Cnet (#20)

* ini

* i

* i

* i

* i

* i

* i

* Update preprocessor_normalbae.py

* i

* i

* i

* i

* Update README.md

* i

* Update preprocessor_depth.py

* Update shared.py

* Update devices.py

* i

* i

* i

* i

* i

* i

* Update README.md

* i

* Update README.md

* i

* Update annotator_path.py

* i

* i

* Update preprocessor_meta.py

extensions-builtin/forge_preprocessor_normalbae/scripts/preprocessor_normalbae.py

@@ -0,0 +1,72 @@
+from modules_forge.shared import Preprocessor, PreprocessorParameter, preprocessor_dir, load_file_from_url, add_preprocessor
+from modules_forge.forge_util import resize_image_with_pad
+
+import types
+import torch
+import numpy as np
+
+from einops import rearrange
+from annotator.normalbae.models.NNET import NNET
+from annotator.normalbae import load_checkpoint
+from torchvision import transforms
+
+
+class PreprocessorNormalBae(Preprocessor):
+    def __init__(self):
+        super().__init__()
+        self.name = 'normalbae'
+        self.tag = 'NormalMap'
+        self.slider_resolution = PreprocessorParameter(label='Resolution', minimum=128, maximum=2048, value=512, step=8, visible=True)
+        self.slider_1 = PreprocessorParameter(visible=False)
+        self.slider_2 = PreprocessorParameter(visible=False)
+        self.slider_3 = PreprocessorParameter(visible=False)
+        self.show_control_mode = True
+        self.do_not_need_model = False
+
+    def load_model(self):
+        if self.model_patcher is not None:
+            return
+
+        model_path = load_file_from_url(
+            "https://huggingface.co/lllyasviel/Annotators/resolve/main/scannet.pt",
+            model_dir=preprocessor_dir)
+
+        args = types.SimpleNamespace()
+        args.mode = 'client'
+        args.architecture = 'BN'
+        args.pretrained = 'scannet'
+        args.sampling_ratio = 0.4
+        args.importance_ratio = 0.7
+        model = NNET(args)
+        model = load_checkpoint(model_path, model)
+        self.norm = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+
+        self.model_patcher = self.setup_model_patcher(model)
+
+    def __call__(self, input_image, resolution, slider_1=None, slider_2=None, slider_3=None, **kwargs):
+        input_image, remove_pad = resize_image_with_pad(input_image, resolution)
+
+        self.load_model()
+
+        self.move_all_model_patchers_to_gpu()
+
+        assert input_image.ndim == 3
+        image_normal = input_image
+
+        with torch.no_grad():
+            image_normal = self.send_tensor_to_model_device(torch.from_numpy(image_normal))
+            image_normal = image_normal / 255.0
+            image_normal = rearrange(image_normal, 'h w c -> 1 c h w')
+            image_normal = self.norm(image_normal)
+
+            normal = self.model_patcher.model(image_normal)
+            normal = normal[0][-1][:, :3]
+            normal = ((normal + 1) * 0.5).clip(0, 1)
+
+            normal = rearrange(normal[0], 'c h w -> h w c').cpu().numpy()
+            normal_image = (normal * 255.0).clip(0, 255).astype(np.uint8)
+
+        return remove_pad(normal_image)
+
+
+add_preprocessor(PreprocessorNormalBae)