Question about demo video

[Jerry-Master]

Sorry for bothering you but I saw in the demo video that you manage to reenact other faces like Obama's. How did you do this? Because as specified in the article, the generated model can only produce expressions close to those available in the dataset you train styleavatar with. Did you find such images for Obama, or is there a way to achieve same result training differently?

[Inferencer]

Sorry for bothering you but I saw in the demo video that you manage to reenact other faces like Obama's. How did you do this? Because as specified in the article, the generated model can only produce expressions close to those available in the dataset you train styleavatar with. Did you find such images for Obama, or is there a way to achieve same result training differently?

I'm just about to start learning style avatar but I would imagine they used video frames to train rather than searching for individual images