[add] image-op

.gitignore

@@ -0,0 +1 @@
+.venv

app.py

@@ -1,17 +1,66 @@
-from sentence_transformers import SentenceTransformer
 import gradio as gr
+print("Loading models...")
+from retinaface import RetinaFace
+print("retinaface loaded")
+import cv2
+print("opencv loaded")
+import numpy as np
+print("numpy loaded")
+from PIL import Image
+print("PIL loaded")
+from rembg import remove
+print("rembg loaded")
+from sentence_transformers import SentenceTransformer
+print("sentence_transformers loaded")
 
-# Load once
 image_model = SentenceTransformer("clip-ViT-B-32")
-text_model = SentenceTransformer("clip-ViT-B-32-multilingual-v1")
+print("CLIP loaded")
 
 def get_image_embedding(image):
     emb = image_model.encode(image)
     return {"embedding": emb.tolist()}
 
-def get_text_embedding(text):
-    emb = text_model.encode(text)
-    return {"embedding": emb.tolist()}
+def process_image(input_image):
+    # Convert PIL → OpenCV
+    img = cv2.cvtColor(np.array(input_image), cv2.COLOR_RGB2BGR)
+
+    # Detect faces
+    faces = RetinaFace.detect_faces(img)
+
+    if not faces:
+        return "No face detected", None
+
+    face = list(faces.values())[0]
+    x1, y1, x2, y2 = face["facial_area"]
+
+    h, w, _ = img.shape
+
+    # Expand bounding box (hair included)
+    top_expand = 0.5
+    side_expand = 0.3
+    bottom_expand = 0.2
+
+    box_width = x2 - x1
+    box_height = y2 - y1
+
+    x1_new = int(max(0, x1 - box_width * side_expand))
+    x2_new = int(min(w, x2 + box_width * side_expand))
+    y1_new = int(max(0, y1 - box_height * top_expand))
+    y2_new = int(min(h, y2 + box_height * bottom_expand))
+
+    cropped = img[y1_new:y2_new, x1_new:x2_new]
+
+    # Convert back to PIL
+    pil_image = Image.fromarray(cv2.cvtColor(cropped, cv2.COLOR_BGR2RGB))
+
+    # Background removal
+    output = remove(pil_image)
+
+    # Resize for CLIP
+    output = output.resize((224, 224))
+
+    return "Success ✅", output
+
 
 with gr.Blocks() as demo:
     with gr.Tab("Image Embedding"):
@@ -19,11 +68,25 @@ with gr.Blocks() as demo:
         img_output = gr.JSON()
         img_btn = gr.Button("Generate")
         img_btn.click(get_image_embedding, img_input, img_output)
+    
+    with gr.Tab("Face Crop & Background Removal"):
+        face_input = gr.Image(type="pil")
+        face_output = gr.Image()
+        face_status = gr.Text()
+        face_btn = gr.Button("Process")
+        face_btn.click(process_image, face_input, [face_status, face_output])
 
-    with gr.Tab("Text Embedding"):
-        text_input = gr.Textbox()
-        text_output = gr.JSON()
-        text_btn = gr.Button("Generate")
-        text_btn.click(get_text_embedding, text_input, text_output)
+    with gr.Tab("Pipe"):
+        pipe_input = gr.Image(type="pil")
+        pipe_output = gr.JSON()
+        pipe_btn = gr.Button("Run Pipe")
+        def run_pipe(img):
+            status, processed_img = process_image(img)
+            if status != "Success ✅":
+                return {"status": status, "embedding": None}
+            return get_image_embedding(processed_img)
+            
+        pipe_btn.click(run_pipe, pipe_input, pipe_output)
 
+print("Launching demo...")
 demo.launch()

requirements.txt

@@ -1,2 +1,8 @@
 sentence_transformers
-Pillow
+retina-face
+opencv-python
+pillow
+rembg
+numpy
+tf-keras
+onnxruntime