FridgeFusion is a full-stack AI-powered cooking and meal planning assistant that transforms food images into complete recipes with nutrition insights.
Using Gemini Vision, the system identifies ingredients directly from images, then generates personalized recipes through a FastAPI + Groq-hosted LLaMA pipeline, supporting dietary preferences, cuisine styles, and multiple recipe outputs.
It also provides goal-based meal recommendations (weight loss, high-protein, diabetic-friendly) and exports recipes into beautifully formatted PDFs.
- 📸 Ingredient detection from food images using Gemini Vision
- 🤖 AI-powered recipe generation with LLaMA (Groq)
- 🥗 Diet & preference-driven cooking suggestions
- 🧪 Nutrition breakdown per serving
- 🧾 Automated PDF export of recipes + instructions
- 🔥 Fusion Recipe Lab for creative multi-style outputs
- 🎯 Goal-based meal planning engine (fitness + health focused)
Upload a food image and Pic2Plate instantly detects:
- Ingredients present in the dish
- Food components for recipe building
- Vision-based understanding for better accuracy
Pic2Plate generates complete recipes with:
- Step-by-step cooking instructions
- Multiple recipe variations
- Cuisine selection (Indian, Italian, etc.)
- Diet control (Veg, Keto, High-protein, etc.)
Powered by:
- FastAPI backend
- Groq-hosted LLaMA model
Every recipe includes:
- Calories per serving
- Protein / Carbs / Fats breakdown
- Health-focused meal insights
Smart meal suggestions for:
- Weight-loss plans
- High-protein muscle diets
- Diabetic-friendly recipes
- Balanced nutrition goals
Users can export recipes as formatted PDFs including:
- Ingredients list
- Cooking steps
- Nutrition facts
- Personalized notes
Perfect for saving or sharing meal plans.
| Layer | Technology |
|---|---|
| Frontend | Next.js |
| Backend | FastAPI (Python) |
| Vision AI | Gemini Vision API |
| LLM Engine | LLaMA via Groq |
| Nutrition | Automated per-serving analysis |
| Output | PDF Export + Recipe Formatting |
Follow these steps to run Pic2Plate locally:
git clone https://github.com/Jayesh251203/Pic2Plate.git
cd Pic2Plate🖥️ Frontend Setup (Next.js)
cd frontend
npm install
npm run dev
Frontend will run at:
⚡ Backend Setup (FastAPI) Create Virtual Environment
cd backend
python -m venv venv
Activate it:
Windows
venv\Scripts\activate
Linux/Mac
source venv/bin/activate
Install Dependencies
pip install -r requirements.txt
Run FastAPI Server
uvicorn main:app --reload
Backend will run at:
🔑 Environment Variables
Create a .env file inside the backend folder: Add Your API key's there to use.
⭐ Support
If you like this project, consider giving it a ⭐ on GitHub — it really helps!