An Artificial Intelligence web app powered by Google Gemini API to read and interpret images to text using multi modal models.
The app can also compare upto 2 images and return the comparison in text format.
The app runs on react & Typescript, hosted on firebase.
Upload an image from file system or use device camera then enter prompt message and Gemini will take time to read your image together with your prompts. You can copy the text from the UI using the copy icon
The app can be run locally by cloning the project here
run npm install then run npm run dev serve locally.
The app is deployed and hosted on Firebase using Firebase CLI
You can fork and create PR against the main branch
Issues can be created on the same branch.