When StyleGAN Meets Stable Diffusion: a $\mathcal{W}_{+}$ Adapter for Personalized Image Generation

Ours with Fine-grained Attributes Editing Age Eye Close Smile Figure 1 . Given a single reference image (thumbnail in the top left), our W+ adapter not only integrates the identity into the text-to-image generation accurately but also enables modifications of facial attributes along the ∆w trajectory derived from StyleGAN. The text prompt is "a woman wearing a spacesuit in a forest".