images

backend/app/api/routes.py

@@ -23,7 +23,7 @@ router = APIRouter()
 
 AVAILABLE_MODELS = {
     "text": ["yaya36095/xlm-roberta-text-detector"],
-    "image": [],
+    "image": ["capcheck/ai-image-detection"],
     "video": [],
     "file": [],
 }
@@ -80,10 +80,10 @@ async def analyze(request: AnalysisRequest) -> AnalysisResponse:
                 detail=f"Text content exceeds maximum length of {MAX_CONTENT_SIZES['text']} characters"
             )
         
-        if len(request.text) < 10:
+        if len(request.text) < 50:
             raise HTTPException(
                 status_code=400,
-                detail="Text content must be at least 10 characters"
+                detail="Text content must be at least 50 characters"
             )
         
         if not AVAILABLE_MODELS["text"]:

backend/app/services/image_analyzer.py

@@ -1,9 +1,54 @@
+import io
 import logging
 import time
 from typing import Dict, Any
+from PIL import Image
+from transformers import pipeline
 
 logger = logging.getLogger(__name__)
 
+_image_classifier = None
+
+def _load_model():
+    global _image_classifier
+    if _image_classifier is None:
+        logger.info("Loading capcheck/ai-image-detection model...")
+        _image_classifier = pipeline(
+            "image-classification",
+            model="capcheck/ai-image-detection",
+            device=-1 
+        )
+        logger.info("Image detector model loaded successfully")
+    return _image_classifier
 
 async def analyze_image(image_bytes: bytes) -> Dict[str, Any]:
-    raise NotImplementedError("Image analysis models not yet configured")
+    start_time = time.time()
+    
+    logger.info(f"Starting image analysis, size: {len(image_bytes)} bytes")
+    
+    try:
+        image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
+    except Exception as e:
+        logger.error(f"Failed to parse image bytes: {str(e)}")
+        raise ValueError("Invalid image format or corrupted bytes") from e
+    
+    classifier = _load_model()
+    
+    result = classifier(image)
+    
+    label = result[0]["label"]
+    score = result[0]["score"]
+    
+    is_deepfake = label.lower() == "fake"
+    confidence = score
+    
+    analysis_time = time.time() - start_time
+    
+    response = {
+        "is_deepfake": is_deepfake,
+        "confidence": round(confidence, 3),
+        "analysis_time": round(analysis_time, 3),
+    }
+    
+    logger.info(f"Image analysis completed. Result: {response}")
+    return response

backend/app/services/text_analyzer.py

@@ -20,12 +20,6 @@ def _load_model():
     return _text_classifier
 
 async def analyze_text(text: str) -> Dict[str, Any]:
-    if len(text) > 5000:
-        raise ValueError("Text content exceeds maximum length of 5000 characters")
-    
-    if len(text) < 10:
-        raise ValueError("Text content must be at least 10 characters")
-    
     start_time = time.time()
     
     logger.info(f"Starting text analysis, length: {len(text)} chars")

backend/requirements.txt

@@ -9,3 +9,4 @@ torch==2.3.1
 numpy==1.26.4
 sentencepiece
 protobuf
+Pillow