Upload a room photo → Describe the purpose → Receive a full interior design brief.
Built by Ayush Nandi · Prototype ready to connect with any Vision AI model.
RoomRevamp AI is an intelligent, front-end interior design assistant that transforms any room photo into a fully structured, purpose-driven design brief.
Simply upload a photo of your space, tell it what you want the room to become, pick your budget level, and get a complete plan — covering style direction, colour palette, furniture layout, lighting strategy, decor accents, and shopping priorities.
The prototype is fully functional as a standalone UI and is architected to plug directly into any Vision AI model (GPT-4o, Claude, Gemini) for full end-to-end AI room analysis in production.
| Feature | Description |
|---|---|
| 📸 Photo Upload | Drag-and-drop or click-to-browse. Supports JPG, PNG, WebP with instant live preview |
| 🎯 Room Type Selector | Bedroom, Living Room, Kitchen, Home Office, Studio, Kids Room, Balcony |
| 💰 Budget Tiers | Budget-friendly · Mid-range · Premium — practical at every level |
| ✍️ Free-form Intent | Describe purpose, vibe, constraints, and mood in plain language |
| 🎨 Design Brief Output | Style direction, colours, furniture, lighting, decor, shopping priorities |
| 📱 Responsive UI | Fully mobile-optimised across all screen sizes |
| 🤖 AI-Ready Architecture | Plug in any Vision model — the interface is complete |
┌─────────────────────────────────────────────────────────┐
│ │
│ 📸 UPLOAD ✍️ DESCRIBE 🎨 DESIGN │
│ ────────── ────────── ────────── │
│ Drop a clear → Room type, → Receive a │
│ room photo budget level, complete │
│ vibe & goals brief │
│ │
└─────────────────────────────────────────────────────────┘
Step 1 — Upload Your Room
Drop a clear photo of the existing space. The app previews the image instantly.
Step 2 — Describe the Goal
Select room type and budget, then write a free-form description — intended purpose, preferred style, specific constraints, and must-haves you want to keep.
Step 3 — Generate Design Plan
Hit Generate and receive a structured design brief you can act on immediately — or pipe into an AI image model for a visual reimagining of the space.
- Pure HTML / CSS / JS — zero build step, zero dependencies
- Unsplash for demo photography
- GitHub Pages for hosting
- Vision Model Ready — connect GPT-4o, Claude, or Gemini via API
interior_design_generator/
├── index.html # Main app entry point
├── style.css # All visual styles & responsive layout
├── script.js # Upload handling, UI logic, design generation
├── assets/ # Static images & icons
└── README.md # You are here
# 1. Clone the repository
git clone https://github.com/ayushnandi718-dev/interior_design_generator.git
# 2. Navigate into the project
cd interior_design_generator
# 3. Open in your browser — no build step required!
open index.htmlOr just visit the live demo directly — no setup needed.
Purpose-First Recommendations
Every suggestion ties directly to the declared room function. A gaming setup gets different lighting and layout advice than a nursery.
Budget Realism
Recommendations are calibrated to three distinct budget tiers — ensuring the output is actionable, not just aspirational.
Production-Ready Architecture
Designed as a front-end prototype that seamlessly connects to any vision/image AI model via API. The interface is complete — plug in a model and it's production-ready.
Minimal Friction UX
Three steps, zero accounts, zero installs. Upload → Describe → Generate.
- Photo upload & live preview
- Room-type & budget selector
- Free-form design brief generation
- Responsive mobile layout
- AI Vision Model integration (GPT-4o / Claude)
- AI room visualiser (DALL-E / Stable Diffusion)
- Shopping link integration
- Save & export design brief as PDF
- User accounts & history
Contributions, issues, and feature requests are welcome!
# 1. Fork the repository
# 2. Create your feature branch
git checkout -b feature/your-feature-name
# 3. Commit your changes
git commit -m "feat: add your feature"
# 4. Push to the branch
git push origin feature/your-feature-name
# 5. Open a Pull RequestThis project is open-source under the MIT License.
