The paper does not specify the need to input the descriptive text of the source image. #13
Description
Dear Authors,
I have a question regarding the implementation accompanying your paper. I noticed that the provided GitHub code requires the descriptive text (source prompt) of the source image when performing real image editing. However, this requirement does not appear to be mentioned in the paper itself.
Could you please clarify why the source description is necessary in the code implementation, even though it wasn't specified in the paper's methodology?