Text to Image generation platform that uses Vision AI to generate images from prompts. It uses Stability API and Stable Diffusion XL model for generating high quality images.
Next.js, TailwindCSS, ContextAPI, TypeScript, Stable Diffusion, Firebase, Zod (for schema validation), React-hook-form
- Create account
- Generate images from prompt
- Images are stored in firebase storage
- Clone the repo
git clone https://github.com/kaifayazkhan/describeArt
- Navigate to the project directory
cd describeArt
- Install the dependencies
npm i
- Rename the .env.example to .env and put your actual keys
- Build the app
npm run build
- Run the app
npm run start