Function modulate

diffsynth/models/wan_video_dit.py:239–240

(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor)

def modulate(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor):
    return (x * (1 + scale) + shift)


def sinusoidal_embedding_1d(dim, position):