Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.

Deploy and Chat with Llama 3.2-Vision Multimodal LLM Using LitServe, Lightning-Fast Inference Engine

A focus on aligning room elements for better flow and space utilization.

Get compliments in the style of Regina George via analyzing video in a @CloudflareDev Worker by breaking it into frames and sending a frame every x seconds to Llama🦙 3.2 Vision hosted on Workers AI!

Dumb image-to-text experiment

The Pictionary app uses LLaMA 3.1 to generate random drawing prompts and LLaMA 3.2 Vision to predict and judge user drawings based on these prompts. It provides an interactive and fun way to test your drawing skills within a set time limit.

A gradio web UI demo for Llama3.2-Vision Model

CLI tool for creating image captions using Ollama vision models

Multimodal Matrix chatbot using ollama, flux.1-schnell, kokoro, and whisper. Mirrored from https://sij.ai/sij/llux

An OCR application that extracts text from images

🔴SALAMA is an AI Safety System focused on improving surveillance through intelligent monitoring and alerts. It uses YOLO11's fast detection and LLaMA 3.2 Vision's contextual analysis to support railway safety by identifying risks in real-time and enabling proactive responses. As a prototype, it is an initial step toward smarter safety solutions.

Shutterstock Image Analyzer is a Python tool that leverages AI to analyze images, generate Shutterstock-compatible metadata (description, keywords, categories), and save the output in CSV format for easy image contribution.

Experiments with various LLMs, including OpenAI GPT-4o, via GitHub Models.