*****************************************************************************

Government Of Karnataka

Department of Collegiate and Technical Education

GOVERNMENT ENGINEERING COLLEGE

MAJALI, KARWAR-581345
DEPARTMENT
OF
COMPUTER SCIENCE AND ENGINEERING
A
MINI-PROJECT
on
“Text-To-Image Generator Using Open-AI ”
Submitted By
Dileep 2GP22CS014
Sachin V Gaonkar 2GP22CS039

Under the Guidance of

Prof. D CHAVHAN

VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI-590002
 GOVERNMENT ENGINEERING COLLEGE
KARWAR, MAJALI – 581345
Department of Computer Science and Engineering

CERTIFICATE

This is to certify that the database management system mini project entitled "Text-To-Image
Generator Using Open-AI", carried out by Dileep bearing USN: 2GP22CS014 and Sachin v
Gaonkar bearing USN:2GP22CS039,are bonafide students of Government Engineering College
Majali, Karwar in partial fulfilment for the award of Bachelor of Engineering (V semester) in
Computer Science and Engineering of the Visvesvaraya Technological University, Belagavi during
the academic year 2024-2025.The mini project report has been approved as it satisfies the academic
requirements prescribed for the said degree.

Signature of the HOD Signature of the Guide Signature of the Principal

Prof. Dhulappa Chauhan Prof. Dhulappa Chauhan Dr. Shanthala B
HOD, Dept of CSE HOD, Dept of CSE Principal
GEC, Karwar GEC, Karwar GEC Karwar

Name of Examiner with date

1…………………………..
2………………………….
 ACKNOWLEDGEMENT

We give our high, respectful gratitude to our guide Prof. DHULAPPA

CHAUHAN, HOD, Dept of CSE, who have been our source of inspiration. Sir has been
especially enthusiastic in giving their opinions and critical reviews and has been the constant
driving force behind the completion of the project..

We have learnt a lot throughout this semester with many challenges yet valuable
experience in order to complete this task. We will remember their contribution forever.

We also thank our respected Principal Dr SHANTHALA B for her constant help
and support throughout.

Our special thanks to our faculty members who have supported us in making this
project a successful one.

We also take this opportunity to thank the technical staffs who have helped us a
lot in providing the software support and any other support whenever needed. My thanks and
appreciation also to my friends who have willingly help us with their ability.

DILEEP 2GP22CS014

SACHIN V GAONKAR 2GP22CS039

 ABSTRACT

The Text-To-Image Generator is a web-based application designed to dynamically fetch and

display images using the Unsplash API. This project enables users to generate images based on
textual prompts or retrieve random images, enhancing creative exploration and user engagement.
Developed using HTML, CSS, and JavaScript, the application provides a user-friendly interface
with features such as dynamic image loading, responsive design, and download functionality.

The system works by taking user input, sending an API request to Unsplash, and displaying high-
quality images in real time. Each image includes a Download option, allowing users to save the
content locally. A loading indicator ensures seamless user interaction while fetching data. The
application demonstrates effective integration of API-driven functionality with client-side
scripting, making it a powerful tool for visual inspiration, content creation, and exploration.

This project showcases the use of modern web development technologies and highlights the
importance of APIs in building interactive applications. Future enhancements include features like
pagination, user authentication, and customizable layouts to further optimize functionality and
user experience.

.
 TABLE OF CONTENTS

CHAPTERNO. CHAPTERNAME PAGENO.

1 INTRODUCTION 1-2
1.1OBJECTIVES

2 SYSTEM ANALYSIS 3
2.1ARCHITECTURE OF OPENAI'S
2.2 USE CASE ANALYSIS

3 REQUIREMENT SPECIFICATION 4
3.1HARDWARE REQUIREMENTS
3.2SOFTWARE REQUIREMENTS

4 SYSTEM DESIGN 5-8

4.1 WORK FLOW
4.2 LOGIN PAGE INTEGRATION
4.3 USECASE DIAGRAM
4.4 ER DIAGRAM

5 SNAPSHOT OF APPLICATION 9-11

CONCLUSION
REFERENCE
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

CHAPTER-1

INTRODUCTION

The Text-To-Image Generator is an interactive, web-based application designed to fetch

and display high-quality images in real time by leveraging the Unsplash API.[3] This tool
empowers users to explore a diverse range of visuals, whether for creative inspiration, image
collection, or general exploration. Users can input specific keywords (prompts) to generate
thematically relevant images or opt for random results to discover new and unexpected visuals[1].

Built using modern web technologies—HTML, CSS, and JavaScript—the application

delivers a seamless and engaging user experience[2]. The clean, responsive interface ensures
accessibility across devices, while intuitive features such as image downloads, dynamic loading
indicators, and organized grid-based layouts enhance usability. The integration of real-time API
interaction ensures that images are fetched dynamically, providing fresh content with every search
or reload[1].

By combining simplicity with functionality, the Random Image Generator serves as a

versatile tool for designers, content creators, and curious users seeking visually rich content,
setting a foundation for further enhancements and real-world applications[1].

Dept.ofCSE,GECKARWAR 2024-2025 1
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

1.1 OBJECTIVES

The primary objectives of the Text-To-Image Generator are as follows:

 Dynamic Image Fetching: Utilize the Unsplash API to retrieve high-quality images either based
on user-provided keywords (prompts) or randomly, ensuring fresh and diverse content with every
request.
 User-Friendly Interface: Design an intuitive and interactive front-end interface that enables
seamless navigation, effortless input of prompts, and smooth viewing of fetched images.
 Image Download Functionality: Provide users with a one-click option to download images
directly to their devices, offering convenience for saving and reusing visuals.
 Responsive Design: Implement a clean, flexible layout using modern CSS techniques to ensure
consistent and optimal viewing experiences across various screen sizes and devices, from desktops
to smartphones.

Dept.ofCSE,GECKARWAR 2024-2025 2
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

CHAPTER-2

SYSTEM ANALYSIS

2.1 Architecture of OpenAI's DALL·E

 Input Layer: Accepts textual descriptions (prompts) as inputs.

 Transformer-Based Models: Utilizes GPT-like transformer models to understand the context of
the text.
 Image Generation Module: Integrates GANs or Diffusion Models to create visually appealing
images.
 Output Layer: Delivers high-quality, generated images.

2.2 Use Case Analysis

 Creative Design: Facilitates concept art and graphic design without the need for manual effort.
 E-Commerce: Generates product visuals based on descriptions, reducing reliance on photography.
 Education: Creates illustrative visuals for complex concepts in learning modules.
 Media and Entertainment: Assists in generating movie scenes, animations, and character designs

Dept.ofCSE,GECKARWAR 2024-2025 3
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

CHAPTER-3

REQUIREMENT SPECIFICATION

3.1 HARDWAREREQUIREMENTS

• Processor Intel Core i3 or higher

• Ram 4 GB or higher
• SystemType Windows11/Linux
• Storage 500 MB (browser cache)

3.2 SOFTWARE REQUIREMENTS

• Web Browser : Chrome, Firefox, or Edge

(latest version)
• Front End :HTML, CSS, JS
• DataBase : MySQL

• ApplicationServer : XAMPP

Dept.ofCSE,GECKARWAR 2024-2025 4
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

CHAPTER-4

SOFTWARE DESIGN

4.1 Workflow Design

1. Text Input: User provides a natural language description.

2. Text Processing: The transformer model tokenizes and encodes the input.
3. Image Synthesis: The generator creates an image matching the description.
4. Output Rendering: The generated image is refined and displayed to the user.
5. User Login: Secure login page validates credentials and stores user data in a MySQL database
using XAMPP.

4.2 Login Page Integration

The system includes a login page to ensure user authentication and secure access to the text-to-image
generation platform. The data is stored locally using MySQL through XAMPP.

Steps for Login System Design:

1. User Interface (Frontend):

o Developed using HTML and CSS for structure and styling.

o Input fields for "Username" and "Password".

o "Login" and "Register" buttons for user actions.

2. Server-Side Processing (Backend):

o PHP scripts handle form submissions and communicate with the MySQL database.

o User credentials are validated against stored data for authentication.

Dept.ofCSE,GECKARWAR 2024-2025 5
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

3.Database Structure:

o Database Name: login_system

o Table Name: users

Field Type Description

id Auto-incremented
INT (Primary)
User ID
username Stores user login
VARCHAR(100)
names
password Hashed user
VARCHAR(255)
password for security

4.Data Flow:

o Step 1: User enters login credentials.

o Step 2: PHP sends credentials to the MySQL database.

o Step 3: MySQL verifies the user credentials.

o Step 4: On successful login, access is granted; otherwise, an error message is displayed.

Dept.ofCSE,GECKARWAR 2024-2025 6
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

4.3USECASEDIAGRAM:-

 Actors: User, Admin

 Functions:
o Provide Login Credentials

o Validate User

o Generate Image

o Store Image History

Fig:-4.3 Usecase diagram of Customer

Dept.ofCSE,GECKARWAR 2024-2025 7
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

4.4 ER DIAGRAM :

Fig:-4.4 Entity-Relationship Diagram

Dept.ofCSE,GECKARWAR 2024-2025 8
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

CHAPTER-5

SNAPSHOTS

HOME PAGE:

Fig:- 5.1 Home Page

Dept.ofCSE,GECKARWAR 2024-2025 9
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

USER REGISTER

Fig:- 5.1 User Register

USER LOGIN:

Fig:- 5.1 User Login

Dept.ofCSE,GECKARWAR 2024-2025 10
 TEXT-TO-IMAGE GENERTOR USING OPEN-AI

PROMPT ENTERED:

fig: Prompt Image Generated

Dept.ofCSE,GECKARWAR 2024-2025 11
 CONCLUSION

The integration of secure login systems with AI-driven text-to-image generation tools like
DALL-E represents a significant leap in technological innovation. By combining the power of AI
with robust security measures, this project opens up new possibilities for creative expression, design
automation, and productivity enhancement. As AI continues to evolve, we can anticipate even more
sophisticated and versatile applications, revolutionizing industries such as advertising, gaming, and
film.

This project demonstrates the potential of merging powerful AI tools with secure user
authentication. By providing a secure platform for users to access and utilize DALL-E, we empower
individuals and businesses to explore their creativity without compromising data privacy. The
streamlined user experience, coupled with the rapid generation of high-quality images, fosters
innovation and accelerates the design process.

Beyond its technical significance, this project has the potential to drive significant social and
economic impact. By democratizing access to advanced image generation tools, we empower
individuals and small businesses to compete with larger organizations. The automation of design
tasks can lead to cost savings and increased efficiency, while the generation of unique visual content
can stimulate creativity and innovation.
 REFERENCES

[1] OpenAI:

https://openai.com/dall-e

[2]MySQL and PHP Tutorials:

https://www.w3schools.com

[3] Unsplash API Documentatimentation:

https://unsplash.com/documentation

[4]CSS Styling Guide - W3Schools:

https://www.w3schools.com/css/

[5]HTML and Web Development - MDN:

httoper.mozilla.org/en-US/docs/Web/HTML