Method forward

src/models/motion_module.py:350–387

(
        self,
        hidden_states,
        encoder_hidden_states=None,
        attention_mask=None,
        video_length=None,
        **cross_attention_kwargs,
    )

        self.set_processor(processor)

    def forward(
        self,
        hidden_states,
        encoder_hidden_states=None,
        attention_mask=None,
        video_length=None,
        **cross_attention_kwargs,
    ):
        if self.attention_mode == "Temporal":
            d = hidden_states.shape[1]  # d means HxW
            hidden_states = rearrange(
                hidden_states, "(b f) d c -> (b d) f c", f=video_length
            )

            if self.pos_encoder is not None:
                hidden_states = self.pos_encoder(hidden_states)

            encoder_hidden_states = (
                repeat(encoder_hidden_states, "b n c -> (b d) n c", d=d)
                if encoder_hidden_states is not None
                else encoder_hidden_states
            )

        else:
            raise NotImplementedError

        hidden_states = self.processor(
            self,
            hidden_states,
            encoder_hidden_states=encoder_hidden_states,
            attention_mask=attention_mask,
            **cross_attention_kwargs,
        )

        if self.attention_mode == "Temporal":
            hidden_states = rearrange(hidden_states, "(b d) f c -> (b f) d c", d=d)

        return hidden_states