NAME ID

Hamza Abdullahi Ahmed 666768

Mumin A. Mumin 667301

Anisah Hussein 664914

Hussein Fahat Mohamud 664772

FACILITATOR: PROFESSOR FREDRICK OGORE

PROJECT NAME: DONHOME

Group Report

AI-Powered Interior Design Generator

Group Members and Roles

Anisah Hussein

Tasks:

- Led the project setup, including environment configuration and integrating the backend
with the frontend.

- Implemented the functionality for Python script execution and image generation using
Stable Diffusion.

Role: Team Leader and Backend Developer

Hamza Abdullahi Ahmed

Tasks:

- Developed the frontend interface for the web application, including the design input forms
and homepage display.

- Styled the application using CSS for a user-friendly and responsive design.

Role: Frontend Developer and UI/UX Designer

Mumin A. Mumin

Tasks:

- Managed the integration of the AI model and ensured seamless interaction between the
Python script and Node.js backend.

- Conducted testing and debugging of the Python script for image generation.

Role: AI Specialist and Debugging Lead

Hussein Fahat Mohamud

Tasks:

- Prepared documentation and reports for the project, including summarizing its objectives,
features, and challenges.
- Contributed to ensuring all code was clean, well-documented, and ready for deployment.

Role: Documentation Specialist and Quality Assurance

Project Overview

The AI-Powered Interior Design Generator is a web application designed to help users
visualize interior design ideas. By selecting a room type and providing descriptive text,
users can generate AI-based images that represent their vision. This innovative tool bridges
the gap between imagination and visualization using cutting-edge AI technology, making
interior design more accessible and engaging.

The platform leverages advanced machine learning algorithms, such as Stable Diffusion, to
generate high-quality images based on user input. By combining textual descriptions with
pre-trained models, the system delivers highly customized visuals that cater to a user’s
unique style and preferences. This functionality is particularly useful for interior designers,
homeowners, and anyone looking for inspiration or validation for their creative ideas.

One of the core objectives of this project is to democratize access to design tools that were
traditionally available only to professionals. By automating the image generation process,
the platform allows users to experiment with various styles, layouts, and features without
requiring design expertise. This opens up a world of creative possibilities for individuals
who might otherwise feel constrained by their technical or artistic skills.

The integration of a user-friendly interface ensures that the application is intuitive and
accessible to a diverse audience. Whether someone is designing a cozy bedroom or an
elegant dining room, the process is streamlined to minimize complexity. Additionally, the
application’s backend architecture supports seamless execution of tasks, from handling user
requests to delivering results efficiently.

In the future, the platform could evolve to incorporate additional features, such as
interactive 3D models or augmented reality previews, further enhancing its utility. By
embracing modern technology, the AI-Powered Interior Design Generator aims to redefine
how individuals and professionals alike approach the art of interior design.

Key Features

 User-Friendly Interface: Offers an intuitive and simple interface where users can
select their desired room type and input detailed design descriptions. The interface
 prioritizes ease of use to cater to a diverse audience, ensuring accessibility for
beginners and professionals alike.

 AI Image Generation: Leverages the power of the Stable Diffusion AI model to

produce high-quality and realistic images based on user-provided text inputs. This
feature bridges the gap between conceptual ideas and visual representation,
allowing users to bring their interior design ideas to life.

 Dynamic Integration: Incorporates robust backend technologies, including Node.js

and Python, to establish seamless communication between the web application and
the AI model. This ensures smooth data processing, quick execution, and reliable
results.

 Real-Time Updates: Enables immediate visualization of generated designs. Once

the AI completes the image generation, the result is dynamically displayed on the
homepage, offering users a real-time preview of their creative input.

 Responsive Design: Styled with a modern, clean, and professional aesthetic using
CSS. The responsive design adapts gracefully to different screen sizes, ensuring an
optimal user experience on desktops, tablets, and mobile devices.

 Extensive Room Selection: Provides multiple room types, such as bedrooms,

kitchens, living rooms, and balconies, allowing users to customize designs for
various spaces.

 Error Handling and Feedback: Includes robust error handling, ensuring users are
informed if something goes wrong during image generation, while providing
actionable feedback for retrying.

Experiences Gained

 Enhanced Technical Skills: Developed a deeper understanding of integrating AI

models with web technologies. The team explored advanced tools like Stable
Diffusion and techniques for combining backend and AI-driven systems.

 Backend Expertise: Gained proficiency in backend development using technologies

such as Node.js, Express.js, and Python. These skills were essential for coordinating
data flow and executing AI scripts seamlessly.

 Frontend Design and Responsiveness: Improved skills in creating responsive and

user-friendly interfaces using HTML, CSS, and EJS templates. Team members
learned how to prioritize design aesthetics without compromising functionality.
  Collaboration and Communication: Strengthened teamwork and collaborative
skills by dividing responsibilities effectively. The team tackled complex challenges
collectively, ensuring open communication and shared problem-solving.

 AI Technology Mastery: Acquired practical knowledge of implementing cutting-

edge AI tools like Stable Diffusion, from installing dependencies to fine-tuning the
model for optimal performance.

