Update app.py

app.py

@@ -1,14 +1,12 @@
 from fastapi import FastAPI, Response
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
-from PIL import Image
 import io
 import base64
 import re
 import numpy as np
-import cv2 # This is the OpenCV library
+import cv2
 
-# Pydantic model to expect two base64 strings
 class InpaintRequest(BaseModel):
     image_data: str
     mask_data: str
@@ -23,40 +21,34 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# --- NO HEAVY MODEL TO LOAD! THE APP STARTS INSTANTLY. ---
 print("OpenCV Magic Eraser API is ready!")
 
 def base64_to_cv2_image(base64_string):
-    """Decodes a base64 string into an OpenCV image (numpy array)."""
     base64_data = re.sub('^data:image/.+;base64,', '', base64_string)
     img_data = base64.b64decode(base64_data)
     np_arr = np.frombuffer(img_data, np.uint8)
-    # cv2.imdecode reads an image from the buffer
     return cv2.imdecode(np_arr, cv2.IMREAD_COLOR)
 
 @app.post("/inpaint")
 async def inpaint_image(request: InpaintRequest):
     try:
-        # 1. Decode base64 strings into OpenCV images
         init_image = base64_to_cv2_image(request.image_data)
         
-        # For the mask, we need it in grayscale
-        mask_image_color = base64_to_cv2_image(request.mask_data)
-        mask_image_gray = cv2.cvtColor(mask_image_color, cv2.COLOR_BGR2GRAY)
-        
-        # The inpainting algorithm needs a binary mask (black and white)
-        # We'll make any non-black pixel white
-        _, mask = cv2.threshold(mask_image_gray, 1, 255, cv2.THRESH_BINARY)
+        # --- SIMPLIFIED MASK HANDLING ---
+        # The mask is now perfectly black and white from the frontend.
+        # We just need to convert it to grayscale for the algorithm.
+        mask_color = base64_to_cv2_image(request.mask_data)
+        mask_gray = cv2.cvtColor(mask_color, cv2.COLOR_BGR2GRAY)
 
         print("Received images. Starting high-speed inpainting...")
         
-        # 2. Run the high-speed OpenCV inpainting algorithm
-        # cv2.INPAINT_NS is based on Navier-Stokes, giving high-quality results
-        inpainted_image = cv2.inpaint(init_image, mask, 3, cv2.INPAINT_NS)
+        # Run the high-speed OpenCV inpainting algorithm
+        # The mask is already perfect, no thresholding needed.
+        inpainted_image = cv2.inpaint(init_image, mask_gray, 3, cv2.INPAINT_NS)
         
-        print("Inpainting complete in milliseconds.")
+        print("Inpainting complete.")
 
-        # 3. Convert the result back to a base64 string to send to the frontend
+        # Convert the result back to a base64 string
         _, buffer = cv2.imencode('.png', inpainted_image)
         img_str = base64.b64encode(buffer).decode("utf-8")