Build an Image Upscaler with Claude Code

Build an Image Upscaler web app. People search for "image upscaler" about 580,000 times a month, plus related searches like "upscale image online", "ai image enhancer", "enlarge image quality". The goal is a tool that ranks for those searches and makes money.

What it should do:
Build an AI image upscaler web app. Create a homepage with a large upload zone that says 'Drop your image to enhance'. When users upload an image, show the original with resolution details. Add upscaling options: 2x, 4x, 8x enhancement levels. Include processing type selectors: 'Photo', 'Art/Drawing', 'Screenshot'. Show a before/after comparison slider when processing is complete. Add download button with file format options (PNG, JPG). Display processing time estimate and enhanced resolution info. Use a clean design with purple and blue gradients. Focus on the upload and enhancement flow first.

How to build it:
1. Read this folder first. If it is empty, set up Next.js (App Router, TypeScript, Tailwind). Write a short PLAN.md with the pages, components, any library or API you need, and what you are leaving for later. Then build.
2. Put the tool itself on the homepage so a visitor can use it within seconds, with no sign-up. Do the processing in the browser where you can, so it is fast and cheap to run. Look at how Upscaler.ai, Waifu2x, Real-ESRGAN do it and make ours simpler and faster.
3. Make it rank. Use "image upscaler" in the title tag, H1 and meta description. Under the tool, add a short how-to and an FAQ with FAQPage schema, and add a sitemap and robots.txt. Scaffold these programmatic pages from one template and a data file: /upscale-[image-type]-images, /image-upscaler-for-[use-case], /enhance-[resolution]-images.
4. Monetisation: Freemium: 5 free upscales/day, $11/mo unlimited + batch processing. Add a pricing page and the free usage limit, and leave Stripe checkout as a clearly marked stub with the environment variables it needs.
5. Run it locally and test the main flow end to end, including edge cases like empty input and very large files. Fix what breaks, then finish with a summary of what works, what is stubbed and how to deploy it to Vercel.

Paste it into Claude Code in an empty folder. It plans first, so read PLAN.md and steer before it starts building.