Method __init__

(self,
                 *,
                 latent_dim: int,
                 clip_dim: int,
                 sync_dim: int,
                 text_dim: int,
                 hidden_dim: int,
                 depth: int,
                 fused_depth: int,
                 num_heads: int,
                 mlp_ratio: float = 4.0,
                 latent_seq_len: int,
                 clip_seq_len: int,
                 sync_seq_len: int,
                 text_seq_len: int = 77,
                 latent_mean: Optional[torch.Tensor] = None,
                 latent_std: Optional[torch.Tensor] = None,
                 empty_string_feat: Optional[torch.Tensor] = None,
                 v2: bool = False,
                 kernel_size: int = 7,
                 sync_kernel: int = 7,
                 use_inpaint: bool = False,
                 use_mlp: bool = False,
                 cross_attend: bool = False,
                 add_video: bool = False,
                 triple_fusion: bool = False,
                 gated_video: bool = False)