Update app_3.py

app_3.py

@@ -150,7 +150,7 @@ vae = AutoencoderKL.from_pretrained(sd15_name, subfolder="vae")
 unet = UNet2DConditionModel.from_pretrained(sd15_name, subfolder="unet")
 # Load model directly
 from transformers import AutoModelForImageSegmentation
-rmbg = AutoModelForImageSegmentation.from_pretrained("briaai/RMBG-1.4", trust_remote_code=True)
+rmbg = AutoModelForImageSegmentation.from_pretrained("briaai/BRIA-RMBG-2.0", trust_remote_code=True)
 rmbg = rmbg.to(device=device, dtype=torch.float32)  # Keep this as float32
 
 # remove bg
@@ -1028,17 +1028,17 @@ def process_image(input_image, input_text):
             rgba = np.dstack((img, alpha)).astype(np.uint8)
             
             # Crop to mask bounds to minimize image size
-            y_indices, x_indices = np.where(first_mask)
-            y_min, y_max = y_indices.min(), y_indices.max()
-            x_min, x_max = x_indices.min(), x_indices.max()
+            # y_indices, x_indices = np.where(first_mask)
+            # y_min, y_max = y_indices.min(), y_indices.max()
+            # x_min, x_max = x_indices.min(), x_indices.max()
             
             # Crop the RGBA image
-            cropped_rgba = rgba[y_min:y_max+1, x_min:x_max+1]
+            #cropped_rgba = rgba[y_min:y_max+1, x_min:x_max+1]
             
             # Set extracted foreground for mask mover
             # mask_mover.set_extracted_fg(cropped_rgba)
             
-            return annotated_frame, cropped_rgba, gr.update(visible=False), gr.update(visible=False)
+            return annotated_frame, rgba, gr.update(visible=False), gr.update(visible=False)
 
     
     else: