Collaborative_edit

[jy12he]

Excellent work! I am very interested in Multi-Modal Collaborative Editing. I have a question: why do the results of Mask_edit and Text_edit show a significant difference in skin tone compared to the input image, while the result of Collaborative_edit has a skin tone very similar to the input image? I look forward to your response, thank you !

[jy12he]

Hi, I have another question: why are both the dynamic diffuser and LDM based on U-Net, but the dynamic diffuser is much smaller than a uni-modal conditional diffusion model? Is it because the model structure of the dynamic diffuser is greatly simplified? Could you please explain this in a bit more detail, thank you !