RoomGPT is an open-source app that lets you upload a photo of your room and generate redesigned versions of it using AI. It uses a model such as ControlNet to condition the generation on the original room layout, producing realistic variations while preserving structure like walls, windows, and furniture placement. The app is built on Next.js and exposes a simple web interface where users can upload images, choose styles, and view generated outputs. Under the hood, it calls a hosted ML model (for example on Replicate) via an API route and uses a service like Bytescale for image storage, keeping the front-end lightweight. The project is often described as an open-source clone or alternative to tools like InteriorAI, making AI-driven interior design experimentation accessible to developers. Because it is open source, developers can fork it, plug in different models, change the UI, or adapt the concept to other domains like garden layouts or product staging.
Features
- Upload-based interface that turns real room photos into AI-generated redesigns
- Uses ControlNet or similar conditioned models to preserve room layout while changing style
- Built with Next.js, using API routes to talk to a hosted ML backend
- External image hosting (e.g., Bytescale) for storing input and generated images
- Easily forkable to experiment with new models, styles, or UI flows
- Serves as a learning template for integrating generative vision into web apps