Open Vision-Language Models Locally

Course

Browser, Computer-Use & Coding Agents

Udemy: coming soon

Tools

• Qwen-VL (open-source)
• Florence-2 (open-source)
• Ollama (open-source, free)

Watch first

• Image Understanding With GPT, Claude and Gemini APIs
• Run AI Locally With Ollama (and LM Studio)

In this module

1. How AI Sees: Vision Models Explained
2. Image Understanding With GPT, Claude and Gemini APIs
3. Document AI: OCR, Forms and Tables
4. Object Detection With YOLO
5. Open Vision-Language Models Locally
6. Project: Receipt and ID Checker