every

handler.py

@@ -15,12 +15,10 @@ from gfpgan import GFPGANer
 logging.basicConfig(level=logging.DEBUG)
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
-
 logger.debug("📦 [INIT] Importing GFPGAN handler module...")
 
-
 # ======================================================
-#  GFPGAN MODEL DOWNLOAD CONFIG
+#  GFPGAN MODEL URL
 # ======================================================
 MODEL_URL = "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth"
 MODEL_NAME = "GFPGANv1.4.pth"
@@ -39,34 +37,33 @@ class EndpointHandler:
         logger.debug(f"🔗 [MODEL] Expected model path: {model_path}")
 
         # ------------------------------------------------------
-        # Download model if not found
+        # Download model if missing
         # ------------------------------------------------------
         if not os.path.exists(model_path):
             try:
-                logger.debug(f"📥 [DOWNLOAD] Model not found locally. Downloading from {MODEL_URL}")
+                logger.debug(f"📥 [DOWNLOAD] Model not found locally — fetching from {MODEL_URL}")
                 r = requests.get(MODEL_URL, stream=True)
                 r.raise_for_status()
                 with open(model_path, "wb") as f:
                     for chunk in r.iter_content(chunk_size=8192):
                         if chunk:
                             f.write(chunk)
-                logger.debug("✅ [MODEL] Downloaded GFPGAN model successfully.")
+                logger.debug("✅ [MODEL] Downloaded GFPGAN weights successfully.")
             except Exception as e:
                 logger.error(f"💥 [ERROR] Failed to download GFPGAN weights: {e}")
                 raise
 
         # ------------------------------------------------------
-        # Initialize GFPGANer just like the official Gradio demo
+        # Initialize GFPGANer (same as official Gradio demo)
         # ------------------------------------------------------
         try:
-            logger.debug("🧠 [MODEL] Initializing GFPGANer (v1.4, upscale=2, no background upsampler)...")
+            logger.debug("🧠 [MODEL] Initializing GFPGANer (upscale=2, arch='clean')...")
             self.restorer = GFPGANer(
                 model_path=model_path,
-                upscale=2,                   # Matches Gradio demo “Rescaling factor: 2”
+                upscale=2,                   # Rescaling factor = 2
                 arch="clean",
                 channel_multiplier=2,
-                bg_upsampler=None,
-                version="1.4",
+                bg_upsampler=None
             )
             logger.debug("✅ [MODEL] GFPGAN model initialized successfully.")
         except Exception as e:
@@ -78,10 +75,10 @@ class EndpointHandler:
     # ======================================================
     def __call__(self, data):
         logger.debug("⚙️ [INFER] Starting inference...")
-        logger.debug(f"📥 Incoming data keys: {list(data.keys())}")
+        logger.debug(f"📥 Incoming data type: {type(data)}")
 
         # ------------------------------------------------------
-        # Handle both raw bytes and JSON base64 inputs
+        # Handle both JSON base64 and raw bytes
         # ------------------------------------------------------
         try:
             if isinstance(data, dict) and "inputs" in data:
@@ -99,7 +96,7 @@ class EndpointHandler:
             return {"error": f"Invalid input: {e}"}
 
         # ------------------------------------------------------
-        # Load and convert image
+        # Decode image
         # ------------------------------------------------------
         try:
             img_np = np.array(Image.open(io.BytesIO(image_bytes)).convert("RGB"))
@@ -109,29 +106,29 @@ class EndpointHandler:
             return {"error": f"Image loading failed: {e}"}
 
         # ------------------------------------------------------
-        # Perform face restoration
+        # Run GFPGAN restoration
         # ------------------------------------------------------
         try:
             cropped_faces, restored_faces, restored_img = self.restorer.enhance(
                 img_np,
                 has_aligned=False,
                 only_center_face=False,
-                paste_back=True,  # ⬅️ Matches web demo behavior
+                paste_back=True  # Matches GFPGAN web demo
             )
-            logger.debug("✅ [RESTORE] Face restoration complete.")
+            logger.debug("✅ [RESTORE] Face restoration completed successfully.")
         except Exception as e:
             logger.error(f"💥 [ERROR] GFPGAN enhancement failed: {e}")
             return {"error": f"Enhancement failed: {e}"}
 
         # ------------------------------------------------------
-        # Encode restored image to base64 for response
+        # Encode result as base64 PNG
         # ------------------------------------------------------
         try:
-            _, buffer = cv2.imencode(".png", restored_img[:, :, ::-1])  # BGR → RGB
+            _, buffer = cv2.imencode(".png", restored_img[:, :, ::-1])  # BGR→RGB
             img_base64 = base64.b64encode(buffer).decode("utf-8")
-            logger.debug("📤 [ENCODE] Successfully encoded restored image.")
+            logger.debug("📤 [ENCODE] Encoded restored image successfully.")
             return {"image": img_base64}
         except Exception as e:
-            logger.error(f"💥 [ERROR] Failed to encode restored image: {e}")
+            logger.error(f"💥 [ERROR] Failed to encode image: {e}")
             return {"error": f"Encoding failed: {e}"}
 

requirements.txt

@@ -2,8 +2,9 @@ torch==2.1.0
 torchvision==0.16.0
 gfpgan==1.3.8
 basicsr==1.4.2
-numpy==1.26.4
-Pillow>=10.0.0
+facexlib==0.3.0
 opencv-python
 requests
+numpy
+Pillow