1

> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <
1
production and broaden the possibilities for artistic expression

Preparation of Papers for by enabling users to create complex graphics just by entering
text prompts. Artificial intelligence (AI) picture generators,

IEEE JOURNALS driven by cutting-edge technologies like diffusion models and

Generative Adversarial Networks (GANs), can interpret and
render a wide range of concepts in a matter of seconds, from
(July 2018) surreal landscapes to hyper-realistic portraits. AI image
First A. Author, Second B. Author, Jr., and Third C. generators have become indispensable tools as the need for
Author, Member, IEEE distinctive and captivating visual material expands across a
variety of industries, including advertising, entertainment,
Abstract—The project “Image Generator using Generative education, and gaming. They not only increase output but also
AI” as the name suggests, aims to step into the new cutting edge stimulate creativity by giving designers and artists new
techniques of Generative AI and revolutionize the concept of an concepts and ideas that they might not have thought of using
AI Image Generator. Generative AI leverages the use of
advanced Machine Learning models to create new images from more conventional techniques. But this technical development
scratch. At the heart of Generative AI is Generative Adversarial also brings up significant issues related to copyright,
Networks (GANs) which consists of two parts, one is the authorship, and the morality of AI-generated art. In order to
generator where a network creates images and a discriminator
where the network evaluates their authenticity. The generator
better understand AI picture generation, this paper will look at
improves iteratively, producing increasingly realistic images that its many uses, how these tools function, and the advantages
the discriminator cannot distinguish from the real ones.Such they provide for the creative industry. In addition, we will
advancements show promising results for various applications examine the difficulties and moral dilemmas raised by this
like art creation, medical imaging, and virtual reality. Generative
AI models are pushing the boundaries of what's possible in visual technology, offering a comprehensive assessment of its
content creation, blending creativity with computational prowess. implications for the development of digital creativity in the
In our project we have learned from the previous researches future. Understanding AI image generators' advantages and
conducted on Generative AI and concepts already used in AI
disadvantages will help us better negotiate the changing
Image Generators and have implemented some of our own ideas
and improvised on the application to make it more user friendly dynamic between technology and artistic expression. But this
and fulfilling the need of different choices. technical development also brings up significant issues related
to copyright, authorship, and the morality of AI-generated art.
Index Terms—About four key words or phrases in
In order to better understand AI picture generation, this paper
alphabetical order, separated by commas. For a list of suggested
keywords, send a blank e-mail to keywords@ieee.org or visit will look at its many uses, how these tools function, and the
http://www.ieee.org/organizations/pubs/ani_prod/keywrd98.txt advantages they provide for the creative industry. In addition,
we will examine the difficulties and moral dilemmas raised by
this technology, offering a comprehensive assessment of its
I. INTRODUCTION
implications for the development of digital creativity in the
future. Understanding AI image generators' advantages and

A rtificial intelligence picture generators are leading the

disadvantages will help us better negotiate the changing
dynamic between technology and artistic expression.
way in this new era of creativity brought about by AI's rapid
progress. These cutting-edge tools democratize picture

1Manuscript received October 9, 2001. (Write the date on which you

submitted your paper for review.) This work was supported in part by the U.S. II. PROCEDURE FOR PAPER SUBMISSION
Department of Commerce under Grant BS123456 (sponsor and financial
support acknowledgment goes here). Paper titles should be written in A. Review Stage
uppercase and lowercase letters, not all uppercase. Avoid writing long Please go to http://mc.manuscriptcentral.com/jqe-ieee to
formulas with subscripts in the title; short formulas that identify the elements
are fine (e.g., "Nd–Fe–B"). Do not write “(Invited)” in the title. Full names of submit your manuscript. Biographies are optional during the
authors are preferred in the author field, but are not required. Put a space review stage but should your paper need to be revised, we will
between authors’ initials. need ALL bios submitted with your revised paper. All revised
F. A. Author is with the National Institute of Standards and Technology,
Boulder, CO 80305 USA (corresponding author to provide phone: 303-555-
papers should include a copy of the revised paper
5555; fax: 303-555-5555; e-mail: author@ boulder.nist.gov). UNDERLINED to show changes as well as a clean copy
S. B. Author, Jr., was with Rice University, Houston, TX 77005 USA. He without the underlines.
is now with the Department of Physics, Colorado State University, Fort
Collins, CO 80523 USA (e-mail: author@lamar.colostate.edu). B. Final Stage
T. C. Author is with the Electrical Engineering Department, University of
Colorado, Boulder, CO 80309 USA, on leave from the National Research When you submit your final version (after your paper has
Institute for Metals, Tsukuba, Japan (e-mail: author@nrim.go.jp).
 2
> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <

been accepted), print it in two-column format, including picas wide). We recommend that you avoid sizing figures less
figures and tables. Also, a complete list of contact information than one column wide, as extreme enlargements may distort
for all authors should be included. Include full mailing your images and result in poor reproduction. Therefore, it is
addresses, telephone numbers, fax numbers, and e-mail better if the image is slightly larger, as a minor reduction in
addresses. This information will be used to send each author a size should not have an adverse affect the quality of the image.
complimentary copy of the journal in which the paper appears.
In addition, designate one author as the “corresponding Size of Author Photographs
author.” This is the author to whom proofs of the paper will be The final printed size of an author photograph is exactly
sent. Proofs are sent to the corresponding author only. 1 inch wide by 1 1/4 inches long (6 picas × 7 1/2 picas). Please
ensure that the author photographs you submit are
proportioned similarly. If the author’s photograph does not
appear at the end of the paper, then please size it so that it is
proportional to the standard size of 1 9/16 inches wide by
C. Figures 2 inches long (9 1/2 picas × 12 picas). JPEG files are only
Format and save your graphic images using a suitable accepted for author photos.
graphics processing program that will allow you to create the
images as PostScript (PS), Encapsulated PostScript (EPS), or How to create a PostScript File
Tagged Image File Format (TIFF), sizes them, and adjusts the First, download a PostScript printer driver from
resolution settings. If you created your source files in one of http://www.adobe.com/support/downloads/pdrvwin.htm (for
the following you will be able to submit the graphics without Windows) or from http://www.adobe.com/support/downloads/
converting to a PS, EPS, or TIFF file: Microsoft Word, pdrvmac.htm (for Macintosh) and install the “Generic
Microsoft PowerPoint, Microsoft Excel, or Portable Document PostScript Printer” definition. In Word, paste your figure into
Format (PDF). a new document. Print to a file using the PostScript printer
driver. File names should be of the form “fig5.ps.” Use Open
D. Electronic Image Files (Optional) Type fonts when creating your figures, if possible. A listing of
the acceptable fonts are as follows: Open Type Fonts: Times
Roman, Helvetica, Helvetica Narrow, Courier, Symbol,
Import your source files in one of the following: Microsoft
Palatino, Avant Garde, Bookman, Zapf Chancery, Zapf
Word, Microsoft PowerPoint, Microsoft Excel, or Portable
Dingbats, and New Century Schoolbook.
Document Format (PDF); you will be able to submit the
graphics without converting to a PS, EPS, or TIFF files. Image
Print Color Graphics Requirements
quality is very important to how yours graphics will
IEEE accepts color graphics in the following formats: EPS,
reproduce. Even though we can accept graphics in many
PS, TIFF, Word, PowerPoint, Excel, and PDF. The resolution
formats, we cannot improve your graphics if they are poor
of a RGB color TIFF file should be 400 dpi.
quality when we receive them. If your graphic looks low in
When sending color graphics, please supply a high quality
quality on your printer or monitor, please keep in mind that
hard copy or PDF proof of each image. If we cannot achieve a
cannot improve the quality after submission.
satisfactory color match using the electronic version of your
files, we will have your hard copy scanned. Any of the files
types you provide will be converted to RGB color EPS files.
If you are importing your graphics into this Word template,
please use the following steps:
Web Color Graphics
Under the option EDIT select PASTE SPECIAL. A dialog
IEEE accepts color graphics in the following formats: EPS,
box will open, select paste picture, then click OK. Your figure
PS, TIFF, Word, PowerPoint, Excel, and PDF. The resolution
should now be in the Word Document.
of a RGB color TIFF file should be at least 400 dpi.
If you are preparing images in TIFF, EPS, or PS format,
Your color graphic will be converted to grayscale if no
note the following. High-contrast line figures and tables
separate grayscale file is provided. If a graphic is to appear in
should be prepared with 600 dpi resolution and saved with no
print as black and white, it should be saved and submitted as a
compression, 1 bit per pixel (monochrome), with file names in
black and white file. If a graphic is to appear in print or on
the form of “fig3.tif” or “table1.tif.”
IEEE Xplore in color, it should be submitted as RGB color.
Photographs and grayscale figures should be prepared with
300 dpi resolution and saved with no compression, 8 bits per
Graphics Checker Tool
pixel (grayscale).
The IEEE Graphics Checker Tool enables users to check
graphic files. The tool will check journal article graphic files
against a set of rules for compliance with IEEE requirements.
Sizing of Graphics
These requirements are designed to ensure sufficient image
Most charts graphs and tables are one column wide (3 1/2
quality so they will look acceptable in print. After receiving a
inches or 21 picas) or two-column width (7 1/16 inches, 43
 3
> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <

graphic or a set of graphics, the tool will check the files figures. Do not put captions in “text boxes” linked to the
against a set of rules. A report will then be e-mailed listing figures. Do not put borders around the outside of your
each graphic and whether it met or failed to meet the figures. Use the abbreviation “Fig.” even at the beginning of a
requirements. If the file fails, a description of why and sentence. Do not abbreviate “Table.” Tables are numbered
instructions on how to correct the problem will be sent. The with Roman numerals.
IEEE Graphics Checker Tool is available at Color printing of figures is available, but is billed to the
http://graphicsqc.ieee.org/ authors. Include a note with your final paper indicating that
For more Information, contact the IEEE Graphics H-E-L-P you request and will pay for color printing. Do not use color
Desk by e-mail at graphics@ieee.org. You will then receive an unless it is necessary for the proper interpretation of your
e-mail response and sometimes a request for a sample graphic figures. If you want reprints of your color article, the reprint
for us to check. order should be submitted promptly. There is an additional
charge for color reprints. Please note that many IEEE
journals now allow an author to publish color figures on
E. Copyright Form
Xplore and black and white figures in print. Contact your
An IEEE copyright form should accompany your final society representative for specific requirements.
submission. You can get a .pdf, .html, or .doc version at Figure axis labels are often a source of confusion. Use
http://www.ieee.org/copyright. Authors are responsible for words rather than symbols. As an example, write the quantity
obtaining any security clearances. “Magnetization,” or “Magnetization M,” not just “M.” Put
units in parentheses. Do not label axes only with units. As in
Fig. 1, for example, write “Magnetization (A/m)” or
III. MATH “Magnetization (A m−1),” not just “A/m.” Do not label axes
If you are using Word, use either the Microsoft Equation with a ratio of quantities and units. For example, write
Editor or the MathType add-on (http://www.mathtype.com) “Temperature (K),” not “Temperature/K.”
for equations in your paper (Insert | Object | Create New | Multipliers can be especially confusing. Write
Microsoft Equation or MathType Equation). “Float over text” “Magnetization (kA/m)” or “Magnetization (10 3 A/m).” Do
should not be selected. not write “Magnetization (A/m) × 1000” because the reader
would not know whether the top axis label in Fig. 1 meant
16000 A/m or 0.016 A/m. Figure labels should be legible,
IV. UNITS approximately 8 to 12 point type.
Use either SI (MKS) or CGS as primary units. (SI units are B. References
strongly encouraged.) English units may be used as secondary
Number citations consecutively in square brackets [1]. The
units (in parentheses). This applies to papers in data
sentence punctuation follows the brackets [2]. Multiple
storage. For example, write “15 Gb/cm2 (100 Gb/in2).” An
references [2], [3] are each numbered with separate brackets
exception is when English units are used as identifiers in trade,
[1]–[3]. When citing a section in a book, please give the
such as “3½-in disk drive.” Avoid combining SI and CGS
relevant page numbers [2]. In sentences, refer simply to the
units, such as current in amperes and magnetic field in
reference number, as in [3]. Do not use “Ref. [3]” or
oersteds. This often leads to confusion because equations do
“reference [3]” except at the beginning of a sentence:
not balance dimensionally. If you must use mixed units,
“Reference [3] shows ... .” Please do not use automatic
clearly state the units for each quantity in an equation.
endnotes in Word, rather, type the reference list at the end of
The SI unit for magnetic field strength H is A/m. However,
the paper using the “References” style.
if you wish to use units of T, either refer to magnetic flux
Number footnotes separately in superscripts (Insert |
density B or magnetic field strength symbolized as µ 0H. Use
Footnote).2 Place the actual footnote at the bottom of the
the center dot to separate compound units, e.g., “A·m2.”
column in which it is cited; do not put footnotes in the
reference list (endnotes). Use letters for table footnotes (see
Table I).
V. HELPFUL HINTS
Please note that the references at the end of this document
A. Figures and Tables are in the preferred referencing style. Give all authors’ names;
Because IEEE will do the final formatting of your paper, do not use “et al.” unless there are six authors or more. Use a
you do not need to position figures and tables at the top and space after authors’ initials. Papers that have not been
bottom of each column. Large figures and tables may span published should be cited as “unpublished” [4]. Papers that
both columns. Place figure captions below the figures; place have been accepted for publication, but not yet specified for an
table titles above the tables. If your figure has two parts, issue should be cited as “to be published” [5]. Papers that have
include the labels “(a)” and “(b)” as part of the artwork. Please been submitted for publication should be cited as “submitted
verify that the figures and tables you mention in the text 2It is recommended that footnotes be avoided (except for the unnumbered
actually exist. Please do not include captions as part of the footnote with the receipt date on the first page). Instead, try to integrate the
footnote information into the text.
 4
> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <

