Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from PIL import Image
+import torch
+from transformers import pipeline
+
+# Load the pre-trained AI image detector model
+detector = pipeline(
+    "image-classification",
+    model="umm-maybe/AI-image-detector",
+    device=0 if torch.cuda.is_available() else -1  # Use GPU if available
+)
+
+def detect_image(image):
+    if image is None:
+        return "Please upload an image."
+    
+    # Run inference
+    results = detector(image)
+    
+    # Get top prediction
+    top_pred = results[0]
+    label = top_pred['label']
+    prob = top_pred['score'] * 100
+    
+    # Format output
+    if label == 'real':
+        return f"Real Image (Confidence: {prob:.2f}%)"
+    else:
+        return f"AI-Generated Image (Confidence: {prob:.2f}%)"
+
+# Create Gradio interface
+with gr.Blocks(title="AI Image Detector – CBSE Board Project 2025-26") as demo:
+    gr.Markdown("# AI Image Detector by [Dipika Singh, Rashvi Singh, Rupanjali Rai, Khusboo Yadav] – CBSE Board Project 2025-26")
+    gr.Markdown("Upload any image → Instantly know if it's Real or AI-Generated!")
+    
+    with gr.Row():
+        image_input = gr.Image(type="pil", label="Drop Image Here - or - Click to Upload")
+        output = gr.Textbox(label="Detection Result")
+    
+    with gr.Row():
+        submit_btn = gr.Button("Submit")
+        clear_btn = gr.Button("Clear")
+    
+    # Event handlers
+    submit_btn.click(fn=detect_image, inputs=image_input, outputs=output)
+    clear_btn.click(fn=lambda: (None, "Upload an image to start!"), inputs=None, outputs=[image_input, output])
+
+if __name__ == "__main__":
+    demo.launch()