RestorePhotos.io is an AI web app for restoring old, blurry, or low-quality face photos and bringing them back to life. It wraps the GFPGAN model (served via Replicate) behind a friendly Next.js front end, so non-technical users can upload an image and receive an enhanced version without ever touching ML code. The workflow is straightforward: you upload a photo, the serverless API route sends it to Replicate, and the restored image is returned and displayed in the UI. The project is production-oriented, not just a toy: it uses Bytescale for storage and image processing, Vercel for hosting and serverless functions, Auth.js + Neon for authentication and database, and Upstash Redis for rate limiting. This combination makes it a good blueprint for building real-world AI apps that must deal with authentication, quotas, and storage as well as inference.
Features
- AI-powered restoration of old and blurry face photos using GFPGAN on Replicate
- Next.js front end with API routes handling the full upload → inference → download loop
- Bytescale integration for image storage and transformations
- Hosted on Vercel with serverless functions for scalable, low-ops deployment
- Auth.js + Neon for authentication and persistent user data where needed
- Upstash Redis for rate limiting to protect APIs and control free vs heavy usage
Project Samples