for publication” [6]. Please give affiliations and addresses for If you wish, you may write in the first person singular or
private communications [7]. plural and use the active voice (“I observed that ...” or “We
Capitalize only the first word in a paper title, except for observed that ...” instead of “It was observed that ...”).
proper nouns and element symbols. For papers published in Remember to check spelling. If your native language is not
translation journals, please give the English citation first, English, please get a native English-speaking colleague to
followed by the original foreign-language citation [8]. carefully proofread your paper.
C. Abbreviations and Acronyms
VI. SOME COMMON MISTAKES
Define abbreviations and acronyms the first time they are
The word “data” is plural, not singular. The subscript for
used in the text, even after they have already been defined in
the permeability of vacuum µ0 is zero, not a lowercase letter
the abstract. Abbreviations such as IEEE, SI, ac, and dc do not
“o.” The term for residual magnetization is “remanence”; the
have to be defined. Abbreviations that incorporate periods
adjective is “remanent”; do not write “remnance” or
should not have spaces: write “C.N.R.S.,” not “C. N. R. S.”
“remnant.” Use the word “micrometer” instead of “micron.” A
Do not use abbreviations in the title unless they are
graph within a graph is an “inset,” not an “insert.” The word
unavoidable (for example, “IEEE” in the title of this article).
“alternatively” is preferred to the word “alternately” (unless
D. Equations you really mean something that alternates). Use the word
Number equations consecutively with equation numbers in “whereas” instead of “while” (unless you are referring to
parentheses flush with the right margin, as in (1). First use the simultaneous events). Do not use the word “essentially” to
equation editor to create the equation. Then select the mean “approximately” or “effectively.” Do not use the word
“Equation” markup style. Press the tab key and write the “issue” as a euphemism for “problem.” When compositions
equation number in parentheses. To make your equations more are not specified, separate chemical symbols by en-dashes; for
compact, you may use the solidus ( / ), the exp function, or example, “NiMn” indicates the intermetallic compound
appropriate exponents. Use parentheses to avoid ambiguities Ni0.5Mn0.5 whereas “Ni–Mn” indicates an alloy of some
in denominators. Punctuate equations when they are part of a composition NixMn1-x.
sentence, as in Be aware of the different meanings of the homophones
“affect” (usually a verb) and “effect” (usually a noun),
(1) “complement” and “compliment,” “discreet” and “discrete,”
“principal” (e.g., “principal investigator”) and “principle”
