🔍 Search your local images effortlessly with PicFinder AI, a privacy-focused tool using natural language and AI for instant results.

🔧 Streamline Hailo CLIP applications in Golang projects with this simple and efficient handler for improved performance and ease of use.

Free to Use AI Face Recognition (O_O)

A portfolio showcasing modern AI pipelines (ETL, training, fine-tuning, etc.) and a text-to-video RAG system prototype. Included are several computer vision pipelines for object detection, object segmentation, and anomaly detection. The RAG system takes textual users prompts and returns relevant video clips from a corpus of class lecture recordings

A semantic search engine for X-ray images supporting text queries and reverse image search, powered by OpenAI CLIP.

Deep learning pet breed recognition app

Project DART. Similarity search, SAM, CLIP, and more

A service converts images into vectors using OpenAI CLIP for similarity comparison

A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.

A semantic image search engine built with Streamlit and Ultralytics, powered by OpenAI's CLIP and Meta's FAISS for intelligent visual content discovery.

A PyTorch implementation of conditional GANs (DCGAN + CLIP) to generate human faces from text prompts.

A visual search engine for fashion that recommends clothing based on style similarity using OpenAI CLIP and Vector Embeddings. 🛍️✨

KoCLIP: Korean port of OpenAI CLIP, in Flax

This project implements a semantic search engine that allows users to find images using natural language descriptions or by uploading a reference image

Novel multimodal architecture for detecting such misinformation by explicitly modeling the consistency between visual content, textual claims, and external factual knowledge.

An offline, private AI image search engine powered by OpenAI CLIP. Search local photos with natural language. No GPU needed.

Multimodal Embeddings using OpenAI-Clip

Course assignments of COL828:- Advanced Computer Vision course at IIT Delhi under Professor Chetan Arora

Few-shot CLIP classification with conformal prediction, probability calibration, and reliability metrics.

Automated formal verification tool for vision classifiers using CLIP embeddings and MILP optimization. Converts OWL ontologies into ConSpec specifications and provides mathematical guarantees about model behavior in safety-critical AI systems.