feat: enhance image handling by ensuring input is a PIL Image and updating forensic image logging

app_mcp.py

@@ -261,6 +261,16 @@ def get_consensus_label(results):
 # Update predict_image_with_json to return consensus label
 
 def predict_image_with_json(img, confidence_threshold, augment_methods, rotate_degrees, noise_level, sharpen_strength):
+    # Ensure img is a PIL Image (if it's not already)
+    if not isinstance(img, Image.Image):
+        try:
+            # If it's a numpy array, convert it
+            img = Image.fromarray(img)
+        except Exception as e:
+            logger.error(f"Error converting input image to PIL: {e}")
+            # If conversion fails, it's a critical error for the whole process
+            raise ValueError("Input image could not be converted to PIL Image.")
+
     # Initialize agents
     monitor_agent = EnsembleMonitorAgent()
     weight_manager = ModelWeightManager()
@@ -537,4 +547,4 @@ with gr.Blocks(css="#post-gallery { overflow: hidden !important;} .grid-wrap{ ov
 
 # --- MCP-Ready Launch ---
 if __name__ == "__main__":
-    demo.launch(mcp_server=True)
+    demo.launch(share=True, mcp_server=True)

utils/ela.py

@@ -1,6 +1,7 @@
 import numpy as np
 import cv2 as cv
 from time import time
+from PIL import Image
 
 def compress_jpg(image, quality):
     """Compress image using JPEG compression."""
@@ -60,4 +61,4 @@ def genELA(img, quality=75, scale=50, contrast=20, linear=False, grayscale=False
     if grayscale:
         ela = desaturate(ela)
     
-    return ela
+    return Image.fromarray(ela)

utils/hf_logger.py

@@ -13,6 +13,10 @@ HF_DATASET_NAME = "aiwithoutborders-xyz/degentic_rd0" # TODO: Replace with your
 
 def _pil_to_base64(image: Image.Image) -> str:
     """Converts a PIL Image to a base64 string."""
+    # Explicitly check if the input is a PIL Image
+    if not isinstance(image, Image.Image):
+        raise TypeError(f"Expected a PIL Image, but received type: {type(image)}")
+
     buffered = io.BytesIO()
     # Ensure image is in RGB mode before saving as JPEG
     if image.mode != 'RGB':
@@ -56,7 +60,19 @@ def log_inference_data(
         
         # Convert PIL Images to base64 strings for storage
         original_image_b64 = _pil_to_base64(original_image)
-        forensic_images_b64 = [_pil_to_base64(img) for img in forensic_images if img is not None]
+        
+        forensic_images_b64 = []
+        for img_item in forensic_images:
+            if img_item is not None:
+                if not isinstance(img_item, Image.Image):
+                    try:
+                        img_item = Image.fromarray(img_item)
+                    except Exception as e:
+                        logger.error(f"Error converting forensic image to PIL for base64 encoding: {e}")
+                        continue # Skip this image if conversion fails
+                
+                # Now img_item should be a PIL Image, safe to pass to _pil_to_base64
+                forensic_images_b64.append(_pil_to_base64(img_item))
 
         new_entry = {
             "timestamp": datetime.datetime.now().isoformat(),
@@ -64,7 +80,7 @@ def log_inference_data(
             "inference_request": inference_params,
             "model_predictions": model_predictions,
             "ensemble_output": ensemble_output,
-            "forensic_outputs": forensic_images_b64,
+            "forensic_outputs": forensic_images_b64, # List of base64 image strings
             "agent_monitoring_data": agent_monitoring_data,
             "human_feedback": human_feedback if human_feedback is not None else {}
         }