Get descriptions of images from OpenAI, Azure OpenAI and Anthropic Claude models. Supports both URLs and local files with batch processing capabilities.

openai

gpt-4

claude

azure

azure-openai

computer-vision

1.1.7 • 9 months ago

@roboflow/roboflow-red

A visual way to interact with computer vision using Node-RED

stellasphere

published 0.1.0 • 2 years ago

vue-mindee-js

Computer Vision SDK for Vue

abdelfattah

published 1.4.0 • 2 years ago

@0xalter/mocap4face

mocap4face by alter

facemoji

published 0.5.1 • 3 years ago

supervision

We write your reusable computer vision tools. 💜

instance-segmentation

r

roboflowbrad

published 0.0.9000 • 2 years ago

@tbmc/opencv-js

OpenCV JavaScript version for node.js or browser

tbmc

published 4.9.0-release.3-custom1 • last year

roboflow-node

Use Roboflow Train computer vision models for inference on images in node.js

r

roboflowbrad

published 0.2.26 • 2 years ago

pixfinder-2

Javascript library for extracting objects from images

bill.dehorty

published 0.2.6 • 6 years ago

omnicode

Simple computer vision annotator.

jterwill

published 1.0.0 • 7 years ago

wizart-vision

Wizart Computer Vision SDK

wizart_ai

published 1.0.7 • last year

@iclemens/rxcv

Computer Vision Library - Reactive Extensions

i

iclemens

published 0.3.5 • 7 years ago

cordova-plugin-ezar-videooverlay

Overlay the Cordova webview onto a live video stream

ezar

published 1.0.0 • 8 years ago

@mixvideo/video-analyzer

Video analysis toolkit using Gemini 2.0 Flash for intelligent video feature extraction

sker008

published 1.0.0 • 2 months ago

frami

AI-powered video thumbnail recommendation library

alphagolf

published 1.0.0 • 2 months ago

hookformers

Simple, performant React Hooks for running Transformers.js in your browser.

seroh

published 1.1.0 • 2 months ago

Advanced MCP server for intelligent computer use automation and AI agent operator control. Supports mouse and keyboard input, window-relative vision and coordinates, Retina display, and screenshot-based debugging. Designed for AI-driven workflows, app and

mcp

model-context-protocol

lksrz

published 0.3.1 • 2 months ago

kensa

[⏳WIP - 🧪Experimental] Web GUI testing tool using computer vision techniques

e

echamudi

published 0.0.4 • 5 years ago

facepointer

Use head tracking and face gestures to move a "mouse" pointer from up to 3m (10ft) away 👋

browsehandsfree

published 0.0.10 • 6 years ago

matchengine

Node module for using the TinEye MatchEngine API.

jeresig

published 0.0.6 • 2 years ago

whatami

Find Whatsoever in image with the convenience of Machine learning at CLI!

coderganesh

published 1.0.8 • 5 years ago

homography-transform

A robust TypeScript implementation of homography-based transformation between 2D planes, ideal for computer vision and image mapping

1.0.0 • 6 months ago

@koush/opencv4nodejs

Asynchronous OpenCV 3.x nodejs bindings with JavaScript and TypeScript API.

koush

published 5.7.2 • 4 years ago

test3-cf-sdk

JavaScript SDK for CompreFace - free and open-source face recognition system from Exadel

vladp456

published 0.6.0 • 4 years ago

emellib

Maintained by Crejo.Fun

published 0.0.16 • 4 years ago

heartthrob-vision

A computer vision to add alt descriptions on images of your website

vtnorton

published 1.1.6 • 6 years ago

@jnv/headtrackr

headtracking via webcam and WebRTC/getUserMedia

jnv

published 1.0.3 • 9 years ago

ngx-polygon-draw

Simple lightweight library to draw polygons over images. This library was created to markup areas on the photo, where the computer vision algorithms will track events. Any other usecase is appreciated, contact me on issues.