README.md

---
title: Project Visualizer Agent
emoji: 🖼
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.25.2
app_file: app.py
pinned: false
license: mit
short_description: This tool uses an AI-powered image generation model to creat
---

**Track:** `mcp-server-track`

---

# 🧠 Project Visualizer Agent

**Turn your project ideas into visuals — instantly.**  
This tool uses an AI-powered image generation model to create high-quality illustrations based on detailed project descriptions.

---

## 🚀 Overview

The **Project Visualizer Agent** is built for makers, designers, and thinkers who want to:

- Quickly visualize abstract concepts.
- Generate artwork for startup ideas, product pitches, or research projects.
- Use curated prompt templates to boost creativity and save time.

It leverages an OpenAI-compatible image generation API and provides advanced controls over image size, inference steps, and seed values.

---

## 🖼️ Features

✅ Text-to-image generation  
✅ Preloaded detailed prompt examples  
✅ Negative prompt support  
✅ Adjustable image dimensions  
✅ Random or fixed seed option  
✅ Simple and fast Gradio UI  

---

## 🧪 Sample Prompts

Examples you can select directly in the app:

- **Smart Farming Dashboard**  
  *A rice paddy at dawn, sensors glowing, farmer holding a holographic dashboard.*

- **Voice-Based Study Companion**  
  *Teen speaking to an AI pod, cozy twilight setup, floating quiz bubbles.*

- **Elderly Health Alert System**  
  *Family scene, wristband alert, daughter holding smartphone showing health graph.*

- **Dream2Scene Storyboard Panel**  
  *Writer in attic, fantasy visuals emerging from typewriter, painterly style.*

(And more…)

---

## 🔧 How to Run

### 1. Clone the repo

### 2. Install dependencies

```bash
pip install -r requirements.txt
```

### 3. Set up environment variables

Create a `.env` file with your Nebius / OpenAI-compatible API credentials:

```env
API_KEY=your_api_key
```

### 4. Run the app

```bash
python app.py
```

---

## 📁 Project Structure

```
.
├── app.py                 # Gradio interface logic
├── utils/
│   └── image.py           # Image generation and saving logic
├── requirements.txt       # Dependencies
└── README.md              # This file
```

---

## 📸 Demo

![screenshot](assets/demo-ui.png)
![alt text](image/20250611_032824.png)
![alt text](image/20250611_035514.png)
---

## ✨ Future Improvements

* Add multi-image comparison
* Integrate actual LLM prompt crafting support
* Enable history and download gallery
* Add animated scene generation

---

## 🧑‍💻 Built With

* [Gradio](https://www.gradio.app/) — for UI
* [Nebius Studio](https://nebius.ai/) Flux Schnell model (OpenAI-compatible)
* Python 🐍

---

## 📬 Contact

Made by **Ritwik Singh**
📧 [officialritwik098@gmail.com](mailto:officialritwik098@gmail.com)


Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference