Method forward

src/diffusers/models/resnet.py:148–185

(self, input_tensor: torch.Tensor, temb: torch.Tensor, *args, **kwargs)

            )

    def forward(self, input_tensor: torch.Tensor, temb: torch.Tensor, *args, **kwargs) -> torch.Tensor:
        if len(args) > 0 or kwargs.get("scale", None) is not None:
            deprecation_message = "The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`."
            deprecate("scale", "1.0.0", deprecation_message)

        hidden_states = input_tensor

        hidden_states = self.norm1(hidden_states, temb)

        hidden_states = self.nonlinearity(hidden_states)

        if self.upsample is not None:
            # upsample_nearest_nhwc fails with large batch sizes. see https://github.com/huggingface/diffusers/issues/984
            if hidden_states.shape[0] >= 64:
                input_tensor = input_tensor.contiguous()
                hidden_states = hidden_states.contiguous()
            input_tensor = self.upsample(input_tensor)
            hidden_states = self.upsample(hidden_states)

        elif self.downsample is not None:
            input_tensor = self.downsample(input_tensor)
            hidden_states = self.downsample(hidden_states)

        hidden_states = self.conv1(hidden_states)

        hidden_states = self.norm2(hidden_states, temb)

        hidden_states = self.nonlinearity(hidden_states)

        hidden_states = self.dropout(hidden_states)
        hidden_states = self.conv2(hidden_states)

        if self.conv_shortcut is not None:
            input_tensor = self.conv_shortcut(input_tensor)

        output_tensor = (input_tensor + hidden_states) / self.output_scale_factor

        return output_tensor


class ResnetBlock2D(nn.Module):