Update app.py

app.py

@@ -1,112 +1,89 @@
 import gradio as gr
-from transformers import pipeline, CLIPProcessor, CLIPModel
+from transformers import pipeline, AutoImageProcessor, SiglipForImageClassification
+import cv2, tempfile, os
 from PIL import Image
-import torch
-import cv2
-import os
-import tempfile
 
 # Load models
-clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
-clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
-news_model = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news")
-# AI Image Detection
-def analyze_image(image):
-    inputs = clip_processor(text=["a real photo", "an AI-generated image"], images=image, return_tensors="pt", padding=True)
-    outputs = clip_model(**inputs)
-    logits_per_image = outputs.logits_per_image
-    probs = logits_per_image.softmax(dim=1).tolist()[0]
-    prediction = "AI-generated" if probs[1] > probs[0] else "Real"
-    confidence = round(max(probs) * 100, 2)
+img_model = SiglipForImageClassification.from_pretrained("prithivMLmods/open-deepfake-detection")
+img_proc  = AutoImageProcessor.from_pretrained("prithivMLmods/open-deepfake-detection")
+news_model = pipeline("text-classification", model="jy46604790/Fake-News-Bert-Detect")
 
-    explanation = (
-        "The image strongly suggests AI generation. Look for smooth textures, perfect symmetry, "
-        "and overly clean details — signs of AI creation."
-        if prediction == "AI-generated"
-        else "This image appears authentic based on texture, lighting, and organic imperfections. "
-             "No major AI traits were detected."
+# Image analysis
+def analyze_image(image):
+    inputs = img_proc(images=image, return_tensors="pt")
+    outputs = img_model(**inputs)
+    probs = outputs.logits.softmax(dim=1).tolist()[0]
+    pred = "Fake (AI-generated)" if probs[0] > probs[1] else "Real"
+    conf = round(max(probs)*100,2)
+    expl = (
+        "⚠️ Likely AI-generated due to visual artifacts or unnatural features."
+        if pred.startswith("Fake")
+        else "✅ Appears authentic with realistic textures and lighting."
     )
-    return f"Prediction: {prediction} ({confidence}%)", explanation
+    return f"{pred} ({conf}%)", expl
 
-# Fake News Detection
+# News analysis
 def analyze_news(text):
-    result = news_model(text)[0]
-    label = result["label"]
-    score = round(result["score"] * 100, 2)
-
-    pred = "Fake News" if label == "LABEL_0" else "Real News"
-    explanation = (
-        "⚠️ This article likely contains misinformation or fabricated facts."
-        if label == "LABEL_0"
-        else "✅ The article seems factual and based on credible information."
+    res = news_model(text)[0]
+    label = res['label']
+    score = round(res['score']*100,2)
+    pred = "Fake News" if label=="LABEL_0" else "Real News"
+    expl = (
+        "⚠️ This article likely contains misinformation or misleading claims."
+        if pred=="Fake News"
+        else "✅ The text appears credible and factually consistent."
     )
-
-    return f"Prediction: {pred} ({score}%)", explanation
-
-# Video Analysis
-def analyze_video(video_file):
-    temp_dir = tempfile.mkdtemp()
-    video_path = os.path.join(temp_dir, "input.mp4")
-    with open(video_path, "wb") as f:
-        f.write(video_file.read())
-
-    cap = cv2.VideoCapture(video_path)
-    fps = cap.get(cv2.CAP_PROP_FPS)
-    frame_rate = int(fps) if fps > 0 else 1
-
-    results = []
-    frame_count = 0
-
-    while cap.isOpened():
-        success, frame = cap.read()
-        if not success:
-            break
-
-        if frame_count % frame_rate == 0:
-            pil_image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
-            result, _ = analyze_image(pil_image)
-            results.append(result)
-
-        frame_count += 1
-
+    return f"{pred} ({score}%)", expl
+
+# Video analysis (≤10s)
+def analyze_video(file):
+    tmp = tempfile.mkdtemp()
+    path = os.path.join(tmp, "vid.mp4")
+    with open(path,"wb") as f: f.write(file.read())
+
+    cap = cv2.VideoCapture(path)
+    fps = cap.get(cv2.CAP_PROP_FPS) or 1
+    frame_idx, ai_detected = 0, False
+
+    while True:
+        ret, frame = cap.read()
+        if not ret or frame_idx/fps>10: break
+        if frame_idx % int(fps)==0:
+            img = Image.fromarray(cv2.cvtColor(frame,cv2.COLOR_BGR2RGB))
+            pred, _ = analyze_image(img)
+            if "Fake" in pred:
+                ai_detected = True
+                break
+        frame_idx += 1
     cap.release()
 
-    if any("AI-generated" in r for r in results):
-        return "Prediction: AI-generated content detected in video.", (
-            "The video includes frames that strongly resemble AI-generated imagery. "
-            "Check for smooth rendering, cartoonish features, or lack of natural flaws."
-        )
-    else:
-        return "Prediction: Video looks real.", (
-            "No strong signs of AI generation were detected in any frame. "
-            "Visuals appear natural and consistent with real-world content."
-        )
+    pred = "Video likely contains AI-generated content" if ai_detected else "Video appears authentic"
+    expl = (
+        "⚠️ At least one frame shows AI generation traits."
+        if ai_detected
+        else "✅ No strong signs of AI generation across frames."
+    )
+    return pred, expl
 
-# Gradio App
 with gr.Blocks() as demo:
-    gr.Markdown("## 🧠 Fake News & AI Media Detector (Image / News / Video)")
-
+    gr.Markdown("## 🤖 Real-Time AI & Fake News Validator")
     with gr.Row():
         with gr.Column():
-            img_input = gr.Image(label="Upload Image")
-            img_btn = gr.Button("Analyze Image")
-            img_result = gr.Textbox(label="Image Result")
-            img_explanation = gr.Textbox(label="Image Explanation")
+            img = gr.Image(type="pil")
+            btn_img = gr.Button("Analyze Image")
+            out_img, expl_img = gr.Textbox(), gr.Textbox()
+            btn_img.click(analyze_image, inputs=img, outputs=[out_img, expl_img])
 
         with gr.Column():
-            news_input = gr.Textbox(label="Paste News Headline or Text")
-            news_btn = gr.Button("Analyze News")
-            news_result = gr.Textbox(label="News Result")
-            news_explanation = gr.Textbox(label="News Explanation")
+            txt = gr.Textbox(lines=4, placeholder="Paste news or claim text")
+            btn_txt = gr.Button("Analyze News")
+            out_txt, expl_txt = gr.Textbox(), gr.Textbox()
+            btn_txt.click(analyze_news, inputs=txt, outputs=[out_txt, expl_txt])
 
     with gr.Row():
-        video_input = gr.File(label="Upload Short Video (≤ 10 sec, MP4)", file_types=[".mp4"])
-        video_btn = gr.Button("Analyze Video")
-        video_result = gr.Textbox(label="Video Result")
-        video_explanation = gr.Textbox(label="Video Explanation")
-
-    img_btn.click(analyze_image, inputs=img_input, outputs=[img_result, img_explanation])
-    news_btn.click(analyze_news, inputs=news_input, outputs=[news_result, news_explanation])
-    video_btn.click(analyze_video, inputs=video_input, outputs=[video_result, video_explanation])
+        vid = gr.File(file_types=[".mp4"])
+        btn_vid = gr.Button("Analyze Video")
+        out_vid, expl_vid = gr.Textbox(), gr.Textbox()
+        btn_vid.click(analyze_video, inputs=vid, outputs=[out_vid, expl_vid])
 
 demo.launch()