Stop Porn is a browser extension engineered to help users prevent access to pornographic content by automatically classifying images on a webpage. When you visit a site, the extension fetches and analyzes the images, and if it detects five or more pornographic images, it blocks the page. The image classification process happens entirely on your device, ensuring no data is transferred outside the extension. The extension has been tested on various well-known adult sites, showing high effectiveness in blocking them. Some sites might require additional interaction, like scrolling or refreshing, for successful monitoring.

The TF Image Classifier is a Chrome extension that employs TensorFlow.js to classify images using models like MobileNet V2 and COCO-SSD. Simply browse any website and use the extension to analyze visible images. It is particularly useful for researchers, students, and professionals looking to identify or catalog visual data quickly. With user-friendly controls and real-time processing, it streamlines the workflow of image classification without needing additional software setup.

LLaVA-Plus builds upon leading vision-language foundations to deliver an agent capable of interpreting and reasoning over multiple images simultaneously. It integrates assembly learning and vision-language planning to perform complex tasks such as visual question answering, step-by-step problem-solving, and multi-stage inference workflows. The framework offers a modular plugin architecture to connect with various LLM backends, enabling custom prompt strategies and dynamic chain-of-thought explanations. Users can deploy LLaVA-Plus locally or through the hosted web demo, uploading single or multiple images, issuing natural language queries, and receiving rich explanatory answers along with planning steps. Its extensible design supports rapid prototyping of multimodal applications, making it an ideal platform for research, education, and production-grade vision-language solutions.