rename to point_labels

README.md

@@ -103,10 +103,11 @@ result = response.json()
 
     // SAM2 COMPATIBLE: Point-based prompts
     "points": [[[x1, y1]], [[x2, y2]]],  // Points for each object
-    "labels": [[1], [1]],  // Labels for each point (1=foreground, 0=background)
+    "point_labels": [[1], [1]],  // Labels for each point (1=foreground, 0=background)
 
     // SAM2 COMPATIBLE: Bounding box prompts
     "boxes": [[x1, y1, x2, y2], [x1, y1, x2, y2]],  // Bounding boxes
+    "box_labels": [1, 0],  // Labels for each box (1=positive, 0=negative/exclude)
 
     "multimask_output": false,  // Optional, defaults to False
     "confidence_threshold": 0.5  // Optional, minimum confidence for returned masks

app.py

@@ -241,8 +241,9 @@ def sam2_compatible_api(data):
         image_b64 = inputs_data.get("image")
         text_prompts = inputs_data.get("text_prompts", [])
         input_points = inputs_data.get("points", [])
-        input_labels = inputs_data.get("labels", [])
+        input_point_labels = inputs_data.get("point_labels", [])
         input_boxes = inputs_data.get("boxes", [])
+        input_box_labels = inputs_data.get("box_labels", [])
         confidence_threshold = inputs_data.get("confidence_threshold", 0.5)
         vectorize = inputs_data.get("vectorize", False)
         simplify_epsilon = inputs_data.get("simplify_epsilon", 2.0)
@@ -252,14 +253,17 @@ def sam2_compatible_api(data):
             return {"error": "No image provided", "success": False}
 
         has_text = bool(text_prompts)
-        has_points = bool(input_points and input_labels)
+        has_points = bool(input_points and input_point_labels)
         has_boxes = bool(input_boxes)
 
         if not (has_text or has_points or has_boxes):
-            return {"error": "Must provide at least one prompt type: text_prompts, points+labels, or boxes", "success": False}
+            return {"error": "Must provide at least one prompt type: text_prompts, points+point_labels, or boxes", "success": False}
 
-        if has_points and len(input_points) != len(input_labels):
-            return {"error": "Number of points and labels must match", "success": False}
+        if has_points and len(input_points) != len(input_point_labels):
+            return {"error": "Number of points and point_labels must match", "success": False}
+
+        if has_boxes and input_box_labels and len(input_boxes) != len(input_box_labels):
+            return {"error": "Number of boxes and box_labels must match", "success": False}
 
         # Decode image
         if image_b64.startswith('data:image'):
@@ -313,9 +317,9 @@ def sam2_compatible_api(data):
         # Process visual prompts (boxes and/or points) - can be combined in a single call
         if has_boxes or has_points:
             combined_boxes = input_boxes if has_boxes else None
-            combined_box_labels = inputs_data.get("box_labels", [1] * len(input_boxes)) if has_boxes else None
+            combined_box_labels = input_box_labels if (has_boxes and input_box_labels) else ([1] * len(input_boxes) if has_boxes else None)
             combined_points = input_points if has_points else None
-            combined_point_labels = input_labels if has_points else None
+            combined_point_labels = input_point_labels if has_points else None
 
             results = sam3_inference(
                 image=image,
@@ -506,7 +510,7 @@ response = requests.post(
             "boxes": [[50, 50, 150, 150]],  # Bounding box
             "box_labels": [0],  # 0=negative (exclude this area)
             "points": [[200, 200]],  # Point prompt
-            "labels": [1],  # 1=positive point
+            "point_labels": [1],  # 1=positive point
             "confidence_threshold": 0.5
         }
     }
@@ -541,7 +545,7 @@ result = response.json()
 
     // SAM2 COMPATIBLE: Point-based prompts (can be combined with text/boxes)
     "points": [[x1, y1], [x2, y2]],  // Individual points (not nested arrays)
-    "labels": [1, 0],  // Labels for each point (1=positive/foreground, 0=negative/background)
+    "point_labels": [1, 0],  // Labels for each point (1=positive/foreground, 0=negative/background)
 
     // SAM2 COMPATIBLE: Bounding box prompts (can be combined with text/points)
     "boxes": [[x1, y1, x2, y2], [x3, y3, x4, y4]],  // Bounding boxes