About hand crafted motion guidance

[emjay73]

Do you plan to release the code for video generation using hand-crafted motion guidance? If not, can you share the input data format of the hand-crafted motion and initial object position?

For instance, in the following image, the initial object position is depicted as a red star, and the motion is described as a red arrow.

How are they transformed to be a network input? Use this red-black image as it is? or split the arrow into multiple pieces and use another image for the initial object position?

Thank you in advance.

[xizaoqu]

Same question. One possible solution is to translate such patterns into motion vectors and sketch sequences.