computer-vision

Written in Python, this project performs image analysis and description generation using Gemini Pro Vision, LLaMA and Ollama models. Supports both cloud-based and local models. Works as an interactive assistant that understands image content and responds to queries.

Features

• →Gemini Pro Vision, LLaMA and Ollama support
• →Image analysis and description generation
• →Local model support
• →Image content querying
• →Python CLI interface