---
title: Ai Virtual Tryon
emoji: 🌍
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 5.42.0
app_file: app.py
pinned: false
---

# AI Virtual Try-On & Fashion Advisor

🌍 An all-in-one, AI fashion assistant and virtual try-on system. This interactive web app combines computer vision, conversational AI, and web automation to deliver:
- Realistic virtual try-on results
- Automated outfit analysis and style advice
- Personalized fashion chatbot
- Similar item search and automated shopping

## 🛍️ Features

### 1. Virtual Try-On & Outfit Analysis
- **Upload Clothing & Avatar Images:** Upload a clothing item and an avatar/person image.
- **AI Try-On Generation:** Generates a virtual try-on using the [try-on-diffusion API](https://rapidapi.com/hlbq/api/try-on-diffusion/).
- **BLIP/CLIP Analysis:** Automatically analyzes the try-on result with BLIP (captioning) and CLIP (fashion prompts).
- **LLM Fashion Advice:** TinyLlama LLM provides detailed, context-aware fashion advice based on the analysis.
- **Unified Results:** See the generated try-on image, AI analysis, and advice together in one place.

### 2. Fashion Chatbot
- **Conversational AI Stylist:** Chat with a TinyLlama-powered stylist for personalized fashion tips.
- **Context-Aware:** The chatbot uses your latest try-on and analysis for relevant, tailored answers.

### 3. Find Similar & Shopping Automation
- **Similar Outfit Search:** Upload any fashion image to get recommendations for similar outfits, accessories, and alternative colors.
- **Store Suggestions:** Recommendations include suggested stores and links.
- **Automated Shopping:** Uses Playwright automation to search and compare prices across e-commerce sites.

### 4. Modern, User-Friendly UI
- **Tabbed Gradio Interface:** Clean, modern layout for easy navigation between try-on, chatbot, and similar item search.

---


## 🏗️ Architecture
- **Frontend:** Gradio (for Hugging Face Spaces)
- **Backend:** Flask API server (runs in background)
- **AI Models:** BLIP, CLIP, TinyLlama (all open-source, loaded on demand)
- **Automation:** Playwright for web scraping and product search


## How It Works
1. All AI models (BLIP, CLIP, TinyLlama) are loaded and run in the backend.
2. Try-on images are generated via the external try-on-diffusion API (RapidAPI key required).
3. The app is organized into tabs for a seamless user experience.


## Requirements
- Python 3.8+
- All dependencies listed in `requirements.txt`
- A valid RapidAPI key for try-on-diffusion (set in `app.py`)


## 🚦 Usage
1. **Clone this repo and open in Hugging Face Spaces or run locally.**
2. **Install requirements:**
	```bash
	pip install -r requirements.txt
	```
3. **Run the app:**
	```bash
	python app.py
	```
4. **Use the web UI:**
	- Try-On & Analysis: Upload images, generate try-on, get analysis and advice.
	- Chatbot: Ask fashion questions with context.
	- Find Similar: Get recommendations for similar outfits and shopping links.


## 🛠️ Setup & Deployment
1. All dependencies are listed in `requirements.txt`.
2. The backend Flask server is started automatically by `app.py`.
3. The Gradio interface is the entry point for Hugging Face Spaces.
4. For Playwright automation, ensure a `postBuild` file exists with:
	```bash
	playwright install chromium
	```


## Credits
- **BLIP:** [Salesforce BLIP](https://huggingface.co/Salesforce/blip-image-captioning-base)
- **CLIP:** [OpenAI CLIP](https://huggingface.co/openai/clip-vit-base-patch32)
- **LLM:** [TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
- **Try-On API:** [try-on-diffusion](https://rapidapi.com/hlbq/api/try-on-diffusion/)


## License
MIT

---