Add BiRefNet_dynamic for test and arbitary input size for it.

app.py

@@ -60,8 +60,9 @@ def FB_blur_fusion_foreground_estimator(image, F, B, alpha, r=90):
 
 class ImagePreprocessor():
     def __init__(self, resolution: Tuple[int, int] = (1024, 1024)) -> None:
+        # Input resolution is on WxH.
         self.transform_image = transforms.Compose([
-            transforms.Resize(resolution),
+            transforms.Resize(resolution[::-1]),
             transforms.ToTensor(),
             transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
         ])
@@ -84,7 +85,8 @@ usage_to_weights_file = {
     'HRSOD': 'BiRefNet-HRSOD',
     'COD': 'BiRefNet-COD',
     'DIS-TR_TEs': 'BiRefNet-DIS5K-TR_TEs',
-    'General-legacy': 'BiRefNet-legacy'
+    'General-legacy': 'BiRefNet-legacy',
+    'General-dynamic': 'BiRefNet_dynamic',
 }
 
 birefnet = AutoModelForImageSegmentation.from_pretrained('/'.join(('zhengpeng7', usage_to_weights_file['General'])), trust_remote_code=True)
@@ -114,7 +116,11 @@ def predict(images, resolution, weights_file):
         elif weights_file in ['General-reso_512']:
             resolution = (512, 512)
         else:
-            resolution = (1024, 1024)
+            if weights_file in ['General-dynamic']:
+                resolution = None
+                print('Using the original size (div by 32) for inference.')
+            else:
+                resolution = (1024, 1024)
         print('Invalid resolution input. Automatically changed to 1024x1024 / 2048x2048 / 2560x1440.')
 
     if isinstance(images, list):
@@ -141,6 +147,10 @@ def predict(images, resolution, weights_file):
 
         image = image_ori.convert('RGB')
         # Preprocess the image
+        if resolution is None:
+            resolution_div_by_32 = [int(int(reso)//32*32) for reso in image.size]
+            if resolution_div_by_32 != resolution:
+                resolution = resolution_div_by_32
         image_preprocessor = ImagePreprocessor(resolution=tuple(resolution))
         image_proc = image_preprocessor.proc(image)
         image_proc = image_proc.unsqueeze(0)