Travel360 : ✈️ Explore, 📸 Selfie — Boosted by Gemini-2.5-flash-image-preview

#devchallenge #googleaichallenge #ai #gemini

Google AI Challenge Submission

This is a submission for the Google AI Studio Multimodal Challenge

What I Built

I built Travel360, an app that offers guided tours of a city’s top landmarks through Google Maps’ immersive 3D view. Along the journey, users can capture AI-powered selfies at iconic spots.

Travel360 turns repetitive selfies into unique, shareable moments and makes city exploration fun, accessible, and engaging — without the cost or limits of physical travel.

With just a camera or a simple drag & drop, Gemini’s Nano Banana AI instantly places users in front of world-famous monuments like Times Square, Tower Bridge, or the Statue of Liberty.

💡 Update: From my original Travel360 idea, I created MapShot — a more refined version with a pretty design and extra multimodal features.
Discover the MapShot submission here 👉 : MapShot

Demo

Here’s a walkthrough of Travel360 in action:

1) Navigate to a city in immersive view : https://travel360-50134736379.us-west1.run.app/

2) Click on start tour

3) Upload or take a selfie using camera.

4) Generate a realistic selfie in the selected place.

👁️ Canva Visual presentation

👁️ Youtube Visual presentation

Current deployed version demos (added features : quick capture mode, and selfie custom weather & daytime) : View NEW live demo :

🎥 Canva Video Demo

🎥 Youtube Video Demo

How I Used Google AI Studio

I leveraged Google AI Studio to bring Gemini’s multimodal capabilities into Travel360 and speed up development:

Code & Debugging Support: Gemini helped generate React/TypeScript snippets, fix bugs, and streamline integration with Google Maps immersive 3D view.
Landmark Data: Gemini suggested the best places to feature in each city and provided their geographic coordinates to build a guided tour experience.
Selfie Generation (Prototype): With Gemini Nano Banana, I connected uploaded user images with context prompts (e.g., “Place the user at Times Square”) to generate realistic selfies at landmarks.
Multimodal Flow: Gemini processed both image + text inputs and produced image outputs, enabling a seamless flow between the guided city tour and selfie creation.

This mix of AI-assisted development and multimodal integration made Travel360 both faster to build and more engaging to use.

Multimodal Features

Travel360 enhances the user experience through multimodality in several ways:

Image + Text Inputs → users upload a photo and Gemini interprets instructions (via prompt) about where to place them.

Immersive Map + AI Output → Google Maps 3D provides the navigation, while Gemini (gemini-2.5-flash-image-preview) generates a personalized selfie at the selected landmark.

By combining the Google Maps immersive API with Gemini’s multimodal image generation API, Travel360 delivers a unique and playful experience — making every city feel instantly accessible.