Open sky-fly97 opened 2 years ago
You mean generate faces with the same pose? For that you can use the learned flow module and give the relevant condition vector with desired yaw and pitch. Then you can sample from the z space of the flow module to produce different w codes having the same pose.
Hello, I want to know that styleflow can artificially generate faces with various poses and expressions. How do I use code to generate a series of continuous poses? Which parameters should I change?