Update app.py

app.py

@@ -1,99 +1,48 @@
 import gradio as gr
 from transformers import pipeline
-from PIL import Image, ExifTags
-import cv2
+from PIL import Image
 import numpy as np
 
-# ===== 1. Load 3 Public Models =====
+# ====== MODEL LIST ======
 model_ids = [
-    "umm-maybe/AI-image-detector",   # Detektor umum
-    "vikhyatk/moondream2",          # Model multimodal
-    "microsoft/resnet-50"           # Baseline visual classifier
+    "vikhyatk/moondream2",          # butuh trust_remote_code=True
+    "umm-maybe/synthetic-image-detector", 
+    "falconsai/nsfw_image_detection"
 ]
 
-detectors = [pipeline("image-classification", model=m) for m in model_ids]
+# Load semua model dengan trust_remote_code
+detectors = [pipeline("image-classification", model=m, trust_remote_code=True) for m in model_ids]
 
-# ===== 2. Fungsi Forensik Manual =====
-def forensic_analysis(img: Image.Image):
-    img_cv = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
-    
-    # Blur (Laplacian variance)
-    blur_var = cv2.Laplacian(img_cv, cv2.CV_64F).var()
-    
-    # Noise (High-pass filter std)
-    gray = cv2.cvtColor(img_cv, cv2.COLOR_BGR2GRAY)
-    noise = cv2.Laplacian(gray, cv2.CV_64F).std()
-    
-    # High-frequency ratio (FFT)
-    f = np.fft.fft2(gray)
-    fshift = np.fft.fftshift(f)
-    magnitude_spectrum = np.abs(fshift)
-    high_freq_ratio = np.sum(magnitude_spectrum > 50) / magnitude_spectrum.size
-    
-    # Metadata kamera
-    exif_data = img.getexif()
-    has_exif = len(exif_data) > 0
-    
-    forensic_score = 0
-    if blur_var > 500: forensic_score += 20
-    if noise > 10: forensic_score += 20
-    if high_freq_ratio > 0.3: forensic_score += 20
-    if has_exif: forensic_score += 40
-    
-    return {
-        "blur": round(blur_var, 2),
-        "noise": round(noise, 2),
-        "high_freq_ratio": round(high_freq_ratio, 3),
-        "has_exif": has_exif,
-        "forensic_score": forensic_score
-    }
-
-# ===== 3. Fungsi Prediksi Gabungan =====
-def detect_ai(image):
-    votes = []
+def detect_image(img: Image.Image):
+    results = []
     scores = []
-    
-    # Jalankan semua model
+
     for det in detectors:
-        preds = det(image)
-        label = preds[0]['label'].lower()
-        score = preds[0]['score']
-        
-        if "ai" in label or "fake" in label or "artificial" in label:
-            votes.append("AI")
-        else:
-            votes.append("Real")
-        scores.append(score)
-    
-    # Analisis forensik
-    forensic = forensic_analysis(image)
-    
-    # Voting
-    ai_votes = votes.count("AI")
-    real_votes = votes.count("Real")
-    
-    if ai_votes > real_votes:
-        final = "AI"
-    elif real_votes > ai_votes:
-        final = "Real"
+        try:
+            out = det(img)
+            # Ambil label & skor tertinggi
+            top = max(out, key=lambda x: x["score"])
+            results.append(f"{det.model.config.name_or_path}: {top['label']} ({top['score']:.2f})")
+            scores.append(top["score"] if "ai" in top["label"].lower() or "fake" in top["label"].lower() or "artificial" in top["label"].lower() else 1 - top["score"])
+        except Exception as e:
+            results.append(f"Error {det.model.config.name_or_path}: {str(e)}")
+
+    if scores:
+        avg_score = np.mean(scores) * 100
     else:
-        # Gunakan forensic sebagai tie-breaker
-        final = "Real" if forensic["forensic_score"] > 50 else "AI"
-    
-    return {
-        "Hasil Deteksi": final,
-        "Voting Model": votes,
-        "Confidence Scores": scores,
-        "Forensik": forensic
-    }
+        avg_score = 0
+
+    verdict = "AI" if avg_score > 50 else "Asli"
+
+    return f"🔎 Hasil Deteksi: {verdict}\nPersentase AI: {avg_score:.2f}%\n\nDetail:\n" + "\n".join(results)
 
-# ===== 4. Gradio UI =====
+# ====== GRADIO UI ======
 demo = gr.Interface(
-    fn=detect_ai,
+    fn=detect_image,
     inputs=gr.Image(type="pil"),
-    outputs="json",
-    title="AI vs Real Image Detector (Ensemble + Forensic)",
-    description="Menggunakan 3 model publik + analisis forensik (blur, noise, frekuensi, metadata)."
+    outputs="text",
+    title="AI vs Real Image Detector",
+    description="Upload foto untuk mendeteksi apakah itu AI-generated atau asli. Menggunakan 3 model publik dengan trust_remote_code=True."
 )
 
 if __name__ == "__main__":