UAdd two more model options, udate the torch version to 2.5.1, and the app_local.py.

app.py

@@ -74,9 +74,11 @@ class ImagePreprocessor():
 usage_to_weights_file = {
     'General': 'BiRefNet',
     'General-HR': 'BiRefNet_HR',
+    'General-reso_512': 'BiRefNet-reso_512',
     'General-Lite': 'BiRefNet_lite',
     'General-Lite-2K': 'BiRefNet_lite-2K',
     'Matting': 'BiRefNet-matting',
+    'Matting-HR': 'BiRefNet_HR-matting',
     'Portrait': 'BiRefNet-portrait',
     'DIS': 'BiRefNet-DIS5K',
     'HRSOD': 'BiRefNet-HRSOD',
@@ -105,10 +107,12 @@ def predict(images, resolution, weights_file):
     try:
         resolution = [int(int(reso)//32*32) for reso in resolution.strip().split('x')]
     except:
-        if weights_file == 'General-HR':
+        if weights_file in ['General-HR', 'Matting-HR']:
             resolution = (2048, 2048)
-        elif weights_file == 'General-Lite-2K':
+        elif weights_file in ['General-Lite-2K']:
             resolution = (2560, 1440)
+        elif weights_file in ['General-reso_512']:
+            resolution = (512, 512)
         else:
             resolution = (1024, 1024)
         print('Invalid resolution input. Automatically changed to 1024x1024 / 2048x2048 / 2560x1440.')

app_local.py

@@ -74,9 +74,11 @@ class ImagePreprocessor():
 usage_to_weights_file = {
     'General': 'BiRefNet',
     'General-HR': 'BiRefNet_HR',
+    'General-reso_512': 'BiRefNet-reso_512',
     'General-Lite': 'BiRefNet_lite',
     'General-Lite-2K': 'BiRefNet_lite-2K',
     'Matting': 'BiRefNet-matting',
+    'Matting-HR': 'BiRefNet_HR-matting',
     'Portrait': 'BiRefNet-portrait',
     'DIS': 'BiRefNet-DIS5K',
     'HRSOD': 'BiRefNet-HRSOD',
@@ -105,10 +107,12 @@ def predict(images, resolution, weights_file):
     try:
         resolution = [int(int(reso)//32*32) for reso in resolution.strip().split('x')]
     except:
-        if weights_file == 'General-HR':
+        if weights_file in ['General-HR', 'Matting-HR']:
             resolution = (2048, 2048)
-        elif weights_file == 'General-Lite-2K':
+        elif weights_file in ['General-Lite-2K']:
             resolution = (2560, 1440)
+        elif weights_file in ['General-reso_512']:
+            resolution = (512, 512)
         else:
             resolution = (1024, 1024)
         print('Invalid resolution input. Automatically changed to 1024x1024 / 2048x2048 / 2560x1440.')
@@ -182,7 +186,7 @@ for idx_example_url, example_url in enumerate(examples_url):
     examples_url[idx_example_url].append('1024x1024')
 
 descriptions = ('Upload a picture, our model will extract a highly accurate segmentation of the subject in it.\n)'
-                 ' The resolution used in our training was `1024x1024`, thus the suggested resolution to obtain good results!\n'
+                 ' The resolution used in our training was `1024x1024`, which is the suggested resolution to obtain good results! `2048x2048` is suggested for BiRefNet_HR.\n'
                  ' Our codes can be found at https://github.com/ZhengPeng7/BiRefNet.\n'
                  ' We also maintain the HF model of BiRefNet at https://huggingface.co/ZhengPeng7/BiRefNet for easier access.')
 

requirements.txt

@@ -1,5 +1,5 @@
-torch==2.0.1
-torchvision==0.15.2
+torch==2.5.1
+torchvision
 numpy<2
 opencv-python
 tqdm