#Real-time

Logo of openpose
openpose
OpenPose detects 135 keypoints for body, hands, face, and feet in real-time across multiple subjects in both 2D and 3D. The system supports diverse input sources such as images, videos, and webcams, and offers consistent runtime performance. It is compatible with Ubuntu, Windows, and macOS and utilizes CUDA and OpenCL for improved performance. OpenPose can be integrated via C++ and Python APIs, offering flexibility for input and output processes, suitable for computer vision and AI research.
Logo of FasterLivePortrait
FasterLivePortrait
FasterLivePortrait delivers real-time portrait animation on RTX 3090 using TensorRT, achieving over 30 FPS. It supports cross-platform deployment with ONNX models, providing approximately 12 FPS. The project enhances functionality by supporting native Gradio apps, multi-face handling, and animal models. Recent updates focus on speed optimization and bug fixes. Deployment is simplified with Docker, a Windows package, and macOS support for M1/M2 chips. Ideal for diverse AI applications.