 Debugging and Problem-Solving: Overcame various technical challenges,

including API integration, image file management, and troubleshooting issues
related to long generation times and system errors.

 Time Management and Coordination: Balanced multiple responsibilities and

synchronized efforts within the group, ensuring deadlines were met without
compromising the quality of the project.

Challenges Faced

 AI Model Performance: Implementing Stable Diffusion for image generation

presented a significant challenge due to its computational requirements. The AI
model necessitated high-performance hardware and substantial memory resources,
leading to delays in processing. Optimizing the model's performance while ensuring
quality output was a constant balancing act. Additionally, managing prolonged
generation times during testing phases impacted the workflow and required careful
time allocation.

 Backend Integration: Ensuring seamless communication between Python scripts

running the Stable Diffusion model and the Node.js backend proved to be complex.
Issues such as handling asynchronous processes, managing data flow, and resolving
API response errors required a deep understanding of both technologies. The
integration process also demanded robust error handling to prevent application
crashes during unexpected situations, such as model timeouts or script failures.

 Styling and Responsiveness: Achieving a consistent, professional, and visually

appealing user interface across all web pages was an iterative process. The team
faced difficulties in ensuring responsive design for various screen sizes and
maintaining cross-browser compatibility. Extensive CSS adjustments were needed
to fine-tune the layout, fonts, and color schemes to meet modern design standards.
Additionally, incorporating dynamic elements, such as generated images, while
maintaining layout consistency posed unique challenges.

 Time Management: Balancing individual responsibilities and coordinating efforts

across team members proved challenging, particularly during debugging and testing
phases. The team encountered unexpected delays caused by technical issues, such
as missing dependencies and model configuration errors. Time constraints
 intensified the need for efficient collaboration and prioritization, often requiring late
hours to resolve critical bugs and meet project deadlines.

 Connectivity Issues: Slow or unreliable internet connectivity hindered several

operations, particularly during the initial setup phases. Downloading large model
files, dependencies, and updates for Stable Diffusion and related libraries took
significantly longer than expected. This delay not only impacted the project timeline
but also limited the ability to conduct multiple iterations and tests in a timely
manner.

 Debugging and Testing: Identifying and fixing errors in both the backend and
frontend components was a time-intensive process. Issues such as unhandled
exceptions in Python scripts, mismatched data formats, and rendering errors on the
client-side required detailed debugging. Testing the integration of AI-generated
images within the web interface added another layer of complexity, as the team had
to ensure proper file handling and rendering across different browsers and devices.

 Resource Constraints: The computational demands of Stable Diffusion highlighted

hardware limitations, such as insufficient GPU capacity on some machines. This
required the team to adapt by optimizing resource usage, leveraging cloud-based
solutions where possible, and sharing hardware for testing.

 Error Handling and User Feedback: Developing a robust error-handling

mechanism to address unexpected issues, such as model failures or server timeouts,
was crucial. Providing meaningful feedback to users, such as informing them about
delays or errors during image generation, required thoughtful implementation to
enhance the user experience.

 Version Management and Dependencies: Managing multiple dependencies across

different platforms and environments proved challenging, especially when dealing
with version mismatches or deprecated libraries. Coordinating updates and
ensuring consistency across team members' systems required careful
documentation and troubleshooting.

 Learning Curve: For some team members, adapting to new technologies such as
Stable Diffusion, Python AI libraries, and Node.js posed a steep learning curve.
Gaining familiarity with these tools while actively working on the project required
significant effort and continuous self-learning.

Entity-Relationship Diagram
Entity-Flow Diagram
Conclusion

The AI-Powered Interior Design Generator was a highly rewarding project that provided
invaluable hands-on experience in integrating artificial intelligence with web development.
It offered the team an opportunity to explore the cutting-edge capabilities of AI models,
such as Stable Diffusion, and understand how they can be utilized in real-world
applications. Through this project, the team gained deep insights into the complexities of AI
integration, from managing computational resources to ensuring seamless backend and
frontend communication. Despite the numerous challenges encountered, such as debugging
complex integrations and addressing performance bottlenecks, the team successfully
delivered a functional application that showcases the transformative potential of AI in the
field of interior design.

This project also highlighted the importance of collaboration and effective time
management, as team members worked together to overcome technical hurdles and meet
deadlines. The experience of designing a user-friendly interface and ensuring a responsive,
visually appealing web application enriched the team's understanding of modern web
development practices. Additionally, tackling real-world challenges, such as optimizing AI
model performance and managing connectivity issues, provided a robust foundation for
future endeavors in AI-driven visualization tools.

The completion of this project not only enhanced technical skills but also inspired a deeper
appreciation for the innovative applications of AI in creative industries. The success of the
AI-Powered Interior Design Generator serves as a testament to the team's resilience and
adaptability and lays a strong foundation for further exploration and enhancement. Moving
forward, the team envisions building upon this work to incorporate more advanced
features, improve efficiency, and broaden the scope of AI's impact in design and
visualization.