Update app.py

app.py

@@ -4,18 +4,18 @@ from transformers import pipeline
 from PIL import Image
 import io, os, traceback
 
-# Cache settings
+# Ensure Hugging Face cache directories are writable
 os.environ["HF_HOME"] = "/app/cache"
 os.environ["TRANSFORMERS_CACHE"] = "/app/cache"
 os.environ["HF_HUB_CACHE"] = "/app/cache/hub"
 
 app = FastAPI()
 
-# Load SmolVLM as pure image-to-text
+# Load BLIP (stable image captioning model)
 pipe = pipeline(
     "image-to-text",
-    model="HuggingFaceTB/SmolVLM-256M-Instruct",
-    device=-1  # CPU
+    model="Salesforce/blip-image-captioning-base",
+    device=-1  # CPU (works on free tier)
 )
 
 @app.get("/")
@@ -45,11 +45,11 @@ async def predict_gender(file: UploadFile = File(...)):
         image_bytes = await file.read()
         image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
 
-        # Run the model (image only)
+        # Run BLIP captioning
         result = pipe(image, max_new_tokens=32)
         caption = result[0]["generated_text"].strip()
 
-        # Very simple heuristic: check for male/female in caption
+        # Simple heuristic for gender detection
         gender = "unknown"
         lower_caption = caption.lower()
         if "male" in lower_caption or "man" in lower_caption: