Popular GitHub Repositories for Vision Api

Open source implementation of "Vision Transformers Need Registers"

Real-time Object Recognition using Apple's CoreML 2.0 and Vision API -

An innovative AI conversation API leveraging Google's Gemini for multimodal understanding. Combines FastAPI, Langchain, and Redis for robust, scalable, and privacy-conscious text and image-based interactions

An android application that implements facial detection

GPT_NEXT is an AI chat tool (OpenAI + Groq).

The GroqCloud API wrapper for Delphi provides access to models from Meta, OpenAI, MistralAI and Google on Groq’s LPUs, offering chat, text generation, image analysis, audio transcription, JSON output, tool integration, and content moderation capabilities.

VisionDetect let you track user face gestures like blink, smile etc.

oCaption: Leveraging OpenAI's GPT-4 Vision for Advanced Image Captioning

Image recognition iOS app with Apple’s CoreML and Vision APIs

Convert an image/wireframe to code in seconds

An app for quick-adding nutritional data to Google Fit using LLMs

A SwiftUI app using CoreML & Vision to extract text content from the images and querying from the context. Underlying it uses Google's BERT model which converted into CoreML model

A WordPress plugin for automatically generating alt text for images with Microsoft's Cognitive Services Computer Vision API.

Google Cloud Vision Api example that uses the webcam to capture images.

A simple Gradio-based app for interacting with Ollama models, supporting image analysis, text completion, and model pullin

EpisteAI Vision with TTS

Net Promoter Score App is an AI powered Windows app that allows you to capture NPS score along with Emotion score (calculated using facial expression of audience).

A photo-enabled Android application that allows users to extract text from their frame and have it be read aloud to them, implementing the Google Vision API, ML Kit for Firebase, and text to speech.

An open source iOS application that uses CoreML to classify images and send the results to a custom nodeJS backend

Apply computer vision algorithms to perform a variety of tasks on input images.