Skip to content
All work
Live

Landscape AI

Snap a photo of your yard, pick a style, and see a photorealistic redesign of your real yard.

Landscape AI live homepage

Overview

A DIY tool for homeowners, not pros: upload a photo of your actual yard, choose a style, and a two-stage Gemini pipeline returns a photorealistic redesign that aims to keep your real yard and house as they are and change only the landscaping. It is live and selling: redesigns are metered in tokens sold as one-time Stripe packs, on a production Next.js + Aurora stack.

The problem

A homeowner who wants to redo their yard has to either hire a designer or imagine the result from a Pinterest board. Generic AI image tools will happily invent a beautiful yard — but it's not *their* yard, so it's useless for actually deciding what to do.

The approach

Landscape AI is built for DIY homeowners, not professionals. You upload a photo of your real yard and pick a style, and a two-stage Gemini pipeline (via the Vercel AI SDK) produces a photorealistic redesign that aims to preserve the existing structure and change only the landscaping — so you're looking at your house, restyled. Usage is token-metered and sold as Stripe packs, on Next.js 16 with Drizzle on Aurora Serverless v2, Auth.js v5 + Cognito, and SST 4.

Highlights

  • Two-stage Gemini pipeline built to preserve the real yard and restyle only the landscaping
  • Photorealistic redesigns from a single homeowner photo
  • Token-metered usage billed through Stripe packs
  • Auth.js v5 + Cognito on an Aurora Serverless v2 backend

Pricing

Free redesigns every day with an account; token packs of 5 for $5, 20 for $15 or 100 for $50 (one-time, no subscription).

As listed on the Landscape AI site on 2026-09-25. The price shown at checkout on the product's own site is the one that applies.

Policies

Terms · Privacy

Each product's own terms govern its use and any purchase. All Idea Engine LLC policies

Tech stack

Next.js 16React 19Vercel AI SDKGeminiDrizzle ORMAurora Serverless v2Auth.js v5CognitoAmazon SESStripeSST 4

Want to talk through how this was built?

I build and ship production apps end-to-end. Happy to dig into the architecture, the tradeoffs, or your next project.