From Image To Imagination Exploring The Impact of Generative AI On Cultural Translation in Jewelry Design

sustainability
Article
From Image to Imagination: Exploring the Impact of Generative
AI on Cultural Translation in Jewelry Design
Yanru Lyu 1,2 , Minghong Shi 3, *, Yanbo Zhang 4 and Rungtai Lin 5
1 Department of Digital Media Arts, School of Design and Arts, Beijing Technology and Business University,
Beijing 102488, China; lyuyanru@gmail.com
2 Key Laboratory of Encyclopedia Knowledge Fusion Innovation Publishing Project, Beijing 100037, China
3 School of Design and Innovation, Shenzhen Technology University, Shenzhen 518118, China
4 Department of Textile, Apparel Design and Merchandizing, Louisiana State University,
Baton Rouge, LA 70803, USA; yzha197@lsu.edu
5 Graduate School of Creative Industry Design, National Taiwan University of Arts, New Taipei 220307, Taiwan;
rtlin@mail.ntua.edu.tw
* Correspondence: shiminghong@sztu.edu.cn
Abstract: The current proliferation of artificial intelligence (AI) is prominently shaping the design
industry. Generative AI, such as text-to-image and image-to-image models, has gained widespread
use, notably for its efficiency and quality improvements. However, their potential to aid in cultural
translation within creative design is underexplored. To address the existing gap, this study aims
to assess the impact of generative AI on cultural translation within jewelry design. Specifically,
a comprehensive study was conducted through a design-action experiment, collecting 46 student
designers’ design-action data and self-reports, and enlisting the evaluation from 30 design experts.
The findings highlight the substantial influence of generative AI on the ideation phase of jewelry
design, especially in depth rather than breadth, and in the shape factor at the technical level such as
detailization and unexpected composition. Leveraging AI image generators has shifted the designer’s
focus from technical tasks to strategic decisions related to visual appeal, cognitive engagement, and
emotional resonance. Furthermore, the challenges inherent in human–AI collaboration have been
revealed, stemming from communication difficulties and the risk of fixating on specific details to
stylistic constraints. Based on data analysis, a novel hybrid model regarding human–AI co-creation
on cultural translation in jewelry design is proposed. Overall, this current study offers a valuable
Citation: Lyu, Y.; Shi, M.; Zhang, Y.;
reference point to future research in terms of examining the effect of emerging technologies on
Lin, R. From Image to Imagination:
cultural translation in creative fields.
Exploring the Impact of Generative AI
on Cultural Translation in Jewelry
Keywords: generative AI; imagination; cultural translation; image stimulation; design fixation;
Design. Sustainability 2024, 16, 65.
https://doi.org/10.3390/su16010065
jewelry design
Academic Editor: Yoshiki Shimomura
Received: 5 November 2023

Revised: 14 December 2023 1. Introduction
Accepted: 18 December 2023 The process of design is characterized by its intricate and elusive nature, but creativity
Published: 20 December 2023 is manifested in the whole process, especially the early stages of design. Ideation in design,
alternatively, creative idea generation, always plays a vital role in the early stages of
production design. With the accelerating development of generative artificial intelligence
(AI) algorithms in recent years, its application has achieved extraordinary outcomes in
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
different fields, including the creative design [1]. To date, designers can harness and
This article is an open access article
interact with various text-to-image or image-to-image Al models (e.g., Midjourney [2],
distributed under the terms and Stable Diffusion [3], OpenAI’s DALL-E 2 [4], and Deep Dream Generator [5]), which could
conditions of the Creative Commons facilitate in augmenting creativity and stimulating visual imagination and ideation [6,7].
Attribution (CC BY) license (https:// Jewelry, being a highly personalized and swiftly iterative product category, necessitates
creativecommons.org/licenses/by/ a multitude of creative concepts to flourish, thus rendering it a pivotal domain suitable
4.0/). for the implementation of AI. It is essential to recognize that this specific product category
Sustainability 2024, 16, 65. https://doi.org/10.3390/su16010065 https://www.mdpi.com/journal/sustainability

Sustainability 2024, 16, 65 2 of 20
transcends mere adornment and extends to encapsulate emotions and attitudes [8]. As
Hong Kong jewelry designer Dickson Yewn stated, jewelry is “the new way to interpret a
culture” [9]. Social progress and cultural development have an obvious influence on the
forms, functions, and meanings of jewelry designs [10]. Cultural sustainability indicates
the capacity to maintain and perpetuate cultural beliefs, practices, and heritage, while also
ensuring the continuation of culture in the future [11]. Within the realm of design, cultural
value can be embedded in products through creative design, which involves integrating
cultural elements into new artistic forms to pass on multiple cultures to consumers and
activate the cultural value [12,13]. However, the potential of human–AI collaboration in
setting cultural translation as a design goal has not yet received wide attention.
To fill the identified research gap, this study aims to investigate and examine how
generative AI technology can affect culture translation in the jewelry design process, the
designers’ mindsets, and the outcomes. To achieve the research purpose, the following
three research questions (RQs) were proposed:
RQ1: How can generative AI affect culture translation in the jewelry design process
during the early stages of ideation?
RQ2: How effective is generative AI in augmenting the design ideation during cultural
translation?
RQ3: What are the typical challenges in the human–AI collaboration?
An experimental study was performed, including 46 jewelry designers tasked with
executing two design assignments inspired by Chinese aesthetics. The first task involved
employing conventional design techniques, while the second task necessitated the use of AI-
generated images to stimulate the ideation process. Data collection encompassed three primary
sources, namely, design activity records, designers’ self-reported insights, and evaluations
from expert design assessors. According to the data analysis results, a model of human–AI
co-creation for culture translation in jewelry design was put forward, which is conducive to
providing a new reference for cultural sustainability in the era of artificial intelligence.
Figure 1 reveals that this study can be divided into three parts. In the first part,
a literature review was performed to explore the research framework for the impact of
generative AI on cultural translation in jewelry design. In the second part, 52 designers
were invited to create following the ideation task. The third section describes self-reported
data from designers, design outcomes, and evaluation results from experts, which were
collected for analysis and discussion. Finally, the conclusions of this study are provided.
Figure
Figure1.1.The
Theprocedures used
procedures in this
used study.
in this study.
2. Literature Review
The literature review consists of three parts that support AI-augmentation research
on the creative process of cultural translation in jewelry design, including computer-aided
design, the activities in human–AI collaboration, and cultural translation in jewelry de-
sign.
2. Literature Review
The literature review consists of three parts that support AI-augmentation research
on the creative process of cultural translation in jewelry design, including computer-aided
design, the activities in human–AI collaboration, and cultural translation in jewelry design.
2.1. Computer-Aided Design

Technology is of great importance in the design process, providing designers with a
series of computer-aided design (CAD) tools, including graphic software, 3D modeling soft-
ware, and digital rendering platforms. The CAD for concept generation can be categorized
into three types according to their potential roles in the human–computer collaborative
relationship: guide, stimulation, and generation [14]. The methods to guide are instruc-
tively involved in the generation of design concepts, which aim to provide design rules
or guidelines for the activities of the designers, such as team-based brainstorming and
mind mapping. Stimulation refers to knowledge-based methods and visual stimuli like
images and sketches, which can influence design performance [15]. Generation denotes
that designers can use various software to draw sketches, pictures, or three-dimensional
prototypes, which is a crucial step in shaping creativity and can help designers further
communicate and evaluate ideas [16].
With the rapid advancement in generative AI technology in recent years, more in-
telligent new design tools and functions are emerging, which then integrate a series of
generative AI models such as generative pre-trained transformers (GPTs), generative deep
models (GDMs), and generative adversarial networks (GANs) [17,18]. These have received
increasing interest from the design community, including the field of jewelry design. Gen-
erative AI tools represented by Midjourney [2] and Stable Diffusion [3] can help designers
quickly complete designs with high accuracy and repeatability. They use prompts as in-
puts combined with image generation algorithms with large language models to facilitate
text-guided image generation. The basic logic is to combine or merge a large number of
ideas to produce much stronger ones [6].
Additionally, increasing studies concentrate on the challenges and opportunities of
human–AI collaboration in diverse contexts [19–21]. Based on some empirical studies, the
AI agent assists designers in diversifying their solutions to fulfill the design objectives and
presents great potential to guide more explorative design strategies [22,23]. However, in
terms of generative AI, there is a great limitation that they are currently only capable of
learning and generating spatially visualized representations of design concepts based on
training data sets, which are mainly helpful for detail design and may cause design fixation
if applied in earlier stages [16].
Although CAD has been widely used in jewelry design to improve efficiency, the
current system focuses more on quick modeling (e.g., Rhinoceros 3D, Blender, ZBrush).
There were few tools to assist in generating conceptual design before the emergence of
generative AI. An earlier AI-design practice named “the chair project”, took generative
adversarial neural networks (GANs) as automatisms to stimulate the imagination of human
designers [24]. Limited by the washout problem of GANs, generative images still need
designers to handle most visualization tasks and to add details based on design principles
and creativity. The latest applications of AI are to generate visual images from natural
language descriptions and initial image guides, which can create thousands of higher-
quality images with minimal effort [6].
The use of new technology forces designers to broaden their understanding of the
design process and adapt their methods, ultimately leading to the potential generation
of innovative products [25,26]. A novel form of production is based on past models but
only comes into being in response to individual demand. Therefore, the advantages and
design limitations brought by AI technology make human–computer interaction more
complex. While there is methodological readiness for designing with CAD, the nuances of
human–AI collaboration need to be further explored from the perspective of the workflow
in generative AI-augmented design creativity (Figure 2). The mapping from potential
innovative products [25,26]. A novel form of production is based on past models but only
comes into being in response to individual demand. Therefore, the advantages and design
limitations brought by AI technology make human–computer interaction more complex.
While there is methodological readiness for designing with CAD, the nuances of human–
Sustainability 2024, 16, 65
AI collaboration need to be further explored from the perspective of the workflow in4gen-of 20
erative AI-augmented design creativity (Figure 2). The mapping from potential ideas to
specific elements is closely associated with the experience and knowledge of the creator
ideas to specific elements is closely associated with the experience and knowledge of the
[21]. After the translation from inputted elements such as images or text description, the
creator [21]. After the translation from inputted elements such as images or text description,
AI model handles the next stage to decoding, latent diffusion, and encoding in the pixel
the AI model handles the next stage to decoding, latent diffusion, and encoding in the pixel
space to generate numerous new related images. Both training data sets and parameter
space to generate numerous new related images. Both training data sets and parameter
settings influence the outputs. Moreover, it may bring positive value, such as guidance,
settings influence the outputs. Moreover, it may bring positive value, such as guidance,
stimulation, and generation, while also having an impact on design fixation.
stimulation, and generation, while also having an impact on design fixation.
2. The workflow in generative

