added Apple's "Depth Pro" preprocessor

modules/control/proc/depth_pro/__init__.py

@@ -0,0 +1,95 @@
+import cv2
+import numpy as np
+import torch
+from PIL import Image
+
+from modules import devices, masking
+from modules.shared import opts
+
+
+class DepthProDetector:
+    """Wrapper around Apple's DepthPro depth estimation model."""
+
+    def __init__(self, model, processor):
+        self.model = model
+        self.processor = processor
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_or_path: str, cache_dir: str, use_fast_processor: bool = False, **kwargs):
+        from transformers import AutoImageProcessor, DepthProForDepthEstimation
+
+        processor_kwargs = {"cache_dir": cache_dir}
+        processor_kwargs.update(kwargs)
+        if use_fast_processor:
+            from transformers.models.depth_pro.image_processing_depth_pro_fast import DepthProImageProcessorFast
+
+            processor = DepthProImageProcessorFast.from_pretrained(
+                pretrained_model_or_path,
+                **processor_kwargs,
+            )
+        else:
+            processor = AutoImageProcessor.from_pretrained(
+                pretrained_model_or_path,
+                **processor_kwargs,
+            )
+
+        model = DepthProForDepthEstimation.from_pretrained(
+            pretrained_model_or_path,
+            cache_dir=cache_dir,
+        )
+        model = model.to(device=devices.device).eval()
+        return cls(model, processor)
+
+    def _prepare_inputs(self, image: Image.Image) -> dict:
+        inputs = self.processor(images=image, return_tensors="pt")
+        tensor_inputs = {}
+        for key, value in inputs.items():
+            if isinstance(value, torch.Tensor):
+                tensor_inputs[key] = value.to(device=devices.device)
+            else:
+                tensor_inputs[key] = value
+        return tensor_inputs
+
+    def __call__(
+        self,
+        image,
+        color_map: str = "inferno",
+        output_type: str = "pil",
+    ):
+        if isinstance(image, list):
+            image = image[0]
+        if image is None:
+            return image
+        if not isinstance(image, Image.Image):
+            image = Image.fromarray(np.array(image))
+
+        original_size = (image.height, image.width)
+        inputs = self._prepare_inputs(image)
+        with devices.inference_context():
+            outputs = self.model(**inputs)
+        results = self.processor.post_process_depth_estimation(outputs, target_sizes=[original_size])
+        depth_tensor = results[0]["predicted_depth"].to(torch.float32)
+        if opts.control_move_processor:
+            self.model.to("cpu")
+
+        # Invert to align with other depth processors that render near as bright
+        depth_tensor = 1.0 / torch.clamp(depth_tensor, min=1e-6)
+        depth_tensor -= depth_tensor.min()
+        max_val = depth_tensor.max()
+        if max_val > 0:
+            depth_tensor /= max_val
+        depth_tensor = (depth_tensor * 255.0).clamp(0, 255).to(torch.uint8)
+        depth = depth_tensor.cpu().numpy()
+
+        if color_map and color_map.lower() != "none":
+            color = color_map.lower()
+            if color not in masking.COLORMAP:
+                color = "inferno"
+            processed = cv2.applyColorMap(depth, masking.COLORMAP.index(color))[:, :, ::-1]
+        else:
+            processed = depth
+
+        if output_type == "pil":
+            mode = "RGB" if processed.ndim == 3 else "L"
+            processed = Image.fromarray(processed, mode=mode)
+        return processed

modules/control/processor.py

@@ -34,6 +34,7 @@ processors = [
     'DPT Depth Hybrid',
     'GLPN Depth',
     'Depth Anything',
+    'Depth Pro',
 ]
 
 

modules/control/processors.py

@@ -39,6 +39,7 @@ config = {
     'DPT Depth Hybrid': {'class': None, 'checkpoint': False, 'params': {}},
     'GLPN Depth': {'class': None, 'checkpoint': False, 'params': {}},
     'Depth Anything': {'class': None, 'checkpoint': True, 'load_config': {'pretrained_model_or_path': 'LiheYoung/depth_anything_vitl14' }, 'params': { 'color_map': 'inferno' }},
+    'Depth Pro': {'class': None, 'checkpoint': True, 'load_config': {'pretrained_model_or_path': 'apple/DepthPro-hf'}, 'params': {'color_map': 'inferno'}},
     # 'Midas Depth Large': {'class': MidasDetector, 'checkpoint': True, 'params': {'bg_th': 0.1, 'depth_and_normal': False}, 'load_config': {'pretrained_model_or_path': 'Intel/dpt-large', 'model_type': "dpt_large", 'filename': ''}},
     # 'Zoe Depth Zoe': {'class': ZoeDetector, 'checkpoint': True, 'params': {}},
     # 'Zoe Depth NK': {'class': ZoeDetector, 'checkpoint': True, 'params': {}, 'load_config': {'pretrained_model_or_path': 'halffried/gyre_zoedepth', 'filename': 'ZoeD_M12_NK.safetensors', 'model_type': "zoedepth_nk"}},
@@ -67,6 +68,7 @@ def delay_load_config():
     from modules.control.proc.dpt import DPTDetector
     from modules.control.proc.glpn import GLPNDetector
     from modules.control.proc.depth_anything import DepthAnythingDetector
+    from modules.control.proc.depth_pro import DepthProDetector
     config = {
         # placeholder
         'None': {},
@@ -95,6 +97,7 @@ def delay_load_config():
         'DPT Depth Hybrid': {'class': DPTDetector, 'checkpoint': False, 'params': {}},
         'GLPN Depth': {'class': GLPNDetector, 'checkpoint': False, 'params': {}},
         'Depth Anything': {'class': DepthAnythingDetector, 'checkpoint': True, 'load_config': {'pretrained_model_or_path': 'LiheYoung/depth_anything_vitl14' }, 'params': { 'color_map': 'inferno' }},
+        'Depth Pro': {'class': DepthProDetector, 'checkpoint': True, 'load_config': {'pretrained_model_or_path': 'apple/DepthPro-hf'}, 'params': {'color_map': 'inferno'}},
         # 'Midas Depth Large': {'class': MidasDetector, 'checkpoint': True, 'params': {'bg_th': 0.1, 'depth_and_normal': False}, 'load_config': {'pretrained_model_or_path': 'Intel/dpt-large', 'model_type': "dpt_large", 'filename': ''}},
         # 'Zoe Depth Zoe': {'class': ZoeDetector, 'checkpoint': True, 'params': {}},
         # 'Zoe Depth NK': {'class': ZoeDetector, 'checkpoint': True, 'params': {}, 'load_config': {'pretrained_model_or_path': 'halffried/gyre_zoedepth', 'filename': 'ZoeD_M12_NK.safetensors', 'model_type': "zoedepth_nk"}},
@@ -155,6 +158,7 @@ def update_settings(*settings):
     update(['Marigold Depth', 'params', 'denoising_steps'], settings[25])
     update(['Marigold Depth', 'params', 'ensemble_size'], settings[26])
     update(['Depth Anything', 'params', 'color_map'], settings[27])
+    update(['Depth Pro', 'params', 'color_map'], settings[28])
 
 
 class Processor():

modules/ui_control_elements.py

@@ -317,5 +317,7 @@ def create_ui_elements(units, result_txt, preview_process):
                     settings.append(gr.Slider(label="Ensemble size", minimum=1, maximum=99, step=1, value=10))
                 with gr.Accordion('Depth Anything', open=True, elem_classes=['processor-settings']):
                     settings.append(gr.Dropdown(label="Depth map", choices=['none'] + masking.COLORMAP, value='inferno'))
+                with gr.Accordion('Depth Pro', open=True, elem_classes=['processor-settings']):
+                    settings.append(gr.Dropdown(label="Depth map", choices=['none'] + masking.COLORMAP, value='inferno'))
                 for setting in settings:
                     setting.change(fn=processors.update_settings, inputs=settings, outputs=[])