(self, in_channel: int, out_channels: int)

(value: float, divisor: int = 8)

( self, block: type[BasicBlock] | type[Bottleneck], planes: int, blocks: int,

(self, model, lora_name)

(image: torch.Tensor)

(node)

(*references, target_size: tuple[int, int] | None = None)

(images: torch.Tensor)

(in_channels: int, out_channels: int, stride: int = 1)

(in_channels: int, out_channels: int, stride: int = 1)

(device: torch.device)

(values)

( *, folder_name: str, model_name: str, manual_model_path: str | None, allow_none: bool =

(images: list[np.ndarray])

(value: Any)

()

( self, detector, source_image, *, conf_threshold, pre_nms_top

(folder_name: str, default_subdir: str)

(raw_state: Any)

()

(path: str, device: torch.device)

(value: str | None)

(batch: torch.Tensor, target_size: tuple[int, int])

( image_rgb: np.ndarray, detection: np.ndarray, *, face_size: int = 512, crop_scale: float

(value: Any)

(name: str)

(loc: Tensor, priors: Tensor, variances: list[float])

(predictions: Tensor, priors: Tensor, variances: list[float])

( self, image_rgb: np.ndarray, *, conf_threshold: float = 0.6, pre_nms

(self)

(network: str)

( *, face_size: int, crop_scale: float = 1.35, crop_shift_y: float = 0.0, )

(cfg: dict[str, Any], backbone: nn.Module)

()

()

(*, weights_path: str, network: str, device_name: str | None = None)

(self, retinaface_name, network, device, manual_retinaface_path)

()

(dets: np.ndarray, threshold: float)

(face_context: Any, expected: int)

(masks: list[np.ndarray])

(image_rgb: np.ndarray)

( image_rgb: np.ndarray, restored_face_rgb: np.ndarray, align_params: dict[str, Any], *, m

(image: Image.Image)

(*, model, lora_path: str | None)

(*, weights_path: str, network: str, device_name: str | None = None)

(device_name: str | None)

(lora_name: str, manual_lora_path: str | None)

(retinaface_name: str, manual_retinaface_path: str | None)

( *, faceir_model: dict[str, Any], clip, vae, face_image: torch.Tensor, prompt: str,

(detections: np.ndarray, selection: str, image_shape: tuple[int, int, int])

(cls)

(cls)

(cls)

(cls)

(cls)

( self, in_channels: int, out_channels: int, kernel_size: int = 3, str

(self, in_channels: int, out_channels: int, stride: int)

(self, in_channels_list: list[int], out_channels: int)

(self, model: nn.Module, indexes: list[int])

(self, width_mult: float)

(self, in_planes: int, out_planes: int, stride: int, expand_ratio: int)

(self)

( self, in_channels: int, out_channels: int, stride: int = 1, downsamp

( self, in_channels: int, out_channels: int, stride: int = 1, downsamp

(self, block: type[BasicBlock] | type[Bottleneck], layers: list[int])

(self, in_channels: int, num_anchors: int = 2, fpn_num: int = 3)

(self, in_channels: int, num_anchors: int = 2, fpn_num: int = 3)

(self, in_channels: int, num_anchors: int = 2, fpn_num: int = 3)

(self, cfg: dict[str, Any])

(self, cfg: dict[str, Any], image_size: tuple[int, int])

(self, *, weights_path: str, network: str, device: torch.device)

(nodeType, nodeData)

(images: torch.Tensor)

( self, retinaface_model, image, face_selection, face_size, cr

(self, x: Tensor)

(self, inputs: OrderedDict[str, Tensor] | dict[str, Tensor])

(self, x: Tensor)

(self, x: Tensor)

(self, x: Tensor)

(self, x: Tensor)

(self, x: Tensor)

(self, x: Tensor)

(self, x: Tensor)

(self, features: list[Tensor])

(self, features: list[Tensor])

(self, features: list[Tensor])

(self, x: Tensor)

()

()

()

()

(self, image, restored_face, align_params, mask_softness)

()

()

()

( self, faceir_model, clip, vae, face_image, prompt, r

(self)

(self)