Be sure that the symbols in your equation have been defined (e.g., “principle of measurement”). Do not confuse “imply”
before the equation appears or immediately following. and “infer.”
Italicize symbols (T might refer to temperature, but T is the Prefixes such as “non,” “sub,” “micro,” “multi,” and “ultra”
unit tesla). Refer to “(1),” not “Eq. (1)” or “equation (1),” are not independent words; they should be joined to the words
except at the beginning of a sentence: “Equation (1) is ... .” they modify, usually without a hyphen. There is no period
after the “et” in the Latin abbreviation “et al.” (it is also
E. Other Recommendations
italicized). The abbreviation “i.e.,” means “that is,” and the
Use one space after periods and colons. Hyphenate complex abbreviation “e.g.,” means “for example” (these abbreviations
modifiers: “zero-field-cooled magnetization.” Avoid dangling are not italicized).
participles, such as, “Using (1), the potential was calculated.” An excellent style manual and source of information for
[It is not clear who or what used (1).] Write instead, “The science writers is [9]. A general IEEE style guide and an
potential was calculated by using (1),” or “Using (1), we Information for Authors are both available at
calculated the potential.” http://www.ieee.org/web/publications/authors/transjnl/index.html
Use a zero before decimal points: “0.25,” not “.25.” Use
“cm3,” not “cc.” Indicate sample dimensions as “0.1 cm × 0.2
cm,” not “0.1 × 0.2 cm2.” The abbreviation for “seconds” is VII. EDITORIAL POLICY
“s,” not “sec.” Do not mix complete spellings and Do not submit a reworked version of a paper you have
abbreviations of units: use “Wb/m2” or “webers per square submitted or published elsewhere. Do not publish
meter,” not “webers/m2.” When expressing a range of values, “preliminary” data or results. The submitting author is
write “7 to 9” or “7-9,” not “7~9.” responsible for obtaining agreement of all coauthors and any
A parenthetical statement at the end of a sentence is consent required from sponsors before submitting a paper.
punctuated outside of the closing parenthesis (like this). (A IEEE TRANSACTIONS and JOURNALS strongly discourage
parenthetical sentence is punctuated within the parentheses.) courtesy authorship. It is the obligation of the authors to cite
In American English, periods and commas are within relevant prior work.
quotation marks, like “this period.” Other punctuation is The Transactions and Journals Department does not publish
“outside”! Avoid contractions; for example, write “do not” conference records or proceedings. The T RANSACTIONS does
instead of “don’t.” The serial comma is preferred: “A, B, and publish papers related to conferences that have been
C” instead of “A, B and C.” recommended for publication on the basis of peer review. As a
 5
> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <

matter of convenience and service to the technical community, APPENDIX

these topical papers are collected and published in one issue of Appendixes, if needed, appear before the acknowledgment.
the TRANSACTIONS.
At least two reviews are required for every paper submitted. ACKNOWLEDGMENT
For conference-related papers, the decision to accept or reject
The preferred spelling of the word “acknowledgment” in
a paper is made by the conference editors and publications
American English is without an “e” after the “g.” Use the
committee; the recommendations of the referees are advisory
singular heading even if you have many acknowledgments.
only. Undecipherable English is a valid reason for rejection.
Avoid expressions such as “One of us (S.B.A.) would like to
Authors of rejected papers may revise and resubmit as new
thank ... .” Instead, write “F. A. Author thanks ... .” Sponsor
papers, whereupon they will be reviewed by two new referees.
and financial support acknowledgments are placed in the
unnumbered footnote on the first page, not here.
VIII. PUBLICATION PRINCIPLES
REFERENCES
The contents of IEEE TRANSACTIONS and JOURNALS are
[1] Zhang, M., Li, C., & Zhou, Z. (2021). Text to image
peer-reviewed and archival. The T RANSACTIONS publishes
synthesis using multigenerator text conditioned generative
scholarly articles of archival value as well as tutorial
adversarial networks. Multimedia Tools and Applications, 80,
expositions and critical reviews of classical subjects and topics
7789-7803.
of current interest. [2] Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang,
Authors should consider the following points:
X., & He, X. (2018). Attngan: Fine-grained text to image
1) Technical papers submitted for publication must advance
generation with attentional generative adversarial networks. In
the state of knowledge and must cite relevant prior work.
2) The length of a submitted paper should be commensurate Proceedings of the IEEE conference on computer vision and
with the importance, or appropriate to the complexity, of pattern recognition (pp. 13161324).
the work. For example, an obvious extension of [3]Zhang, C., Zhang, C., Zhang, M., & Kweon, I. S. (2023).
previously published work might not be appropriate for Text-to-image diffusion models in generative ai: A survey.
publication or might be adequately treated in just a few arXiv preprint arXiv:2303.07909.
pages. [4] Beyan, E. V. P., & Rossy, A. G. C. (2023). A review of AI
3) Authors must convince both peer reviewers and the image generator: influences, challenges, and future prospects
editors of the scientific and technical merit of a paper; the for architectural field. Journal of Artificial Intelligence in
Architecture, 2(1), 53-65.
standards of proof are higher when extraordinary or
[5] Oppenlaender, J. (2022, November). The creativity of text-
unexpected results are reported.
to-image generation. In Proceedings of the 25th international
4) Because replication is required for scientific progress,
academic mindtrek conference (pp. 192-202). [6]Chen, W.,
papers submitted for publication must provide sufficient Hu, H., Saharia, C., & Cohen, W. W. (2022). Re-imagen:
information to allow readers to perform similar Retrievalaugmented text-to-image generator. arXiv preprint
experiments or calculations and use the reported results. arXiv:2209.14491.
Although not everything need be disclosed, a paper must ALL BIOS ARE REQUIRED
contain new, useable, and fully described information. For
example, a specimen’s chemical composition need not be First A. Author (M’76–SM’81–F’87) and the other authors may include
reported if the main purpose of a paper is to introduce a biographies at the end of regular papers. Biographies are often not included in
new measurement technique. Authors should expect to be conference-related papers. This author became a Member (M) of IEEE in
challenged by reviewers if the results are not supported by 1976, a Senior Member (SM) in 1981, and a Fellow (F) in 1987. The first
paragraph may contain a place and/or date of birth (list place, then date). Next,
adequate data and critical details. the author’s educational background is listed. The degrees should be listed
5) Papers that describe ongoing work or announce the latest with type of degree in what field, which institution, city, state, and country,
technical achievement, which are suitable for presentation and year degree was earned. The author’s major field of study should be
lower-cased.
at a professional conference, may not be appropriate for The second paragraph uses the pronoun of the person (he or she)
publication in a TRANSACTIONS or JOURNAL. and not the author’s last name. It lists military and work experience, including
summer and fellowship jobs. Job titles are capitalized. The current job must
have a location; previous positions may be listed without one. Information
concerning previous publications may be included. Try not to list more than
IX. CONCLUSION three books or published articles. The format for listing publishers of a book
within the biography is: title of book (city, state: publisher name, year) similar
A conclusion section is not required. Although a conclusion to a reference. Current and previous research interests end the paragraph.
may review the main points of the paper, do not replicate the The third paragraph begins with the author’s title and last name
abstract as the conclusion. A conclusion might elaborate on (e.g., Dr. Smith, Prof. Jones, Mr. Kajor, Ms. Hunter). List any memberships in
professional societies other than the IEEE. Finally, list any awards and work
the importance of the work or suggest applications and for IEEE committees and publications. If a photograph is provided, the
extensions. biography will be indented around it. The photograph is placed at the top left
of the biography. Personal hobbies will be deleted from the biography.