Add gunicorn with 2 workers for better concurrent request handling

Dockerfile

@@ -17,5 +17,14 @@ COPY . .
 # Expose port 7860 (Hugging Face default)
 EXPOSE 7860
 
-# Run the application
-CMD ["python", "main.py"]
+# Run with gunicorn + uvicorn workers for better concurrency
+# - 2 workers for CPU hardware (adjust based on available cores)
+# - 120s timeout for long video generation
+# - graceful timeout for clean shutdown
+CMD ["gunicorn", "main:app", \
+     "--workers", "2", \
+     "--worker-class", "uvicorn.workers.UvicornWorker", \
+     "--bind", "0.0.0.0:7860", \
+     "--timeout", "300", \
+     "--graceful-timeout", "120", \
+     "--keep-alive", "5"]

requirements.txt

@@ -1,5 +1,6 @@
 fastapi==0.109.0
 uvicorn==0.27.0
+gunicorn==21.2.0
 python-multipart==0.0.6
 httpx==0.26.0
 boto3==1.34.0