README.md

metadata

title: Video Face Swap API
emoji: 🐠
colorFrom: pink
colorTo: indigo
sdk: docker
sdk_version: latest
app_file: api_server.py
pinned: false
disable_embedding: false
short_description: GPU-accelerated face swap video processing API
license: mit

Face Swap Video API

GPU-accelerated FastAPI backend for face swap video processing with MongoDB storage.

🚀 Quick Start

Docker Deployment (Recommended)

docker-compose up --build

The API will be available at http://localhost:8000

See API Documentation for detailed usage and endpoints.

Features

• ✅ GPU acceleration with CUDA support
• ✅ Asynchronous face swap processing
• ✅ MongoDB Atlas integration
• ✅ RESTful API with Swagger documentation
• ✅ Result video download URLs
• ✅ Job status tracking

API Endpoints

• POST /api/source-image - Upload source image
• POST /api/target-video - Upload target video
• POST /api/face-swap - Start face swap processing
• GET /api/job/{job_id} - Get job status
• GET /api/result-video/{result_video_id} - Download result video
• GET /docs - Interactive API documentation

Requirements

• Docker with NVIDIA GPU support (nvidia-docker2)
• MongoDB Atlas account (or local MongoDB)
• CUDA 12.1+ compatible GPU

License

MIT License - Based on DeepFakeAI/facefusion Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference