DEV Community: bowen jian

[Boost]

bowen jian — Sun, 14 Sep 2025 13:19:03 +0000

Google AI Challenge Submission

bowen jian

Sep 12 '25

🏠 RoomAI: Your Personal Interior Designer Powered by Multimodal AI

#devchallenge #googleaichallenge #ai #gemini

Comments

2 min read

🏠 RoomAI: Your Personal Interior Designer Powered by Multimodal AI

bowen jian — Fri, 12 Sep 2025 05:16:01 +0000

This is a submission for the Google AI Studio Multimodal Challenge

What I Built

Our SkillUp30 team @xuanna_chen @bowen007 developed an AI-powered smart home renovation design assistant that leverages multimodal technology to help users quickly achieve professional-grade interior design solutions. This application addresses three major pain points in traditional interior design: high entry barriers, expensive costs, and low decision-making efficiency. Users simply need to upload photos of their rooms and either select preset styles or upload reference style images, and the system instantly generates personalized renovation plans, empowering everyone to become the designer of their own home.

Demo

Project Link: https://smart-home-makeover-ai-317981316224.us-west1.run.app

Core Features Showcase:

📸 Upload current room photos with AI automatic space structure recognition
🎨 Multiple preset design styles (Modern Minimalist, Scandinavian, New Chinese, Industrial, etc.)
🖼️ Support for uploading reference style images for style transfer
💡 One-click generation of renovation renderings and design suggestions
📋 Detailed material lists and budget estimates

Users can preview different style transformations in real-time and make adjustments based on personal preferences, significantly improving the efficiency and accuracy of renovation decisions.

How I Used Google AI Studio

I fully leveraged Google AI Studio's multimodal capabilities to build this application:

Gemini Vision API: For analyzing uploaded room photos, identifying spatial layouts, existing decoration styles, lighting conditions, and other key information
Image Generation: Creating high-quality renovation renderings based on user-selected styles and room characteristics
Natural Language Processing: Converting visual analysis results into professional design recommendations and material suggestions
Style Transfer Technology: Extracting style features from reference images uploaded by users and applying them to target rooms
Prompt Engineering Optimization: Carefully crafted prompts to ensure generated renderings are both aesthetically pleasing and practical

Multimodal Features

The multimodal characteristics are the core competitive advantage of this project:

🔄 Image-to-Image Transformation: Converting existing room photos into design renderings of different styles. This visual transformation allows users to intuitively see the post-renovation effects.

📝 Image-to-Text Generation: The system not only generates visual effects but also provides detailed textual explanations, including design concepts, material recommendations, and construction considerations, offering users comprehensive guidance.

🎯 Multimodal Input Fusion: Simultaneously processing users' room photos, style reference images, and text descriptions, integrating multiple input sources to generate solutions that best meet user needs.

💬 Interactive Optimization: Users can further adjust designs through natural language descriptions (e.g., "make the living room brighter," "add more storage space"), and the system understands the intent and updates the renderings accordingly.

These multimodal features significantly enhance the user experience, transforming interior design from a professional service into an intelligent tool accessible to everyone, truly democratizing design
Team Credits: This project was collaboratively developed by the SkillUp30 Team. Our team is dedicated to leveraging AI technology to lower the barriers of professional services, making technology's benefits accessible to more people.
skillup30 team : @bowen007 @xuanna_chen

Pet MBTI Personality Analyzer: Understanding Your Furry Friend's Unique Character

bowen jian — Sun, 24 Aug 2025 15:39:40 +0000

This post is my submission for DEV Education Track: Build Apps with Google AI Studio.

Pet MBTI Personality Analyzer: Understanding Your Furry Friend's Unique Character

What I Built

I developed a web application that applies the Myers-Briggs Type Indicator (MBTI) framework to pets, helping owners better understand their animal companions through personality psychology. The Pet MBTI Personality Analyzer guides users through a comprehensive assessment to determine which of the 16 personality types best matches their pet, providing detailed insights into behavioral patterns, environmental needs, and owner compatibility.

Key Features:

Interactive personality assessment questionnaire
Comprehensive 16-type personality system adapted for pets
Detailed personality profiles including strengths, challenges, ideal environments, and owner compatibility
Responsive design that works across all devices
User-friendly interface with progress tracking

The app transforms generic pet care advice into personalized, science-based insights that help owners create better relationships with their pets.