Figure 2. generative AI-augmented
AI-augmented design
design creativity.
creativity.
2.2. Activities in Human–AI Collaboration

2.2. Activities in Human–AI Collaboration
In Cross’s earlier studies, he found that seemingly, the only ”positive” effect of CAD
In Cross’s earlier studies, he found that seemingly, the only ”positive” effect of CAD
was to speed up the design process, while reducing the person-power required in the
was to speed up the design process, while reducing the person-power required in the team
team [27]. However, he believed human–machine interaction would efficiently produce
[27]. However, he believed human–machine interaction would efficiently produce design
design solutions better than that which a human or a machine could produce alone. To find
solutions better than that which a human or a machine could produce alone. To find the
the answer to whether the machine can design, it is necessary to analyze the design activities
answer to whether the machine can design, it is necessary to analyze the design activities
of people [28]. Unlike conventional liner technology that achieves one outcome based on
of people
one action,[28].
AI Unlike conventional
poses challenges liner
to the technology
creative thatand
process achieves one outcome
workflow, based by
characterized on
one action, AI poses challenges to the creative process and workflow, characterized
its learning pattern and random generation [29]. Computer design research informs us by its
concerning designers’ thinking [28]. Facing infinite and limitless sources of information,
requirements, wants and needs, limitations, and opportunities, the designer has to make all
kinds of decisions and judgments [30]. Numerous studies on design practice have indicated
that designers who can handle complex design situations successfully use design thinking
and activities [31,32]. The utilization of emerging technologies stimulates designers to
expand their understanding of the design process and alter their design methods, which
in turn has potentially generated new products [26]. Moreover, incorporating AI into
products, services, and systems is complex, requiring the attention of the design discipline,
and the initial answers might be hidden in the design cognition [33].
The design process involves a continuous series of decision-making activities that
collectively shape a final outcome [34]. Design as research is an approach that combines
the principles of design and research methodologies to address complex problems and
generate new knowledge. It involves using design processes and methods to investigate,
explore, and understand problems, as well as to propose and test potential solutions [35,36].
Designing is intimately tied to new technologies that generate a complex set of decision
points for designers. The changes, problems, and solutions of traditional design influenced
by technology can be explored from the design process [26,37]. In collaboration with gen-
erative AI tools, the activities, such as what prompts should be inputs and which images
can be chosen to further update, are usually driven by decisions. Then, decision-making is
also influenced by experience, knowledge, and preferences. Visual stimulation can assist
the perception and interpretation of more ephemeral phenomena by color, texture, form,
images, and status [38]. Iteration is considered an integral part of design activity that may
be classified as the diagnostic and transformative process [39,40]. Adams and Atman empir-
ically explored the iteration behavior in the design process, recognizing that compared to
beginners in design, senior designers iterate more times and more effectively [41]. Focusing
images can be chosen to further update, are usually driven by decisions. Then, decision-
making is also influenced by experience, knowledge, and preferences. Visual stimulation
can assist the perception and interpretation of more ephemeral phenomena by color, tex-
ture, form, images, and status [38]. Iteration is considered an integral part of design activ-
Sustainability 2024, 16, 65 ity that may be classified as the diagnostic and transformative process [39,40]. Adams and
5 of 20
Atman empirically explored the iteration behavior in the design process, recognizing that
compared to beginners in design, senior designers iterate more times and more effectively
[41]. Focusing on the impact of AI on design iteration, Zhou et al. conducted a graphic
on the impact of AI on design iteration, Zhou et al. conducted a graphic design experiment
design experiment and results indicate AI augmentation increases the frequency of cog-
and results indicate AI augmentation increases the frequency of cognitive activities during
nitive activities during iteration [23]. Actually, the activities of human–AI collaboration
iteration [23]. Actually, the activities of human–AI collaboration encompass a complex
encompass a complex cyclical process, as shown in Figure 3.
cyclical process, as shown in Figure 3.
Figure 3. The workflow of

Figure of generative
generative AI-aided
AI-aideddesign
designcreativity.
creativity.
2.3.
2.3. Cultural Translation in
Cultural Translation in Jewelry
Jewelry Design
Design
Currently,
Currently, more
more attention is given
attention is given to
to the
therole
roleand
andimportance
importanceofofculture
cultureininsustainable
sustainable
development.
development. Cultural features are considered unique features that can be embedded inin
Cultural features are considered unique features that can be embedded
products
products to toachieve
achievesustainable
sustainablecultural
culturalspread
spreadandandvalue
valuetransformation
transformation [42,43]. Therefore,
[42,43]. There-
it is crucial to confirm the methods for integrating cultural elements into creative
fore, it is crucial to confirm the methods for integrating cultural elements into creative product
design.
product Based
design.onBased
previous research,research,
on previous the factors
the that affect
factors thatcultural and creative
affect cultural product
and creative
design include aesthetics, creativity, practicality, and commercial value,
product design include aesthetics, creativity, practicality, and commercial value, whichwhich are taken
into consideration
are taken [44,45]. Lee[44,45].
into consideration [46] introduced
Lee [46] the term “cultural
introduced variable”,
the term “culturalwhich means
variable”,
to profile cultural characteristics and identify the key design attributes, such as functional,
aesthetic, and symbolic ones. There, cultural objects can be incorporated into cultural
design. Lin [43] identified three design features: inner-level (e.g., stories, emotions, and
cultural features), mid-level (e.g., function, operational concerns, usability, and safety), and
outer-level (e.g., color, texture, form, decoration, surface pattern, line quality, and detail).
To bridge the implicit layer of culture and an explicit layer of design characteristics, a
series of culture-embedded product design models were proposed and developed from
the perspective of communication [43,47,48], which divided the design and perceptual
process of the product into the technical level, semantic level, and effectiveness level.
The technical level requires attracting the users through cultural features through their
senses; the semantic level focuses on precisely transmitting cultural information; and the
effectiveness level concerns the emotional connection and reflection.
Traditional jewelry design is time-consuming and labor-intensive. It requires a high
level of drafting skills. Furthermore, the unique jewelry design can be created by harnessing
different pattern combinations in varying proportions, but it leads to a very tedious design
process [24]. While several designers have embraced traditional Chinese elements such as
dragons, the phoenix, bamboo, and Chinese characters into their products, they occasionally
do not apply or combine them properly, making them become less meaningful [9]. On the
contrary, appropriate combinations of elements can accurately convey cultural information.
Designers pass the new concept into the jewelry through the material, color, craft technique,
etc., which causes the wearer’s spiritual resonance [49]. From the coding perspective of
jewelry design, the external features of design include shape, craftsmanship, and materials.
The combination of these features also carries cultural metaphors, ultimately conveying a
sense of ritual and pleasure [9,50], as displayed in Figure 4.
ful [9]. On the contrary, appropriate combinations of elements can accurately convey cul-
tural information. Designers pass the new concept into the jewelry through the material,
color, craft technique, etc., which causes the wearer’s spiritual resonance [49]. From the
coding perspective of jewelry design, the external features of design include shape, crafts-
Sustainability 2024, 16, 65 manship, and materials. The combination of these features also carries cultural metaphors,
6 of 20
ultimately conveying a sense of ritual and pleasure [9,50], as displayed in Figure 4.
The
Figure4.4.The
Figure research
research framework
framework for impact
for the the impact of generative
of generative AI on cultural
AI on cultural translation
translation in
in jewelry
design.
jewelry design.
The development
The development of of technology
technology could
could indeed
indeed have
have an
an impact
impact onon the
the actions
actions of
ofdesign
design
creativity, both positively and negatively. Especially in the collaborative
creativity, both positively and negatively. Especially in the collaborative creation process creation process
between humans
between humans andand generative
generativeAI AI technology,
technology, the the path
path in
in design
design thinking
thinking shows
shows newnew
features. Despite powerful AI methods becoming increasingly accessible
features. Despite powerful AI methods becoming increasingly accessible for creative de- for creative design,
we still
sign, weknow relatively
still know little little
relatively aboutabout
how howto translate cultural
to translate features
cultural in collaboration
features with
in collaboration
AI-powered image generation systems. Culture and creative designing
with AI-powered image generation systems. Culture and creative designing are, after all, are, after all, a form
aofform
designing. The discussion
of designing. about theabout
The discussion impacttheof generative
impact of AI on the ideation
generative AI on process must
the ideation
be firmly based on the model of conventional design. Therefore, this
process must be firmly based on the model of conventional design. Therefore, this articlearticle is concerned
with
is the impact
concerned of the
with generative
impact AI technology AI
of generative on technology
the ideationon of the
embedded
ideationculture features
of embedded
in jewelry design and explores the positive and negative effects of technology on design
thinking from a cultural perspective.
2.4. Research Framework

According to this literature review and the purpose of the study, a research framework
is proposed, as displayed in Figure 4. In the encoding process of incorporating cultural
features into jewelry design, it includes first encoding from the inner-level (e.g., emotion,
culture, taste) to the mid-level (e.g., story, metaphor, information), and second encoding
from the description of meaning to the outer-level (e.g., shape, craft, material). The outputs
serve as stimuli to trigger the designer’s decision-making during iterative behavior toward
description and parameters. Viewing image stimulation as a decoding process involves
bottom-up evaluation at the technical levels (i.e., what does it symbolize?), semantic level
(i.e., what is its meaning?), and effectiveness level (i.e., what does it look like?). In the
action analysis of new technology-assisted ideation, attention needs to be given to the
empowerment in guidance, stimulation, and generation, together with the design fixation
on thinking and decision-making.
3. Methods
3.1. Participants
This study was conducted as a class exercise in a jewelry design class at Shenzhen
University of Technology. Totally, 52 senior undergraduate students (S1–S52) volunteered
for the experiment. All of these participants were industrial design students. As a
prerequisite, they are already proficient in using a series of generative AI tools, such
as Midjourney, Stable Diffusion, and Deep Dream Generator. Both Midjourney and
Deep Dream Generator are online platforms that allow users to create images using deep
learning algorithms, paid by a charge that is based on the number of images or usage
time. Stable Diffusion is operated by most users on Google Colab (https://github.com/
AUTOMATIC1111/stable-diffusion-webui, accessed on 25 April 2023), which renders
additional higher learning costs, more control freedom, and lower operation expenses.
Due to the consideration of originality in the design, participants were encouraged to
update the design concept by using the initial image, perhaps combined with prompts.
Based on the output results, there were six participants (S4, S7, S15, S24, S47, S52) who
did not meet the experimental requirements; their data were excluded. Therefore, the
final analysis data came from 46 participants.
3.2. Experimental Procedure

Initially, the participants were asked to complete, using a traditional design approach
and within one week, a concept design task for a set of jewelry designs with embedded
Chinese cultural features. During that process, conceptualization, sketching, refinement,
and 3D modeling are normally involved. Then, they were tasked to collaborate with a
familiar AI tool to explore Chinese-style jewelry within another week. All participants
worked individually and spent a variable amount of time. They were encouraged to keep
all the outputs labeled with a concise description of the different components of their ideas
and document their thoughts and comments as they developed their concepts. Finally, all
the outputs with notes in the ideation process and final concept design (i.e., one individual
design and one collaborative design with AI) were collected, after which they self-evaluated
the effect of AI in culture translation by filling in the questionnaire with nine questions
corresponding to the matrix of the three translation levels (i.e., technical level, semantic
level, and effectiveness level) and three jewelry design attributes (i.e., shape, craft, and
material). The web-based questionnaire was designed using Qualtrics, and each item was
assessed using a 7-point Likert scale with 1 indicating very low and 7 indicating very high
(as shown in Part_01 of Appendix A). Moreover, a semi-structured one-on-one interview
based on the matrix was carried out (as shown in Part_02 of Appendix A). During the
evaluation stage, thirty jewelry design educators and experts were invited to measure
the concept designs with and without AI using a 7-point Likert scale from the technical,
semantic, and effectiveness levels (as shown in Part_03 of Appendix A).
3.3. Analytical Methods

Firstly, the images generated during the process were collected and compiled into
tables, such as Table 1. Concept images were classified based on direction, and the numbers
were counted. One-way ANOVA was adapted to test whether the impact of the generative
AI was significant (the significance level was set at 0.05) for the design activity. The notes
marked during the design process were integrated to explore the main action stimulated
by technology.
Secondly, the questionnaire data from participants’ self-assessments was statistically
analyzed. Two-way ANOVA was performed to examine the effects of the three cultural
translation levels (i.e., technical level, semantic level, and effectiveness level) and three
jewelry design attributes (i.e., shape, craft, material) as two independent variables on the
dependent variable of AI-augmented feeling. Based on the matrix structure, interview data
were summarized for further discussion.
Finally, based on evaluation data from thirty experts, descriptive statistics were used
to evaluate and compare design outputs generated with AI and without AI. Then, the
relationship between the two types of concept design was analyzed.
stimulated
analyzed. by technology.
Two-way ANOVA wasdataperformed to examine the effects of thewas three cultural
Secondly,
translation the (i.e.,
levels questionnaire
technical level,from participants’
semantic self-assessments
level, and statistically
stimulated
analyzed.Secondly,by
Two-way technology.
the ANOVA
questionnaire was dataperformed
from to examine
participants’ theeffectiveness
effects of thelevel)
self-assessments three
was and three
cultural
statistically
translation
analyzed.
jewelry levels
Two-way
design
Secondly, (i.e.,
attributes
the technical
ANOVA (i.e.,
questionnaire waslevel,
shape,
data semantic
performed
craft,
from level,
to examine
material)
participants’ and
as two effectiveness
theindependent
self-assessments level)
effects of the and
three
variables
was three
cultural
on
statisticallythe
translation
analyzed. levels
Two-way (i.e., technical
ANOVA level, semantic
was performed level, and
to examine effectiveness
the level)
effects of the and three
three cultural
jewelry design
translation
dependent
analyzed. attributes
levels
variable
Two-way (i.e.,
of
ANOVA (i.e., shape,
technical
AI-augmented
was craft,
level, material)
semantic
feeling.
performed toBasedas two
level,
examineandthe
on independent
effectiveness
the matrix
effects variables
level)
structure,
of the threeand onthree
interview the
cultural
jewelry design
translationvariableattributes
levels (i.e., (i.e., shape, craft,
technical level,feeling. material)
semantic as two
level,onand independent variables on the
dependent
jewelry
data were
translationdesign
summarized
levels of AI-augmented
attributes
(i.e., for(i.e., shape,
further
technical craft,
discussion.
level, semantic Based
material)
level, theeffectiveness
as and
two independent
level)interview
matrix structure,
variables
and three
andon the
dependent
jewelry variable
design of AI-augmented
attributes (i.e., shape, feeling.
craft, Based
material) on the effectiveness
as two matrix structure,
independent level) interview
variables onthree
the
data were
dependent
jewelry summarized
Finally, variable
design based on
attributes for further
ofevaluation
AI-augmented
(i.e., discussion.
data
shape, feeling.
from
craft, Based
thirty
material) ontwo
experts,
as the matrix structure,
descriptive
independent statistics interview
were
variables onused
the
Sustainability 2024, 16, 65 data were summarized
dependent variable of for further discussion.
AI-augmented feeling. Based on descriptive
the matrix statistics
structure,wereinterview 8 of 20
data
to Finally,
dependent based
were summarized
evaluate and
variable on
compareevaluation
of for
AI-augmented data
furtheroutputs
design from
discussion.thirty experts,
generated
feeling. Based with
on AI
the and
matrixwithout
structure,AI. Then, used
interview the
Finally, based on evaluation data from thirty experts, descriptive statistics were used
todata were summarized
evaluate
Finally,
relationship
data were and compare
based
between
summarized on the
for
fortwo
further
design
evaluation types
further
discussion.
outputs
dataof from generated
thirty
concept
discussion. with
experts,
design was AI and without
descriptive
analyzed. AI. Then,
statistics were used the
to evaluate
Finally,and compare
based on design outputs
evaluation generated with AI and without AI. Then, the
relationship
to evaluate
Finally, between
and
based the
compare
on two typesdata
design
evaluation
from
of concept
outputs
data from
thirty
design
generated
thirty
experts,
was
experts,
descriptive
withanalyzed.
AI and without
descriptive
statistics were used
AI. were
statistics Then,used the
relationship between the two types of concept design was
to evaluate and compare design outputs generated with AI and without AI. Then, the analyzed.
relationship
Table
to 1. Sample
evaluate between
and list
comparethe two
of design typesoutputs
activity
design of concept
data onedesign
fromgenerated was analyzed.
of participants
with AI (ID S43).
and without AI. Then, the
Table 1. Sample list of design activity Table
data from
relationshiponebetween
1. Sample of
listparticipants
the two
of design (ID
activityS43).
typesdataoffrom
concept
one ofdesign was analyzed.
participants (ID S43).
relationship between the two types of concept design
Table 1. Sample list of design activity data from one of participants (ID S43). was analyzed.
Table 1. Sample list of design activity data fromDesign
one of participants (ID S43). Num. of
Type Category Type Category Direction
Direction Outcomes during
Outcomes during Process
one of Design Process Num. of Num. of Images
Type Category DirectionTable 1. Sample list of design activity
Outcomes data
during fromDesign participants
Process (ID S43).
Num.Images of
Type Category DirectionTable 1. Sample list of design activityduring
Outcomes data from one ofProcess
Design participants (ID S43). Images
Num. of
Type Category Direction Outcomes during Design Process Images
Num. of
Type Chiba
Category Direction
Red Chiba Red Outcomes during Design Process Images
Num. of
NecklaceChiba
Necklace Type Category Direction
Red Outcomes during Design Process Images
2 2
Pearl PearlRed
Necklace Chiba Images
2
Necklace Pearl
Chiba Red 2
NecklacePearl
Chiba Red 2
Necklace Pearl
Chiba
Chiba Red
Red 2
Regular NecklaceChibaPearl 2
Pearl Red
Regular Regular ChibaBrooch
Red Butterfly
Chiba Red 2
Design Brooch Butterfly
Brooch Regular Chiba Red 2 2
Design Regular Butterfly
Design Brooch wingwing
Butterfly
Chiba Red 2
Design
Regular Brooch wing wing
Butterfly
Chiba Red 2
Design
Regular Brooch Butterfly 2
Design Brooch wing Chiba Red
Butterfly 2
Chiba
Design EarringsChibawing Red
Ribbon
wing Red 4
Earrings
Chiba Red Ribbon
Chiba Red 4
Earrings knot Red
Earrings Ribbon
Chiba 4 4
Ribbon
Earrings knot
knotRibbon
Chiba Red 4
knot
Earrings Ribbon 4
Earrings knot
Ribbon
Sunflower 4
knot 5
Sunflower
knot
Diamond
Sunflower 5
Diamond
Sunflower
SunflowerDiamond 5
Sunflower 5 5
Diamond Diamond
Sunflower 5
Diamond
Butterfly 5
Diamond
Butterfly 5
Gemstone
Butterfly 5
Gemstone
Butterfly 5
AI- Butterfly Gemstone
Butterfly
Gemstone
5
AI- Butterfly 5 5
Aug-
AI- Gemstone Gemstone 5
Aug-
AI- Necklace Gemstone
mented
Aug- Necklace
AI- Necklace
AI- mented
Aug-
AI-
Design
Augmented Necklacemented
Aug-
Design
mented
Necklace
Necklace
Design Aug-
Design
mented Necklace Chiba Red
Design
mented
Design Chiba Red 15
Design PearlRed
Chiba 15
Pearl
Chiba Red 15
Pearl
Chiba Red 15
Pearl
Chiba Red
Chiba Red Pearl 15
15 15
Pearl Pearl
Table 1. Cont.
Type Category Direction Outcomes during Design Process Num. of Images
Chiba Red
Chiba Red Chiba Red
Brooch Butterfly
Chiba Red 27 27
Brooch
Butterfly wing
Butterfly 27
wing
Brooch Butterfly 27
Brooch wing
wing
AI- Chiba Red

Augmented Chiba Red
Chiba Red ChibaRibbonRed 10
Design Ribbon 10 10
knot
Ribbon knot Ribbon 10
Earrings knot
Earrings Earrings knot
Ribbon
Earrings Ribbon
knot
Ribbon 3
knot
Ribbon knot Spirit 3
knot 3 3
Spirit Spirit
•
Spirit Automatically identify and repair defects, noise, blurring, or distortion in images.
• Automatically identify and repair defects, noise, blurring, or distortion in images.
Action response—save actionand
time for detailed
defects,depictions.
Positive •ActionAutomatically
response—save
identify
action
repair
time noise,
for detailed
noise, blurring, or distortion in images.
depictions.
• Positive •
Automatically
Action identify
Automaticallyand
response—save repair
adjust defects,
actioncontrast,
time blurring,
brightness,
for detailed andorcolor
distortion
depictions. balanceinto
images.
make the image fuller and
Notes •
Positive Automatically adjust contrast,depictions.
brightness, and color balance to make the image fuller and
Action response—save
Notes • more vivid, action time
enhancing for
the detailed
visual effect of the image.
Positive by more Automatically adjust contrast, brightness, and color balance to make the image fuller and
Notes • Made
Notes
Automatically
Made by more
vivid,
adjust
Actionvivid,
enhancing
response—save
enhancing
the visual effect
contrast, brightness,
action
the time
visual and
effect
of the
forcolor
updated
of the
image.to make the image fuller and more vivid, enhancing the visual effect of the image.
balance
visual.
image.
MadeS42
ActionS42 by Action
response—save response—save
action action
timeoriginal time
for updated for updated
visual. visual.
Made by S42 • Able to convert images into
Action response—save action time for updated visual. different artistic styles.
• Able
S42 to • Able
convert to convert
original imagesoriginal
into images
different into different
artistic styles. artistic styles.
Action
• response—stimulate more explorative action.
Able to convert original images into different artistic styles.
Action response—stimulate
Action response—stimulate more explorativemoreaction.
explorative action.
•
Action Unable to truly understand
response—stimulate more the emotionsaction.
explorative and meanings of the initial image.
• Unable to truly understand the emotions and meanings of the initial image.
• Negative Action
Unable •to truly response—repeat
understand
Unable to trulythe test the effect
emotionsthe
understand of prompt.
andemotions
meanings and of meanings
the initial image.
of the initial image.
Negative Action response—repeat test the effect of prompt.
Notes
Action • Relying
response—repeat
Negative Action more
test theon
response—repeat thetest
effect matching
of prompt. of of
the effect algorithms
prompt. and data patterns, unable to truly express per-
Negative Notes • Relying more on the matching of algorithms and data patterns, unable to truly express per-
Notes Made by S42 • Made
Notes by •sonal
Relying opinions,
moreRelying feelings,
on the matching
more ofand
on the the depth
algorithms
matching and
of of data
artistic creation,
patterns,
algorithms and
unable
and data sometimes
to truly
patterns, even
express
unable resulting
personal
to truly in dis-
opinions,
express per- feelings, and the depth of artistic
Made by
creation,sonal
and opinions,
sometimes feelings,
even and the in
resulting depth of artistic
distorted and creation, and
incorrect sometimes even resulting in dis-
shapes.
S42 torted and incorrect shapes.
Made by sonal opinions, feelings, and the depth of artistic creation, and sometimes even resulting in dis-
Action S42 torted and incorrect
response—improve shapes.
the times in decision-making.
S42 Actionand
torted response—improve
incorrect shapes. the times in decision-making.
Action response—improve the times in decision-making.
Action response—improve the times in decision-making.
4. Results
4. Results
4.1.
4. Result of Stimulation to Design Actions
Results
4.1. Result of Stimulation to Design Actions
Basedofon
4.1. Result the encoding
Stimulation of theActions
to Design transition behaviors, descriptive statistics, and paired
Based
samples, a on thewas
T-test encoding
made of analyze
to the transition behaviors,
the designers’ descriptive
activities, statistics,
including and
theand paired
number of
Based on the encoding of the transition behaviors, descriptive statistics, paired
4. Results
4.1. Result of Stimulation to Design Actions
Based on the encoding of the transition behaviors, descriptive statistics, and paired
samples, a t-test was made to analyze the designers’ activities, including the number of
image outputs and the number of directions during the ideation. According to the results
shown in Table 2, AI augmentation improves the frequency of exploration action to a great
extent (t (45) = 7.598, p < 0.001), which demonstrates there are significant differences in
image outputs between the regular design process and the AI-assisted design process.
The designer iterated more images with the assistance of AI tools. Apart from that, the
square deviation up to 42.71 in the type of AI augmentation indicates a huge difference
between individuals, with a maximum of 198 images. For the design direction, there also is
a significant difference in the number of directions (t (45) = 2.202, p < 0.05), which denotes
that AI can stimulate the further expansion of imagination, and potentially generate new
products [26].
Table 2. Descriptive statistics and T-test analysis results from participant self-evaluation.
Type of Design Encoding

Activity Data
Regular AI-Augmented Significance
Number of Images 3.98 ± 3.64 52.00 ± 42.71 ***
Number of Directions 2.98 ± 1.18 3.54 ± 1.28 *
* p < 0.05, *** p < 0.001.
The participants actually used one or two AI tools, with most adopting Midjourney,
reaching 32 people, Stable Diffusion being 14 people, and Deep Dream Generator being
11 people. From the number of images generated, it can be seen that the average number
of images generated by designers using only Midjourney is 43.55 while using only Stable
Diffusion generated an average of 103.78 images. It is suggested that easier operations can
attract selection by more people, while more control freedom and lower cost will encourage
users to make more iterative actions.
By further sorting the notes and self-reports from designers about their feelings
concerning collaboration with AI, as shown in Table 3, the stimulation mainly focuses on
the exploration at the technical level, such as material combination, layout possibility, and
craft expressions. Furthermore, there was an increase in decision-making actions at the
technical, semantic, and effectiveness levels. For the decreased activities, a series of work
on the technical level is obvious. Compared to traditional design processes, the efficiency
of generating high-quality image outputs of AI effectively stimulates designers to explore
more possibilities, but it also brings more decision-making burdens.
Table 3. Changes in jewelry design actions for embedded culture.
Category Design Levels Design Actions

• Explore more material combinations
• Explore more layouts
Technical • Explore more craft expressions
level • Determine whether the image is beautiful
• Determine whether the structure in the image is reasonable and executable
Increased actions • Repair some details
Semantic • Determine whether the image accurately tells the story
level • Determine whether the image matches the cultural metaphor
• Determine whether the image matches the original creativity
Effectiveness
• Determine whether the image delivers cultural taste
level
• Determine whether the image delivers cultural spirit
inability 2024, 16, 65

Table 3. Cont.
Category Design Levels Design Actions
There are •significant differences in the cultural translation levels (F

Refine the shape
Technical • Improve the visual quality
Decreased actions p < 0.001). It can
level • be observed
Material matching from the specific comparison differences
• Layout matching
the technical level is significantly higher than that for the effectiveness
fectiveness level is also significantly higher than the semantic level. A
4.2. Experience of Designers Collaborating in AI Augmentation
encoding types, there is also a significant difference in the experience of c
The data from the questionnaire for designers were collected and analyzed. From the
AIperspective
(F (4, 413) = 9.000,
of user p < the
experience, 0.001). The value
three cultural of AI
translation forand
levels shape is obviously
the three jewelry h
design attributes were analyzed using two-way ANOVA. The results indicate that both the
craft and material.
“cultural translation levels” and “jewelry design attributes” have a significant interactive
relationship, as shown in Figure 5. Therefore, further one-way ANOVA was performed on
each factor.
Figure 5. Comparison of the mean score for “cultural translation levels” and “jewelry encoding types”.
Figure 5. Comparison of the mean score for “cultural translation levels” and
There are significant differences in the cultural translation levels (F (4, 413) = 29.681,
types”.
p < 0.001). It can be observed from the specific comparison differences that the score
for the technical level is significantly higher than that for the effectiveness level, and the
Concerning
effectiveness thesignificantly
level is also feedbackhigher fromthan interviews, the data
the semantic level. As for were classified
the jewelry
encoding types, there is also a significant difference in the experience of collaborating with
matrix
AI (F (4, by
413)three
= 9.000,cultural translation
p < 0.001). The levels
value of AI for shape and threehigher
is obviously jewelry encoding
than that for t
Table 4. material.
craft and In addition, the result also reflects the designers’ experience in
Concerning the feedback from interviews, the data were classified according to the
ofmatrix
AI inbyterms of shape and technical level. However, there are more neg
three cultural translation levels and three jewelry encoding types, as shown in
inTable
the4.creative
In addition,aspects
the result of
alsocraft and
reflects material,
the designers’ alonginwith
experience lessvalue
the added accurate
of tra
AI in terms of shape and technical level. However, there
tural semantics. The reason may be that both Midjourney and Stable Dare more negative experiences
in the creative aspects of craft and material, along with less accurate transmission of
the universal
cultural semantics. AIThegenerative
reason may bemodels and are and
that both Midjourney notStable
very suitable
Diffusion for app
belong
to the universal
specialized AI generative
jewelry craftsmodels
andand are not very suitable for application to highly
materials.
specialized jewelry crafts and materials.
Table 4. Categories of feedback for AI-empowered ideation.
Levels Shape Craft

● Element replacement ♦ Does not match the ini-● Div
● Element recombination tial idea binat
● Add more details ♦ Unsuitable jewelry craft ♦ U
Table 4. Categories of feedback for AI-empowered ideation.
Levels Shape Craft Material

• Element replacement ♦ Does not match the initial idea • Diverse material combinations
• Element recombination ♦ Unsuitable jewelry craft ♦ Unsuitable jewelry materials
• Add more details
Technical level
• Fit product standards
• Easy to change aesthetic style
♦ Unexpected appearance
• Stimulates new narrative thinking ♦ Difficult to deliver the ♦ Difficult to deliver the
Semantic level ♦ Blurs meaning by an cultural connotation traditional significance
abstract shape
• Some improvement in the ♦ Difficult to reflect the essence of ♦ Lack of creativity
cultural taste the traditional craft
Effectiveness level
• Unexpected surprises ♦ More common commercial styles
♦ Difficult to reflect spirited situation
• indicates positive feedback; ♦ indicates negative feedback.
4.3. Evaluation of the Outputs

After collecting the best conceptual design and AI-augmentation design from each
designer, they were evaluated by 30 experts in terms of technical level, semantic level,
and effectiveness level. T-test was adapted to test whether AI technology had an impact
on all three levels of evaluation indicators. The result, as shown in Table 5, shows that
AI-augmentation design outputs have higher evaluation scores than regular design at all
three levels.
Table 5. Descriptive statistics and T-test analysis results for expert evaluation.
Type of Design Encoding

Evaluation Items
Regular AI-Augmented Significance
Technical level 4.42 ± 1.62 3.94 ± 1.60 ***
Semantic level 3.99 ± 1.58 3.72 ± 1.58 ***
Effectiveness level 4.14 ± 1.67 3.87 ± 1.63 ***
*** p < 0.001.
To further analyze the distribution characteristics in AI-added value, the regular

design scores for 46 designers were arranged in ascending order, and the corresponding AI-
augmented design scores are displayed to compare the differences, as shown in Figures 6–8.
As presented in Figure 6, AI technology fluctuates at a certain stable level in terms of shape,
craft, and material, thus significantly improving conceptual designs that were initially
weak at this level. In Figures 7 and 8, there are similar trends, indicating that the regular
designs with low-scoring grades can be enhanced at the semantic and effective levels under
the empowerment of AI. However, regular designs with high-scoring grades were not
improved by utilizing AI technology.
In Table 6, the regular designs with the highest scores at three levels and their corre-
sponding AI-augmented designs are listed (i.e., S20, S23, S11), while the AI-augmented
designs with the highest scores and their corresponding regular designs are also displayed
(i.e., S31, S34, S5) for comparison. As the conceptual design S20, the interweaving of the
two materials is very vivid, but after AI iteration, the smooth shape and clever structure
disappeared. The interpretation of Tai Chi’s meaning highlights the accurate symbol rep-
resentation in the regular work S23. Unfortunately, the AI system cannot decode Tai Chi
culture and encode corresponding symbol graphics, which deviates from the precise trans-
mission of semantics. As the regular design with the highest score on effectiveness level,
the cultural scenario translated through traditional elements and the story of “Chang’s
running to the moon” (Chinese mythology) provides a good emotional experience. Com-
pared with human intelligence, AI cannot understand and reproduce this scenario thus
Effectiveness level 4.14 ± 1.67 3.87 ± 1.63 ***
*** p < 0.001.
Sustainability 2024, To further

16, 65 analyze the distribution characteristics in AI-added value, the regular de- 13 of 20
sign scores for 46 designers were arranged in ascending order, and the corresponding AI-
augmented design scores are displayed to compare the differences, as shown in Figures
6–8. As presented far.
in Figure 6, AI
The value oftechnology fluctuates
AI can be better at by
reflected a certain
addingstable
detailslevel in terms
of shape, of craft, and
diverse
materials thus
shape, craft, and material, on the technical level,
significantly includingconceptual
improving S31. In the designs
imagination
that of the regular
were ini- design
S34, the addition of porcelain materials interprets the meaning of Taoist
tially weak at this level. In Figures 7 and 8, there are similar trends, indicating that the culture. Under the
comprehensive effect of blue and white porcelain material, elegant shape, and traditional
regular designs with low-scoring grades can be enhanced at the semantic and effective
craft, the AI-augmented work S5 achieved the best cultural experience. Evidently, for
levels under the empowerment of AI. However, regular designs with high-scoring grades
regular designs with lower scoring grades, AI can provide more in-depth detail shaping
were not improved bydivergent
and utilizing styling.
AI technology.
However, for regular designs that garnered high-scoring grades,
little or negative enhancement has been revealed in the collaboration with AI.
024, 16, 65 13 of 19
24, 16, 65 13 of 19
Figure
Figure 6. Comparison Comparison
of the6.score of the score
between regular between
design regular designdesign
and AI-augmented and AI-augmented design at the
at the technical
level. technical level.
Figure 7. Comparison of the score between regular design and AI-augmented design at the semantic
level. Figure 7. Comparison of the score between regular design and AI-augmented design at the
Figure 7. Comparison of the score between regular design and AI-augmented design at the semantic
semantic level.
level.
Figure
Figure 8. Comparison Comparison
of 8.the of the regular
score between score between regular
design design and AI-augmented
and AI-augmented design atdesign at the effective-
the effec-
tiveness level. ness level.
Figure 8. Comparison of the score between regular design and AI-augmented design at the effec-
tiveness level.
designs with the highest scores and their corresponding regular designs are also dis-
played (i.e., S31, S34, S5) for comparison. As the conceptual design S20, the interweaving
designs with the highest scores and their corresponding regular designs are also dis-
Sustainability 2024,
Sustainability2024,
Sustainability 16,
2024,16, 65
16,65
65 14
14ofof
14 19
of19
19
Sustainability
Sustainability
Sustainability2024,
2024,
2024,16,
16,
16,65
65
65 14
14
14of
of
of19
19
19
Sustainability
Sustainability2024,
Sustainability 2024,16,
2024, 16,65
16, 65
65 14
14ofof
14 of19
19
19
Sustainability2024,
Sustainability
Sustainability 2024,16,
2024, 16,65
16, 65
65 14ofof
14
14 of19
19
19
Table 6. List of high-scoring regular designs and AI-augmented designs.
Table
Table6.6.
Table List
6.List of
Listof high-scoring
ofhigh-scoring regular
high-scoringregular designs
regulardesigns and
designsand AI-augmented
andAI-augmented designs.
AI-augmenteddesigns.
designs.
Table
Table
Table6.6.
6.List
List
Listof
of
ofhigh-scoring
high-scoring
high-scoringregular
regular
regulardesigns
designs
designsand
and
andAI-augmented
AI-augmented
designs.
designs.
Table Technical
Table
Table6.
6. List
6. Listof
List ofLevel
high-scoring
of high-scoring regular
high-scoring regular Semantic
designs
regular designs
designsand
and Level
AI-augmented
and AI-augmented designs.Effectiveness Level
AI-augmented designs.
designs.
Table Technical
Technical
Table
Table 6.List
6.6. Listof
List Level
Level
ofhigh-scoring
of high-scoringregular
high-scoring Semantic
Semantic
regulardesigns
regular designs
designs Level
Level
andAI-augmented
and
and EffectivenessLevel
Effectiveness
AI-augmented designs.
designs. Level
Regular designs withwith Technical
Technical
Technical Level
Level
Level Semantic
Semantic
Semantic Level
Level
Level Effectiveness
Effectiveness
Effectiveness Level
Level
Level
Regular
Regular designs
designs with Technical
Technical
Technical
S20 Level
Level
Level Semantic
Semantic
Semantic
S23 Level
Level
Level Effectiveness
Effectiveness
Effectiveness
S11 Level
Level
Level
Regular
Regular
Regular
the designs
highestdesigns
designswith
with
with
scorescore Technical
Technical
Technical S20
S20 Level
Level
Level S23
S23 Level
Semantic
Semantic
Semantic Level
Level S11
S11 Level
Effectiveness
Effectiveness
Effectiveness Level
Level
the highest
the highest
Regular
Regular
Regular score
designs
designs
designswith
with
with S20
S20
S20 S23
S23
S23 S11
S11
S11
the
the
thehighest
Regular
Regular
Regular highest
highestscore
score
score
designs
designs
designs with
with
with S20
S20
S20 S23
S23
S23 S11
S11
S11
the
the highest
the highestscore
highest score
score S20
S20
S20 S23
S23
S23 S11
S11
S11
thehighest
the
the highestscore
highest score
score
Regular
Regular
Regular
Regular
Regular
Regular
Regular
design
design
design
design
Regular
Regular
Regular
design
design
design
Regular
Regular
Regular
design
design
design
design
design
design
AI-augmented
AI-augmented
AI-augmented
AI-augmented
AI-augmented
AI-augmented
AI-augmented
design
design
design
AI-augmented
AI-augmented
AI-augmented
design
design
design
design
AI-augmented
AI-augmented
AI-augmented
design
design
design
design
design
design
AI-augmenteddesign
AI-augmented design
AI-augmented
AI-augmented
AI-augmenteddesign
design
design S31
S31 S34
S34 S5
S5
with
AI-augmented
with thedesign
the
AI-augmentedhighest
highest
AI-augmented
AI-augmented score
with
score
design
design
design S31
S31
S31 S34
S34
S34 S5
S5
S5
with
with
with the
the
thehighest
highest
highest
AI-augmented
AI-augmented
AI-augmented score
score
score
design
design
design S31
S31
S31
S31 S34
S34
S34
S34 S5
S5
S5
S5
the highest
with
withthe
with score
thehighest
the highestscore
highest score
score S31
S31 S34
S34 S5
S5
S31 S34 S5
withthe
with
with thehighest
the highestscore
highest score
score
Regular
Regular
Regular
Regular
Regular
Regular
design
design
design
Regular
Regular
Regular
Regular
design
design
design
Regular
Regular
Regular
design
design
design
design
design
design
design
AI-augmented
AI-augmented
AI-augmented
AI-augmented
AI-augmented
AI-augmented
design
design
design
AI-augmented
AI-augmented
AI-augmented
design
design
design
AI-augmented
AI-augmented
AI-augmented
AI-augmented
design
design
design
design
design
design
design
5.5.Findings
Findingsand andDiscussions
Discussions
5.5.
5.Findings
Findings
Findingsand and
andDiscussions
Discussions
Discussions
5.5.
5.Findings
5.1.
5.1. Findings
Influence
Findings
Influence and
and
ofofAI
and Discussions
AIDiscussions
Augmentationon
Discussions
Augmentation onCulture
CultureTranslation
TranslationininJewelryJewelryDesignDesign
5.5.
5.
5.1.
5.1.Findings
Findings
Findings
5.1. Influence
Influence
Influence and
and
and
ofof
ofAIAI
AIDiscussions
Discussions
Discussions
Augmentation
Augmentation
Augmentationon on
onCulture
Culture
CultureTranslation
Translation
Translationin in
inJewelry
Jewelry
JewelryDesign
Design
Design
5. Findings
5.1.
5.1.Influence
5.1. Influenceand
Concerning
Influence
Concerning Discussions
ofof
ofAIAI
AIAugmentation
Augmentation
the
the ideation process,
Augmentation
ideation on
onCulture
on Culture
process,
Culture theTranslation
the Translation
distribution
Translation
distribution ininJewelry
in Jewelry
ofof design Design
design
Jewelry Design
actions has
Design
actions has changed,
changed,
5.1.Influence
5.1.
5.1. Influence
Influence
Concerning
Concerning
Concerning ofAI
ofof AIthe
AI Augmentation
Augmentation
Augmentation
the
the ideation
ideation
ideation ononCulture
on
process,Culture
Culture
process,
process, the
the
the Translation
Translation
Translation
distribution
distribution
distribution ininJewelry
in ofJewelry
Jewelry
of
of design
design
designDesign
Design
Designactions
actions
actionshas has
haschanged,
changed,
changed,
5.1. mainly
Influence
mainly atatof
Concerning
Concerningthe
Concerning AItechnical
the Augmentation
technical
the
the
the level.
ideation
ideation
ideation on Culturefrom
level.Benefiting
Benefiting
process,
process,
process, theTranslation
from
the
the distribution
distributionin Jewelry
theefficient
the efficient
distribution of image
image
of
of Design
design
design
designgeneration
generation
actions
actions
actions of
of
has
hasAI
AI
has technol-
technol-
changed,
changed,
changed,
mainly
mainly
mainly atat
atthe
Concerning
Concerning
Concerning the
thetechnical
technical
technical level.
theideation
the
the level.
level.Benefiting
ideation
ideation Benefiting
Benefiting
process,
process,
process, from
from
from
the
the
the the
the
theefficient
efficient
efficientof
distribution
distribution
distribution image
image
image
of
of generation
design
design
design generation
generation
actions
actions
actions of
of
ofAI
has
has
has AI
AI technol-
technol-
technol-
changed,
changed,
changed,
ogy,
ogy,
mainly there
there
Concerning
mainly
mainly atat the
atwas was
was
the
the theaa significant
significant
technical
ideation
technical
technical level. reduction
reduction
Benefiting
process,
level.
level. the
Benefiting
Benefiting inin depth
depth
from
distribution
from
from actions,
actions,
the
the
the of such
such
efficient
design
efficient
efficient image
imageas
as
image detail
detail
actions characterization
characterization
generation
has
generation
generation of
ofAI
changed,AI technol-and
and
mainly
technol-
of AI technol-
ogy,
ogy,
ogy,
mainly
mainly
mainly there
there
there
at at
at was
was
the
the
the aaasignificant
significant
significant
technical
technical
technical level.
level.
level. reduction
reduction
reduction
Benefiting
Benefiting
Benefiting in
in depth
depth
infrom
depth
from
from actions,
actions,
actions,
the
the
the such
efficient
efficient
efficient such
such as
as
asdetail
image
image
image detail
detail characterization
characterization
characterization
generation
generation
generation of
of
of AIAI
AI and
and
and
technol-
technol-
technol-
at theadjustment
adjustment
ogy,
ogy,
ogy, there
there
technical
there was was actions,
actions,
was
level.aa like
like
significant
significant
Benefiting
a significant style
style uniformity.
uniformity.
reduction
reduction
from
reduction inin
the in Accordingly,,
Accordingly,,
depth
depth
efficient
depth actions,
actions, a
sucha
such
image generation
actions, such large
large
as
as number
number
detail
detail ofof decision-mak-
decision-mak-
characterization
characterization
of AI
as detail technology,
characterization and
and
there
and
adjustment
adjustment
adjustment
ogy,
ogy,
ogy, there
there
there wasactions,
actions,
actions,
was
was aaa like
like
likestyle
significant
significant
significant style
style uniformity.
uniformity.
uniformity.
reduction
reduction
reduction in in
in Accordingly,,
Accordingly,,
Accordingly,,
depth
depth
depth actions,
actions,
actions, aaalarge
such
such
such large
large
as
as
as number
number
number
detail
detail
detail of
of
ofdecision-mak-
decision-mak-
decision-mak-
characterization
characterization
characterization and
and
and
wasinging actionsare
actions
adjustment
adjustment
aadjustment
significant are
actions,generated
generated
actions,
actions,
reduction like
like
like that
that
style
style
instyle
depth are
are bottom-up
bottom-up
uniformity.
uniformity.
uniformity.
actions, evaluations
evaluations
Accordingly,,
Accordingly,,
Accordingly,,
such as detail aof
aof visual,
visual,
acharacterization
large
large
large meaningful,
meaningful,
number
number
number ofof andemo-
and
decision-mak-
of
anddecision-mak-
decision-mak-
adjustment emo-
ing
ing
ingactions
actions
actionsare
adjustment
adjustment
adjustment are
are generated
generated
generated
actions,
actions,
actions, likestyle
like
like that
that
style
style are
are
arebottom-up
bottom-up
thatuniformity.
bottom-up
uniformity.
uniformity. evaluations
evaluations
evaluations
Accordingly,,
Accordingly,,
Accordingly,, aaof
of
of visual,
visual,
visual,
large
large
aexploration
large meaningful,
meaningful,
meaningful,
number
number
number of and
and
andemo-
ofdecision-mak-
of decision-mak-
decision-mak- emo-
emo-
tional
tional
ing
ingactions
ing
actions, aspects.
aspects.
actions
actions
like styleare
are The
The
generatedstrong
strong
generated
areuniformity.
generated ability
ability
that
that
that are
are
areofof
Accordingly„ AIcan
AI
bottom-up
bottom-up
bottom-upcan stimulate
a stimulate
evaluations
evaluations
evaluations
large number anexploration
an of ofvisual,
of ofmore
of more
visual,meaningful,
visual, meaningful,
meaningful,
decision-making possibilities,
possibilities,
and
andemo-
and
actions emo-
emo-
are
tional
tional
tional
ing
ing
ing aspects.
aspects.
aspects.
actions
actions
actions are
are
are The
The
The strong
strong
strongthat
generated
generated
generated ability
ability
ability
that
that are
are
are ofof
of AI
AI
AIcan
bottom-up
bottom-up
bottom-up can
can stimulate
stimulate
stimulate
evaluations
evaluations
evaluations an
an
anexploration
exploration
exploration
ofof
of visual,
visual,
visual, of
of
ofmore
more
morepossibilities,
meaningful,
meaningful,
meaningful, possibilities,
possibilities,
and
and
and emo-
emo-
emo-
such
such
tional
tional
tional
generated asas theare
the
aspects.
aspects.
aspects.
that mapping
mapping
The
The
The of
strongofvarious
strong
strong
bottom-up various
ability
ability
ability shapes,
shapes,
of
evaluations of
of AI
AI
AI can
of the
the
can
can combination
combination
stimulate
stimulate
stimulate
visual, an
an
an
meaningful, ofofmultiple
multiple
exploration
exploration
exploration
and materials,
materials,
of
of
ofmore
more
more
emotional thepossi-
the
possibilities,possi-
possibilities,
possibilities,
aspects. The
such
such
suchas
tional
tional
tional as
as the
the
themapping
aspects.
aspects.
aspects. mapping
mappingThe
The
The ofof
ofvarious
strong
strong
strong various
various
ability
ability
ability shapes,
shapes,
shapes,
ofofAI
of AI
AI the
the
can
can
can the combination
combination
combination
stimulate
stimulate
stimulate ofof
ofmultiple
anexploration
an
an multiple
multiple
exploration
exploration materials,
materials,
materials,
of
of more
more the
the
thepossi-
possi-
possi-
possibilities,
possibilities,
strongbility
bility
such
such
such as of
of
as
as
ability the layouts,
layouts,
the
the mapping
mapping
mapping
ofmapping
AI can and
and ofof
ofthe
the
stimulate expression
expression
various
various
various shapes,
shapes,
shapes,
anshapes, of
of
exploration craftsmanship.
craftsmanship.
the
the
the combination
combination
combination The
The
of impactof
impact
ofmultiple
of
of more possibilities, multiple
multiple on
on more
action
materials,
possibilities,
action
as theis
materials,
materials, is
the
the
theconcen-
concen-
possi-
possi-
possi-
bility
bility
bility
such
such
such asof
of
of
as
as layouts,
layouts,
the
the
the layouts,
mapping
mapping and
and
and ofthe
the
of
ofthe expression
expression
expression
various
various
various shapes,
shapes, of
of craftsmanship.
ofthecraftsmanship.
craftsmanship.
the
the combination
combination
combination The
The
The
ofof
of impactsuch
impact
impact
multiple
multiple
multiple on
on
onaction
action
action
materials,
materials,
materials, isismapping
is
the concen-
the
the concen-
concen-
possi-
possi-
possi-
trated
trated
bility
bility
bility in
of
ofinlayouts,
of thediagnostic
the
layouts,diagnostic
layouts, and
and
and the
the
theprocess.
process.
expression
expressionThecognitive
The
expression cognitive
of
of
of aspectsrelated
aspects
craftsmanship.
craftsmanship.
craftsmanship. related
The
The
The todetermining
to
impact
impact
impactdetermining
on
on
onaction
action
action how
how
isis
is toas-
to
concen-
concen-as-
concen-
of various
trated
trated
tratedof
bility
bility
bility in
of
of shapes,
in the
the
inlayouts,
layouts,
layouts, the
thediagnostic
diagnostic
diagnostic
and
and
and combination
the
the
the process.
process.
process.
expression
expression
expression of
The
The multiple
Thecognitive
cognitive
cognitive
of materials,
aspects
aspects
ofcraftsmanship.
of aspectsrelated
craftsmanship.
craftsmanship. the
related
related
TheThe
The possibility
to
to
todetermining
impact
impact
impact of
determining
determining
ononaction
on layouts,
how
how
how
actionlayer
action is totoand
to
isconcen-
is as-
as-
as-
concen-
concen-
sess
sess
trated
trated
trated the
the inin semantic
semantic
the
the
insemantic
the diagnosticlayer
layer
diagnostic
diagnostic and
and the
the
process.
process.
process. emotional
emotional
The
Thecognitive
The cognitive
cognitive aspects
aspects
aspectslinked
linked
aspects
aspects related to
to
related
related the
theto effectiveness
effectiveness
todetermining
to determining
determining layer
howhowto
how tohave
have
toas-
as-
as-
the trated
expression
sess
sess
sess
trated
trated the
the
the
inin thethe
the of
insemantic
semantic craftsmanship.
layer
layer
layerand
diagnostic
diagnostic
diagnostic and
and theThe
the
the
process.
process.
process. Theimpact
emotional
emotional
emotional
The
The cognitive
cognitive
cognitive onaspects
aspectsaction
aspects
aspects linked
aspects
aspects isrelated
linked
linked concentrated
to
to
related
related tothe
the
the
to
to in the how
toeffectiveness
effectiveness
effectiveness
determining
determining
determining diagnostic
layer
layer
layer
how
how have
tohave
have
to
to as-
as-
as-
sess
sess
sess
process. the
the
the
The semantic
semantic
semantic
cognitivelayer layer
layer
layer
aspects and
and
and the
the
the emotional
emotional
emotional aspects
aspects
aspects linked
linked
linked to
to
tothe
the
the effectiveness
effectiveness
effectiveness layer
layer
layer have
have
have
sessthe
sess
sess thesemantic
the semantic
semantic layer
layer andrelated
and
and the to determining
theemotional
the emotional
emotional how
aspectslinked
aspects
aspects linked
linked toto assess
to
to the semanticlayer
theeffectiveness
the
the effectiveness
effectiveness layerhave
layer
layer and
have
have
the emotional aspects linked to the effectiveness layer have served as sources of inspiration
for multiple creative directions. Thus, the collaboration with AI led to a notable increase in
the diversity of design directions explored.
The designers participating in the experiment generally feel that AI provided sig-
nificantly greater assistance in shape than in craft and material during jewelry coding.
Therefore, the current general generative AI is more adept at inspired styling, and for parts
with substantial professional limitations, further exploration is required for customization.
At the three levels of cultural translation, the effect of added value on technical and ef-
fectiveness layers is significantly higher than the semantic layer. Similar to the previous
studies [21], AI’s accurate understanding and mapping of semantics remains a gap in
human–AI co-creation, whereas visual-based iterations can still trigger emotional arousal.
Through the evaluation of the results, the optimization of AI at the technical level is
relatively stable, which can add more details and diverse processes and materials to the
prompt diagram. At the semantic and effectiveness levels, the height of AI augmentation
is related to the regular designs, which are below mid-level. In other words, the better
the original idea is, the more quality the iteration will be. However, for human designs
with the highest score in the experiment, which stand out in their particular symbolic
metaphors or specific story scenarios, the assistance of AI is unsatisfactory. Due to the lack
of understanding of shapes and scenes in specific cultural backgrounds in AI models, some
semantic information was lost in the results, making it difficult to achieve the emotional
level. Therefore, zones where shapes are closely linked to specific cultural semantics are
difficult for AI but can be handled by senior designers.
5.2. Effects of Generative AI in Augmenting the Imagination

In the three stages of computer-aided design [14], AI exhibits varying degrees of
empowerment in the guidance, stimulation, and generation stages. Among them, the
one augmented the most is the generation part, and the AI-augmented outputs were
significantly enhanced, compared to regular designs, in the technology, semantics, and
effectiveness levels, which will be favorable for designers to communicate their ideas
with others. During the stimulate stage, the stimulation from images effectively triggers
consideration of the shape, technical, and effect layers, while lacking in craft, material, and
semantic level. In terms of the designer’s self-reported results, the designer’s subjective
consciousness still dominates the guidance. Stimulation from AI augmentation can trigger
a limited divergence, but the value at this stage is insignificant.
In general, the effects of generative AI in augmenting the design ideation are reflected
in depth rather than breadth, and in the shape factor at the technical level such as detailiza-
tion and unexpected composition. Whether visual iteration can rise to the level of meaning
delivery and emotional arousal depends on the designer’s initial ideas and decision-making
power. Therefore, human creativity remains the core power of guiding design direction
and shaping the final outcome.
In addition, from the image to the imagination, whether created or iterated by
humans or generative AI, the hybrid imagination still has a bottom-up process [43].
Specifically, it involves sequentially achieving visual attraction, cognitive activation, and
emotional arousal.
5.3. Challenges in Collaborating with Generative AI

