Pretrained pose detection model

Pretrained face detection model

Pretrained face landmarks detection model

Pretrained hand pose detection model

Vector annotation node types, tools, and controls for Veyrajs — bounding boxes, polygons, polylines, keypoints, skeletons, and cuboids.

Create landmark array from keypoints & keypoints3D arrays from the predictions of new tensorflow hand pose model

Framework-agnostic pose analyzer for calisthenics. Compares detected body keypoints against a JSON of target joint angles and reports per-joint feedback.

Pretrained hand detection model

Powerful React image and video annotation tool for machine learning, computer vision, and AI training data creation. Features rotatable bounding boxes, polygons, keypoints, segmentation with TypeScript support and Material-UI components.

Pretrained pose detection model

WebGPU-powered hand tracking. Faster than MediaPipe, zero dependencies.

Pretrained face landmarks detection model

Framework-free virtual try-on pipeline: person segmentation, pose estimation, TPS garment warp, and mask/depth-aware compositing — embeddable in any app, on-device, no server.

GPU-accelerated Computer Vision for JavaScript

Deploy AI agents to E2B and Daytona sandboxes

A set of components to perform Tensorflow.js pose detection on hands, face, and body. Provides a player to perform visualization overlays while source video or webcam is playing.

Pretrained hand pose detection model

Pretrained face detection model

Friendly hand tracking for p5.js — a wrapper around ml5.js HandPose for beginners

Markdown document analyzer for AI agents - extract metadata, headings, links, tables, tokens, and key points