Demo

Live Application: https://pet-mbti-personality-analyzer-317981316224.us-west1.run.app/

Sample ISTP Pet Profile Results

Type Description
The ISTP pet is a true 'Craftsman' or 'Practical Independent' of the animal world. They are highly observant and grounded in the present moment, taking in their surroundings with a quiet intensity. These pets are masters of their immediate physical environment, often learning through direct experience and hands-on (or paws-on) exploration. While they can be affectionate, it's almost always on their own terms and for brief, intense periods, quickly followed by a need for solitude.

Key Profile Sections:

Strengths: Highly independent and self-reliant, observant and alert, practical and resourceful, calm under pressure
Challenges: Can appear aloof, strongly guards personal space, may be difficult to read emotionally
Ideal Environment: Opportunities for independent exploration, designated quiet zones, predictable routines with flexibility
Owner Compatibility: Best matched with patient, observant owners who respect boundaries and appreciate subtle affection

Interface Features

Clean, intuitive assessment flow
Pet-friendly visual design
Real-time progress tracking
Comprehensive result profiles with actionable insights
Mobile-responsive design

My Experience

Key Prompt Components That Made the Difference

1. Framework Specification: Explicitly mentioning "MBTI framework" and "16 personality types" ensured the AI understood I wanted the complete system, not a simplified version.

2. Visual Requirements: Specifying "personalized MBTI-style personality cards with cute pet avatars" gave clear direction for the visual design, resulting in the appealing interface you see in the final app.

3. Behavioral Translation: The phrase "pet-specific interpretations" was crucial - this told the AI to adapt human MBTI concepts for animal behavior rather than just applying them directly.

4. Comprehensive Output: Requesting "detailed reports explaining their personality dimensions" ensured the results would be thorough and educational, not just surface-level categorization.

5. Practical Value: Including "tailored care recommendations" made the app practical rather than just entertaining.

What I Learned About Prompting

Be Specific About Scope: Instead of "analyze personalities," I specified exactly which framework (MBTI) and how many types (16) to prevent the AI from creating a simplified system.

Balance Detail with Clarity: The prompt needed to be comprehensive enough to capture my vision while remaining clear enough for the AI to execute effectively.

Consider User Experience: Including terms like "cute pet avatars" and "personalized cards" shaped not just functionality but the entire user experience design.

Think About Integration: Explicitly mentioning both Imagen and Gemini in specific contexts (visuals vs. analysis) resulted in better integration of Google AI Studio's capabilities.

The Result

This carefully crafted prompt produced an app that exceeded my expectations. The AI understood not just what to build, but how to make it engaging, scientifically grounded, and practically useful. The key was being specific about the psychology framework while allowing creative freedom in the implementation details.

The lesson learned: great prompts aren't just about describing what you want - they're about communicating your vision in a way that guides the AI toward the best possible execution of that vision.

Key Takeaways

Bridging Psychology and Pet Care: The most fascinating aspect of this project was adapting human personality psychology frameworks for animals. I discovered that many MBTI concepts translate surprisingly well to pet behavior, from introversion/extroversion to sensing/intuition preferences.

User Experience Design: Creating an assessment that feels engaging rather than clinical was crucial. I learned the importance of crafting questions that pet owners could easily observe and answer about their companions without requiring specialized knowledge.

Personalization Impact: What surprised me most was how much demand there is for personalized pet insights. Generic pet care advice is abundant, but owners crave understanding of their individual pet's unique personality and needs.

What I Learned

Behavioral Translation: Converting abstract personality concepts into observable pet behaviors required deep thinking about how animals express different traits
Assessment Design: Balancing comprehensive personality evaluation with user-friendly question formats taught me about survey design and user psychology
Scientific Adaptation: Maintaining the integrity of the MBTI framework while making it relevant for animals was a challenging but rewarding exercise in conceptual translation

What Was Surprising

The depth of emotional connection owners have with their pets became even more apparent through this project. Users don't just want to know "what type" their pet is—they want validation of what they already sense about their companion and guidance on how to better meet their pet's specific needs.

The project reinforced that technology can enhance rather than replace the human-animal bond by providing frameworks for deeper understanding and more thoughtful care approaches.

Technical Implementation

Built as a responsive web application with:

Interactive questionnaire system
Dynamic personality type calculation
Comprehensive result generation
Mobile-first responsive design
Clean, accessible user interface

The app represents a unique intersection of personality psychology, pet care, and user experience design, demonstrating how established psychological frameworks can be thoughtfully adapted for new applications.