Thanks to visit codestin.com
Credit goes to github.com

Skip to content

codrkai/ollama-vision

Repository files navigation

Ollama Vision

Created using NextJS, this project allows selecting a model from ollama, then dropping in an image for it to describe.

Requirements

Visit www.ollama.com

  • install ollama
  • download a vision model: llava, llama3.2-vision, bakllava, etc.

Installation

Rename .env-example to .env

  npm install
  npm run dev

Open http://localhost:3000

screenshot

ollama vision screenshot

About

NextJS v15 app that uses ollama to read an image with drag and drop and describes what is in the image.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published