitatively. Our project page
is~\href{https://tianhao-qi.github.io/DEADiff/}{this https URL}.

通过使用 DEADiff 的两种策略解决了目前基于编码器的文本到图像模型在转换风格时导致的文本可控性下降的问题，并展示了 DEADiff 在视觉风格化方面的最佳结果和在文本到图像模型中文本可控性和与参考图像的风格相似性之间的最佳平衡。