accepting image blob inputs

app.py

@@ -1,4 +1,3 @@
-# app.py
 import gradio as gr
 import torch
 import torch.nn as nn
@@ -6,7 +5,7 @@ import timm
 import cv2
 import numpy as np
 from PIL import Image
-import matplotlib.pyplot as plt
+from io import BytesIO
 import os
 
 # ===============================
@@ -46,9 +45,9 @@ def depth_to_normal(depth):
     return normal
 
 # ===============================
-# MAIN PROCESSING FUNCTION
+# CORE PROCESSING FUNCTION
 # ===============================
-def process_saree(base_image: Image.Image, pattern_image: Image.Image):
+def _process_saree_core(base_image: Image.Image, pattern_image: Image.Image):
     # Convert base to numpy
     img_pil = base_image.convert("RGB")
     img_np = np.array(img_pil)
@@ -136,16 +135,39 @@ def process_saree(base_image: Image.Image, pattern_image: Image.Image):
 
     return Image.fromarray(pattern_rgba, mode="RGBA")
 
+# ===============================
+# WRAPPER: ACCEPT BLOBS FROM DATA ARRAY
+# ===============================
+def process_saree(data):
+    """
+    Accepts [base_blob, pattern_blob] as bytes (e.g., API POST with blobs)
+    """
+    if not isinstance(data, (list, tuple)) or len(data) != 2:
+        raise ValueError("Expected an array with two elements: [base_blob, pattern_blob]")
+
+    base_blob, pattern_blob = data
+
+    if isinstance(base_blob, bytes):
+        base_image = Image.open(BytesIO(base_blob)).convert("RGBA")
+    else:
+        raise ValueError("Base image must be provided as bytes")
+
+    if isinstance(pattern_blob, bytes):
+        pattern_image = Image.open(BytesIO(pattern_blob)).convert("RGBA")
+    else:
+        raise ValueError("Pattern image must be provided as bytes")
+
+    return _process_saree_core(base_image, pattern_image)
+
 # ===============================
 # GRADIO INTERFACE
 # ===============================
 iface = gr.Interface(
     fn=process_saree,
-    inputs=[gr.Image(type="pil", label="Base Saree Image"),
-            gr.Image(type="pil", label="Pattern Image")],
+    inputs=gr.Dataframe(headers=["Base Blob", "Pattern Blob"], type="array"),
     outputs=gr.Image(type="pil", label="Final Saree Output"),
-    title="Saree Depth + Pattern Draping",
-    description="Upload base saree & pattern images to get depth-aware draped output (transparent edges, no black outline)."
+    title="Saree Depth + Pattern Draping (Blob API Compatible)",
+    description="Send image blobs as array [base, pattern] or use Gradio UI for testing."
 )
 
 if __name__ == "__main__":