How We Built StyleSense: AI Virtual Try-On Powered by Amazon Aurora & Vercel

A developer built StyleSense, an AI-powered virtual try-on tool, in 72 hours using Amazon Aurora PostgreSQL and Vercel. The system allows users to upload a selfie and see themselves wearing clothes from any product URL, addressing the $816 billion annual cost of online clothing returns. The architecture uses Aurora Serverless v2 with IAM authentication for passwordless database access and Vercel edge middleware for seamless auth.

Online clothing returns cost the industry over $816 billion a year. The root cause is simple: shoppers can't see how clothes look on their body before buying. We built StyleSense to fix that — an AI-powered virtual wardrobe where you upload a selfie, add clothes from any product URL, and instantly see yourself wearing them. Here's how we built it, and why Amazon Aurora PostgreSQL and Vercel were the right choices for a 72-hour hackathon build. We needed a database that could handle: Aurora Serverless v2 solved all three. It scales to zero between test runs, scales up instantly under load, and supports IAM authentication — meaning our FastAPI backend never stores a database password. Instead of a static DATABASE URL with a password, we use boto3 to mint a short-lived token at connection time: python import boto3 def get iam token : client = boto3.client "rds", region name="ap-south-1" return client.generate db auth token DBHostname="stylesense.cluster-c9cswq8kqykn.ap-south-1.rds.amazonaws.com", Port=5432, DBUsername="stylesense app", Region="ap-south-1", We wire this into SQLAlchemy's connection pool via a custom creator function that refreshes the token before each new connection — tokens expire in 15 minutes, so this is essential: python from sqlalchemy import create engine engine = create engine "postgresql+psycopg2://", creator=lambda: psycopg2.connect host=AURORA HOST, port=5432, dbname="stylesense", user="stylesense app", password=get iam token , sslmode="require", No password in .env . No password in CI. No password in the repo. Just an IAM role. We kept it lean — 4 core tables in Aurora: | Table | What it stores | |---|---| users | Selfie URLs, stylized avatar URLs, body analysis | wardrobe items | Clothing images, categories, colors, source URLs | try on results | Generated try-on images, event scenes, video URLs | outfits | Saved outfit combinations | Auth and social friendships, chat threads stay in Supabase, which already has Row-Level Security and Realtime built in. Aurora handles the data that benefits from SQL joins and full ACID transactions — like "show me all try-ons for items in category X that this user saved as outfits." Our Next.js frontend deploys to Vercel with three environment variables and zero configuration files. The things that made the biggest difference: Edge middleware for auth : Supabase session refresh runs at the edge on every request, so protected pages never flash unauthenticated content. This is one middleware.ts file: js // middleware.ts import { createServerClient } from "@supabase/ssr"; import { NextResponse } from "next/server"; export async function middleware request: NextRequest { // Refreshes the Supabase session cookie on every request // Redirects to /login if the user is not authenticated } Mumbai region : We deployed both the Vercel frontend bom1 and Aurora ap-south-1 in Mumbai, keeping API latency under 20ms for the database round-trip. The one gotcha : Runway ML requires all image URLs to be public HTTPS. Localhost URLs fail silently. Every selfie and wardrobe image gets re-hosted to Supabase Storage before being passed to any Runway API call — Vercel's environment variables made switching between dev and prod URLs painless. The "wow moment" flow that we demoed: The entire pipeline is async. FastAPI fires each Runway task and returns a task ID; the frontend polls via Zustand store state that survives page navigation. Aurora IAM token refresh in connection pools : SQLAlchemy's connection pool reuses connections, so a token minted at startup expires mid-session. The fix: use NullPool or override the creator so a fresh token is minted for every logical connection. We went with the creator approach and a short pool recycle time. Runway image URL requirement : Every image URL sent to Runway must be a public HTTPS URL. During development this means all local uploads get re-hosted to Supabase Storage before the Runway call — an extra round-trip but essential. Credit budget discipline : Runway gen4.5 video costs 60-100 credits per 5 seconds. With a 50,000-credit budget, we used gen4 image turbo 2 credits for all dev testing and reserved the full quality models for demo recordings. The full source is on GitHub. The live demo runs on Vercel at https://style-sense-steel.vercel.app/ https://style-sense-steel.vercel.app/ . Built in 72 hours for the H0: Hack the Zero Stack with Vercel v0 and AWS Databases hackathon. H0Hackathon