From the perceptive of human–AI interaction, compared to giving an initial image,
providing appropriate prompts is a challenge for most designers. Invalid or biased commu-
nication becomes a limitation for their ideation. On the technical level, the understanding
of professional crafts and materials is powerless. Probably the professional platform should
focus on defining and training attributes. For the semantic and effectiveness level, they are
closely related to the cultural context and knowledge of the audience. Owing to such a lack
in these trained language models, it is difficult to accurately decode and encode them into
the high-level requirements necessary for designers.
There is still design fixation in collaboration with AI in earlier stages [16]. Since the
AI modelThereis generated underfixation
is still design the guidance of prompts
in collaboration andAI
with initial images,
in earlier designers
stages [16]. Sinceare the
easily
AItrapped
model isingenerated
a cycle selection
under the process by constantly
guidance of prompts refining or reorganizing
and initial the de- are
images, designers
tailseasily
of thetrapped
solution.inAdditionally,
a cycle selection out-of-box
process bythinking was refining
constantly overlooked. At the samethe
or reorganizing time,
details
of theofsolution.
the style Additionally,
the training set will also out-of-box
result inthinking was overlooked.
the convergence At the
of outputs. same time,
Although the the
stylecommercial
general of the training setcan
style willenhance
also result
theinindustrialization
the convergence of outputs.
level Although
of low-level the general
design, it
may lead to losing the edge in personalized direction. Therefore, the designers need to be to
commercial style can enhance the industrialization level of low-level design, it may lead
alertlosing thefixation
to these edge in issues.
personalized direction. Therefore, the designers need to be alert to these
fixation issues.
6. Conclusions, Limitations, and Future Research
6. Conclusions, Limitations, and Future Research
In this study, the impact of generative AI in jewelry design for cultural translation
In thisAccording
was explored. study, thetoimpact of generative
the experiment AI in
results, AIjewelry design mainly
augmentation for cultural translation
functions in
the stages of stimulation and generation during design ideation. The influence of AIfunctions
was explored. According to the experiment results, AI augmentation mainly aug-
in the stages
mentation of stimulation
has changed and generation
the distribution of actions,during design
mainly on the ideation.
technical The influence
level, and has of AI
augmentation
enabled reductionhas changed
in some the distribution
refining of actions,
work. Instead, there mainly on the technical
is a significant increaselevel, and has
in deci-
enabled reduction in some refining work. Instead, there is a significant increase in decision-
sion-making on whether it triggers visual attraction, cognitive activation, and emotional
making on whether it triggers visual attraction, cognitive activation, and emotional arousal.
arousal. Concerning the influence of the ideation process, AI augmentation significantly
Concerning the influence of the ideation process, AI augmentation significantly improved
improved exploration in depth rather than breadth, and in the shape factor at the technical
exploration in depth rather than breadth, and in the shape factor at the technical level such
level such as detailization and unexpected composition. In fact, the conceptual design that
as detailization and unexpected composition. In fact, the conceptual design that accurately
accurately delivers cultural stories and metaphors makes it easier to achieve the emotional
delivers cultural stories and metaphors makes it easier to achieve the emotional levels. It is
levels. It is worth noting that generative AI can significantly improve the culture transla-
worth noting that generative AI can significantly improve the culture translation in regular
tion in regular designs with the grades of the low- to medium-level scoring. The challenge
designs with the grades of the low- to medium-level scoring. The challenge in human–AI
in human–AI co-creation lies in the communication gap, as well as the risk of design fixa-
co-creation lies in the communication gap, as well as the risk of design fixation caused by
tion caused by focusing on details and limitations from the data set.
focusing on details and limitations from the data set.
Humans send initial images and prompts to generative AI, and then algorithms en-
Humans send initial images and prompts to generative AI, and then algorithms
codeencode
numerous possiblepossible
numerous outputs after understanding
outputs the purposethe
after understanding of humans
purposebyofdecoding
humans by
the information. Based on the data analysis results, a hybrid imagination
decoding the information. Based on the data analysis results, a hybrid imagination model of hu- model
man–AI co-creation for culture translation in jewelry design is proposed,
of human–AI co-creation for culture translation in jewelry design is proposed, as shown as shown in Fig-
ure 9.
in Consistent with the three
Figure 9. Consistent with culture
the threetranslation levels, thelevels,
culture translation decision-making also eval-also
the decision-making
uatesevaluates whether the generated images achieve the three bottom-up aspects.also
whether the generated images achieve the three bottom-up aspects. It can It can bealso
taken as a reference for research on the design impact of other new technologies
be taken as a reference for research on the design impact of other new technologies on on cul-
turalcultural
translation.
translation.
Figure 9. The9.hybrid
Figure imagination
The hybrid model ofmodel
imagination human–AI co-creationco-creation
of human–AI on culture on
translation
culture in jewelry in
translation
design.
jewelry design.
One of the limitations of this study is that participants are student designers with
relatively limited design experience. Experience is an important factor influencing human–
computer interaction; thus, this limitation may affect the study outcomes. For future
research, more senior designers could be invited to participate in experiments to expand
the diversity of samples. Although the Chinese style is used as a compass for two design
actions, the first one is bound to have a potential impact on the second outcome. In future
research, therefore, more routes can be used in the experiment to compare the advantages
and disadvantages of AI tools in aid of human creative design. Moreover, the changes and
invariance in cultural transfer in AI embedding in different product design processes will
also be further explored.
Author Contributions: Conceptualization, Y.L. and M.S.; methodology, Y.L.; software, Y.Z.; validation,
Y.Z., Y.L. and R.L.; formal analysis, Y.L.; investigation, M.S.; resources, M.S.; data curation, Y.L.;
writing—original draft preparation, Y.L.; writing—review and editing, Y.Z. and R.L.; visualization,
Y.L.; supervision, R.L.; project administration, M.S. All authors have read and agreed to the published
version of the manuscript.
Funding: This research was funded by Beijing Municipal Education Commission, NO. SM202110011005;
and a grant from Graduate School of Beijing Technology and Business University.
Institutional Review Board Statement: The study was approved by the Institutional Review Board
of Louisiana State University.
Informed Consent Statement: Not applicable.
Data Availability Statement: Data are contained within the article.
Acknowledgments: The authors thank all the designers and experts who provided the images for
this study.
Conflicts of Interest: The authors declare no conflict of interest.
Appendix A
Part_01: The questionnaire for self-reporting by student designers
1. What do you think is the degree of AI assistance in improving the aesthetic attraction
of shape?
of craft?
of materials?
4. What do you think is the degree of AI assistance in improving the meaning connection
of shape? (like metaphor and story)
of craft? (like metaphor and story)
of materials (like metaphor and story)
7. What do you think is the degree of AI assistance in improving the emotional touch of
the shape? (like cultural taste and creativity)
the craft? (like cultural taste and creativity)
the materials? (like cultural taste and creativity)
Part_02: The questions for the interview with student designers
1. What are the advantages of using AI to assist in improving the attraction of shape?
What are the limitations?
2. What are the advantages of using AI to assist in improving the attraction of craft?
3. What are the advantages of using AI to assist in improving the attraction of materials?
4. What are the advantages of using AI to assist in improving the meaning connection of
shape? What are the limitations?
craft? What are the limitations?
materials? What are the limitations?
7. What are the advantages of using AI to assist in improving the emotional touch of
shape? What are the limitations?
craft? What are the limitations?
materials? What are the limitations?
Part_03: The questions for evaluation by experts
1. What degree of technical presentation for Chinese culture do you think this jewelry
design has?
2. What degree of meaningful connection with Chinese culture do you think this jewelry
design has?
3. What degree of emotional touch to Chinese culture do you think the shape of this
jewelry design has?
References
1. Hwang, A.H.-C. Too late to be creative? AI-empowered tools in creative processes. In Proceedings of the CHI Conference on
Human Factors in Computing Systems Extended Abstracts, New Orleans, LA, USA, 29 April 2022; pp. 1–9.
2. Midjourney. Available online: www.midjourney.com (accessed on 25 April 2023).
3. Rombach, R.; Blattmann, A.; Lorenz, D.; Esser, P.; Ommer, B. High-resolution image synthesis with latent diffusion models. In
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 19–24 June
2022; pp. 10684–10695.
4. Ramesh, A.; Dhariwal, P.; Nichol, A.; Chu, C.; Chen, M. Hierarchical text-conditional image generation with clip latents.
arXiv 2022, arXiv:2204.06125.
5. Deep Dream Generator. Available online: https://deepdreamgenerator.com/ (accessed on 25 April 2023).
6. Eapen, T.T.; Finkenstadt, D.J.; Folk, J.; Venkataswamy, L. How Generative AI Can Augment Human Creativity. Harv. Bus. Rev.
2023, 101, 55–64.
7. Liao, Q.V.; Subramonyam, H.; Wang, J.; Wortman Vaughan, J. Designerly understanding: Information needs for model trans-
parency to support design ideation for AI-powered user experience. In Proceedings of the 2023 CHI Conference on Human
Factors in Computing Systems, Hamburg, Germany, 23 April 2023; pp. 1–21.
8. Yu, Q.; Meng, K.; Guo, J. Research on innovative application of silver material in modern jewelry design. MATEC Web Conf. 2018,
176, 02013. [CrossRef]
9. Lucas, A.; Chapin, M.; Lin, M.; Jia, X. The Chinese Soul in Contemporary Jewelry Design. Gems Gemol. 2015, 51, 18–30. [CrossRef]
10. Yuan, X. Principle of Design to Follow Nature’s Course. Take Jewelry Design as an Example. In Proceedings of the
3rd International Conference on Arts, Design and Contemporary Education (ICADCE 2017), Moscow, Russia, 30 May
2017; pp. 504–507.
11. Macagnan, C.B.; Seibert, R.M. Culture: A Pillar of Organizational Sustainability. In Ecotheology-Sustainability and Religions of the
World; IntechOpen: London, UK, 2022.
12. Zhao, C. Strategies for promoting the value of tourist cultural and creative brands based on cultural elements. E3S Web Conf.
2021, 251, 03028. [CrossRef]
13. Moalosi, R.; Setlhatlhanyo, K.N.; Sealetsa, O.J. Cultural Memory, an Asset for Design-Driven Innovation within the Creative
Industries Sector: Lessons for Design Education. Des. Technol. Educ. 2016, 21, 9–22.
14. Zhu, Q.; Luo, J. Generative transformers for design concept generation. J. Comput. Inf. Sci. Eng. 2023, 23, 041003. [CrossRef]
15. Goldschmidt, G.; Smolkov, M. Variances in the impact of visual stimuli on design problem solving performance. Des. Stud. 2006,
27, 549–569. [CrossRef]
16. Viswanathan, V.; Tomko, M.; Linsey, J. A study on the effects of example familiarity and modality on design fixation. AI EDAM
2016, 30, 171–184. [CrossRef]
17. Jovanovic, M.; Campbell, M. Generative artificial intelligence: Trends and prospects. Computer 2022, 55, 107–112. [CrossRef]
18. Muller, M.; Chilton, L.B.; Kantosalo, A.; Martin, C.P.; Walsh, G. GenAICHI: Generative AI and HCI. In Proceedings of the CHI
Conference on Human Factors in Computing Systems Extended Abstracts, New Orleans, LA, USA, 30 April 2022; pp. 1–7.
19. Quan, S.J.; Park, J.; Economou, A.; Lee, S. Artificial intelligence-aided design: Smart design for sustainable city development.
Environ. Plan. B Urban Anal. City Sci. 2019, 46, 1581–1599. [CrossRef]
20. Hunde, B.R.; Woldeyohannes, A.D. Future prospects of computer-aided design (CAD)–A review from the perspective of artificial
intelligence (AI), extended reality, and 3D printing. Results Eng. 2022, 14, 100478. [CrossRef]
21. Lyu, Y.; Wang, X.; Lin, R.; Wu, J. Communication in human–AI co-creation: Perceptual analysis of paintings generated by
text-to-image system. Appl. Sci. 2022, 12, 11312. [CrossRef]
22. Song, B.; Soria Zurita, N.F.; Nolte, H.; Singh, H.; Cagan, J.; McComb, C. When faced with increasing complexity: The effectiveness
of artificial intelligence assistance for drone design. J. Mech. Des. 2022, 144, 021701. [CrossRef]
23. Zhou, C.; Li, Y.; Wu, C.; Shao, Y.; Zhou, Y. Study of cognitive activity in AI-augmented design iteration support. In Proceedings
of the 2021 14th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China, 11 December
2020; pp. 78–82.
24. Fatma, N.; Haleem, A.; Bahl, S.; Javaid, M. Prospects of jewelry designing and production by additive manufacturing. In
Proceedings of the Current Advances in Mechanical Engineering: Select Proceedings of ICRAMERD 2020, Bhubaneswar, India,
24 July 2020; pp. 869–879.
25. Katz, B.M. Review essay: Technology and design—A new agenda. Technol. Cult. 1997, 38, 452–466. [CrossRef]
26. Parsons, J.L.; Campbell, J. Digital apparel design process: Placing a new technology into a framework for the creative design
process. Cloth. Text. Res. J. 2004, 22, 88–98. [CrossRef]
27. Cross, N. Human and Machine Roles in Computer-Aided Design; University of Manchester Institute of Science and Technology:
Manchester, UK, 1974.
28. Cross, N. Can a machine design? Des. Issues 2001, 17, 44–50. [CrossRef]
29. Audry, S. Art in the Age of Machine Learning; Mit Press: Cambridge, MA, USA, 2021.
30. Stolterman, E. The nature of design practice and implications for interaction design research. Int. J. Des. 2008, 2, 55–65.
31. Cross, N. Designerly Ways of Knowing: Design Discipline Versus Design Science. Des. Issues 2001, 17, 49–55. [CrossRef]
32. Moggridge, B.; Atkinson, B. Designing Interactions; MIT Press Cambridge: Cambridge, MA, USA, 2007; Volume 17.
33. Stoimenova, N.; Price, R. Exploring the nuances of designing (with/for) artificial intelligence. Des. Issues 2020, 36, 45–55. [CrossRef]
34. Lee, J.H.; Ostwald, M.J. Creative decision-making processes in parametric design. Buildings 2020, 10, 242. [CrossRef]
35. Koskinen, I.; Zimmerman, J.; Binder, T.; Redstrom, J.; Wensveen, S. Design research through practice: From the lab, field, and
showroom. IEEE Trans. Prof. Commun. 2013, 56, 262–263. [CrossRef]
36. Chi, L. Introduction: Design as Research. J. Archit. Educ. 2001, 54, 250. [CrossRef]
37. Pasricha, A.; Greeninger, R. Exploration of 3D printing to create zero-waste sustainable fashion notions and jewelry. Fash. Text.
2018, 5, 1–18. [CrossRef]
38. Garner, S.; McDonagh-Philp, D. Problem interpretation and resolution via visual stimuli: The use of ‘mood boards’ in design
education. J. Art Des. Educ. 2001, 20, 57–64. [CrossRef]
39. Adams, R.S.; Atman, C.J. Cognitive processes in iterative design behavior. In Proceedings of the FIE’99 Frontiers in Education,
29th Annual Frontiers in Education Conference. Designing the Future of Science and Engineering Education, San Juan, PR, USA,
13 November 1999; Volume 11, pp. 11A16/13–11A16/18.
40. Hybs, I.; Gero, J.S. An evolutionary process model of design. Des. Stud. 1992, 13, 273–290. [CrossRef]
41. Adams, R.S. Cognitive Processes in Iterative Design Behavior; University of Washington: Seattle, WA, USA, 2001.
42. Hartley, J. Communication, Cultural and Media Studies: The Key Concepts; Routledge: Abingdon, UK, 2019.
43. Lin, R.-T. Transforming Taiwan aboriginal cultural features into modern product design: A case study of a cross-cultural product
design model. Int. J. Des. 2007, 1, 45–53.
44. Hsueh, S.-L.; Zhou, B.; Chen, