Update controlnet_module.py

controlnet_module.py

@@ -910,7 +910,7 @@ class ControlNetProcessor:
                 best_mask_idx = 0
                 best_score = -1
                 
-                for i, mask_np in enumerate(all_masks_original):
+                for i, mask_np in enumerate(all_masks_crop):
                     mask_max = mask_np.max()
                     
                     # Grundlegende Filterung
@@ -925,14 +925,15 @@ class ControlNetProcessor:
                     if np.sum(mask_binary) == 0:
                         print(f"   ❌ Maske {i+1}: Keine Pixel nach Threshold {adaptive_threshold:.3f}")
                         continue
-                    
+                        
+                    #Maskenfläche in Pixeln (Crop-Grösse)
                     mask_area_pixels = np.sum(mask_binary) 
 
                     # ============================================================
                     #        SPEZIALHEURISTIK 
                     # ============================================================
 
-                    print(f"   🔍 Analysiere Maske {i+1} mit GESICHTS-HEURISTIK")
+                    print(f"   🔍 Analysiere Maske {i+1} auf Crop-Größe")
         
                     # 1. FLÄCHENBASIERTE BEWERTUNG (40%)
                     area_ratio = mask_area_pixels / bbox_area
@@ -983,9 +984,9 @@ class ControlNetProcessor:
                         print(f"       • Kompaktheits-Score: {compactness_score:.3f}")
         
                     # 3. BBOX-ÜBERLAPPUNG (20%)
-                    bbox_mask = np.zeros((original_image.height, original_image.width), dtype=np.uint8)
-                    
-                    bbox_mask[original_bbox[1]:original_bbox[3], original_bbox[0]:original_bbox[2]] = 1
+                    bbox_mask = np.zeros((image.height, image.width), dtype=np.uint8)
+
+                    bbox_mask[y1:y2, x1:x2] = 1
                     
                     overlap = np.sum(mask_binary & bbox_mask)