An intelligent web accessibility auditor that finds WCAG violations and provides AI-powered suggestions to help developers fix them.
AI-powered Streamlit app that instantly analyzes any image using Salesforce BLIP (deep vision model). Generates rich natural-language descriptions + detects dominant colors with RGB values. Modern glassmorphic UI, blazing fast, fully open-source. Built by ASAD-AZIZ
An AI-powered video summarization and Q&A pipeline. It samples frames from a video, generates scene captions with BLIP, extracts on-screen text via OCR, and uses an LLM (Groq Llama 3) to weave everything into a coherent narrative summary. The summary is then embedded into a FAISS vector store, powering a retrieval-augmented chatbot that lets you as
Emotica AI is a compassionate and therapeutic virtual assistant designed to provide empathetic and supportive conversations. It integrates a local LLaMA model for text generation, a vision model for image captioning, a RAG system for information retrieval, and emotion detection to tailor its responses.
Welcome to the AI-Powered Interactive Learning Assistant! 🚀. This is an open-source, free, and low-hardware-intensive project designed especially for students and educators! Our goal is to bring the power of AI right into your classroom, making learning more interactive, engaging, and accessible for everyone.
This project implements an AI application that bridges Computer Vision and Natural Language Processing (NLP) to automatically generate descriptive text captions for images.
LUME is an AI-powered app that turns your images into viral memes. Upload a photo, add an optional trending topic, and let Lume use BLIP and Groq AI to craft witty, high-quality captions with stylish overlays—ready to download and share instantly.
Image Captioning Tool that uses the BLIP vision-language model to generate natural captions for images. Includes scripts/notebooks for setup, running inference, and experimenting with prompts.
Multimodal AI assistant for visually impaired users — combines YOLOv8 object detection, BLIP image captioning, Tesseract OCR, and text-to-speech in a real-time Streamlit app.
An AI-powered image captioning web app using BLIP model from Hugging Face and Gradio.
It is a basic Email Phishing Analyser which uses Computer Vision and BLIP image processing along with AI pipeline to tell which Email is Phishing and which is not.
A simple web application that generates captions for images using the BLIP model from Hugging Face Transformers and a user-friendly interface created with Gradio.
This project generates behavioral descriptions from images by combining computer vision and natural language processing. It goes beyond basic scene descriptions to infer human behaviors, intentions, and social contexts.
Add a description, image, and links to the blip-model topic page so that developers can more easily learn about it.
To associate your repository with the blip-model topic, visit your repo's landing page and select "manage topics."