Class T2IAdapter

diffusers/src/diffusers/models/adapter.py:217–285

r""" A simple ResNet-like model that accepts images containing control signals such as keyposes and depth. The model generates multiple feature maps that are used as additional conditioning in [`UNet2DConditionModel`]. The model's architecture follows the original implementation of [

class T2IAdapter(ModelMixin, ConfigMixin):
    r"""
    A simple ResNet-like model that accepts images containing control signals such as keyposes and depth. The model
    generates multiple feature maps that are used as additional conditioning in [`UNet2DConditionModel`]. The model's
    architecture follows the original implementation of
    [Adapter](https://github.com/TencentARC/T2I-Adapter/blob/686de4681515662c0ac2ffa07bf5dda83af1038a/ldm/modules/encoders/adapter.py#L97)
     and
     [AdapterLight](https://github.com/TencentARC/T2I-Adapter/blob/686de4681515662c0ac2ffa07bf5dda83af1038a/ldm/modules/encoders/adapter.py#L235).

    This model inherits from [`ModelMixin`]. Check the superclass documentation for the generic methods the library
    implements for all the model (such as downloading or saving, etc.)

    Parameters:
        in_channels (`int`, *optional*, defaults to 3):
            Number of channels of Aapter's input(*control image*). Set this parameter to 1 if you're using gray scale
            image as *control image*.
        channels (`List[int]`, *optional*, defaults to `(320, 640, 1280, 1280)`):
            The number of channel of each downsample block's output hidden state. The `len(block_out_channels)` will
            also determine the number of downsample blocks in the Adapter.
        num_res_blocks (`int`, *optional*, defaults to 2):
            Number of ResNet blocks in each downsample block.
        downscale_factor (`int`, *optional*, defaults to 8):
            A factor that determines the total downscale factor of the Adapter.
        adapter_type (`str`, *optional*, defaults to `full_adapter`):
            The type of Adapter to use. Choose either `full_adapter` or `full_adapter_xl` or `light_adapter`.
    """

    @register_to_config
    def __init__(
        self,
        in_channels: int = 3,
        channels: List[int] = [320, 640, 1280, 1280],
        num_res_blocks: int = 2,
        downscale_factor: int = 8,
        adapter_type: str = "full_adapter",
    ):
        super().__init__()

        if adapter_type == "full_adapter":
            self.adapter = FullAdapter(in_channels, channels, num_res_blocks, downscale_factor)
        elif adapter_type == "full_adapter_xl":
            self.adapter = FullAdapterXL(in_channels, channels, num_res_blocks, downscale_factor)
        elif adapter_type == "light_adapter":
            self.adapter = LightAdapter(in_channels, channels, num_res_blocks, downscale_factor)
        else:
            raise ValueError(
                f"Unsupported adapter_type: '{adapter_type}'. Choose either 'full_adapter' or "
                "'full_adapter_xl' or 'light_adapter'."
            )

    def forward(self, x: torch.Tensor) -> List[torch.Tensor]:
        r"""
        This function processes the input tensor `x` through the adapter model and returns a list of feature tensors,
        each representing information extracted at a different scale from the input. The length of the list is
        determined by the number of downsample blocks in the Adapter, as specified by the `channels` and
        `num_res_blocks` parameters during initialization.
        """
        return self.adapter(x)