README.md

---
title: Image Agent
emoji: 🏃
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
short_description: Image Agent
tags:
  - mcp-in-action-track-enterprise
  - mcp-in-action-track-customer
  - mcp-in-action-track-creative
---

# 🖼️ Image Agent — Conversational AI for Image Generation & Editing  

**Image Agent** is a conversational AI that enables users to **generate and edit multiple images using natural language prompts**, powered by **Gemini 2.5 Flash**, **Gemini Nano Banana**, **Gradio**, **Image MCP**  and the **Strands Agents SDK**.  

Image Agent demonstrates how **reasoning-based agents** can autonomously understand user intent, plan creative tasks, and use generative models for both image generation and editing.  

## Demo Video
https://www.youtube.com/watch?v=S_0ICEN2jRU

## 🚀 Key Features  

- **Conversational Image Generation** — Users simply describe what they want, and the agent creates high-quality visuals.  
- **Conversational Image Editing** — Batch-edit multiple images with natural instructions.
- **Autonomous Reasoning** — Powered by **Gemini 2.5 Flash**, the agent plans, decides, and refines actions in a reasoning loop.    


## 💡 Impact  

Image Agent enables anyone — from designers to developers — to **create and modify visuals conversationally**, bridging the gap between language and image creation. It’s a practical showcase of how **reasoning LLMs and generative tools** can collaborate to streamline creative workflows.


## Getting Started

### Setup Env variables

```
vi .env
```

```
OPENROUTER_API_KEY={openrouter_api_key}
MCP_SERVER={mcp_server}
```

Get OpenRouter API Key from https://openrouter.ai/settings/keys

Use the MCP Server from https://huggingface.co/spaces/viraja1/image-mcp

### Install requirements.txt

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

### Run App

```
python app.py 
```

Then visit http://127.0.0.1:7860 in the browser