fix: minor fixes to types in the DA Detector

Author: blessedcoolant

invokeai/backend/image_util/depth_anything/__init__.py

@@ -9,6 +9,7 @@
 from PIL import Image
 from torchvision.transforms import Compose
 
+from build.lib.invokeai.backend.model_management.models.base import ModelNotFoundException
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
 from invokeai.backend.image_util.depth_anything.model.dpt import DPT_DINOv2
 from invokeai.backend.image_util.depth_anything.utilities.util import NormalizeImage, PrepareForNet, Resize
@@ -17,6 +18,8 @@
 
 config = InvokeAIAppConfig.get_config()
 
+DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
+
 DEPTH_ANYTHING_MODELS = {
     "large": {
         "url": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitl14.pth?download=true",
@@ -53,9 +56,9 @@
 class DepthAnythingDetector:
     def __init__(self) -> None:
         self.model = None
-        self.model_size: Union[Literal["large", "base", "small"], None] = None
+        self.model_size: Union[DEPTH_ANYTHING_MODEL_SIZES, None] = None
 
-    def load_model(self, model_size=Literal["large", "base", "small"]):
+    def load_model(self, model_size: DEPTH_ANYTHING_MODEL_SIZES = "small"):
         DEPTH_ANYTHING_MODEL_PATH = pathlib.Path(config.models_path / DEPTH_ANYTHING_MODELS[model_size]["local"])
         if not DEPTH_ANYTHING_MODEL_PATH.exists():
             download_with_progress_bar(DEPTH_ANYTHING_MODELS[model_size]["url"], DEPTH_ANYTHING_MODEL_PATH)
@@ -84,16 +87,19 @@ def to(self, device):
         self.model.to(device)
         return self
 
-    def __call__(self, image, resolution=512):
-        image = np.array(image, dtype=np.uint8)
-        image = image[:, :, ::-1] / 255.0
+    def __call__(self, image: Image.Image, resolution: int = 512):
+        if self.model is None:
+            raise ModelNotFoundException("Depth Anything Model not loaded")
+
+        np_image = np.array(image, dtype=np.uint8)
+        np_image = np_image[:, :, ::-1] / 255.0
 
-        image_height, image_width = image.shape[:2]
-        image = transform({"image": image})["image"]
-        image = torch.from_numpy(image).unsqueeze(0).to(choose_torch_device())
+        image_height, image_width = np_image.shape[:2]
+        np_image = transform({"image": image})["image"]
+        tensor_image = torch.from_numpy(np_image).unsqueeze(0).to(choose_torch_device())
 
         with torch.no_grad():
-            depth = self.model(image)
+            depth = self.model(tensor_image)
             depth = F.interpolate(depth[None], (image_height, image_width), mode="bilinear", align_corners=False)[0, 0]
             depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0