Update app.py

app.py

@@ -1,47 +1,36 @@
-# fake_video_detector.py
-
-import streamlit as st
-import requests
-from PIL import Image
-from io import BytesIO
-from transformers import pipeline
-
-def extract_thumbnail_url(youtube_url):
-    """Extracts the thumbnail URL from a YouTube video link."""
-    video_id = youtube_url.split("v=")[-1].split("&")[0]
-    return f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
-
-def load_image(url):
-    """Loads an image from a URL."""
-    response = requests.get(url)
-    if response.status_code == 200:
-        return Image.open(BytesIO(response.content))
-    return None
-
-def main():
-    st.title("🔎 YouTube Fake Video Detector")
-    st.write("Enter a YouTube video link to detect if its thumbnail is AI-generated or manipulated.")
-
-    youtube_url = st.text_input("YouTube Video Link")
-
-    if youtube_url:
-        thumbnail_url = extract_thumbnail_url(youtube_url)
-        st.subheader("Thumbnail Preview:")
-        image = load_image(thumbnail_url)
-
-        if image:
-            st.image(image, caption="Video Thumbnail", use_column_width=True)
-
-            with st.spinner("Analyzing thumbnail..."):
-                # Load a pretrained model for image classification (can be replaced with a custom model)
-                model = pipeline("image-classification", model="nateraw/resnet50-oxford-flowers")
-                results = model(thumbnail_url)
-
-            st.subheader("Detection Results:")
-            for result in results:
-                st.write(f"**{result['label']}**: {result['score']*100:.2f}% confidence")
-        else:
-            st.error("Failed to load thumbnail. Please check the YouTube link.")
-
-if __name__ == "__main__":
-    main()
+import streamlit as st
+from transformers import pipeline
+from PIL import Image
+import requests
+from io import BytesIO
+
+# Title and description
+st.title("Deepfake Image & Video Detector")
+st.write("Upload an image or enter a video link to check for AI manipulations.")
+
+# Image Detection Function
+def detect_image(image_file):
+    model = pipeline("image-classification", model="microsoft/resnet-50")
+    image = Image.open(image_file)
+    results = model(image)
+    return results
+
+# Video Detection Function (Placeholder)
+def detect_video(video_link):
+    st.write("Video detection coming soon.")
+
+# Image Upload Section
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+if uploaded_image:
+    st.image(uploaded_image, caption="Uploaded Image", use_container_width=True)
+    with st.spinner("Analyzing image..."):
+        image_results = detect_image(uploaded_image)
+    st.write("### Detection Results:")
+    for result in image_results:
+        st.write(f"{result['label']}: {result['score']*100:.2f}%")
+
+# Video Link Section
+video_link = st.text_input("Enter a video link")
+if video_link:
+    st.write(f"Analyzing video at: {video_link}")
+    detect_video(video_link)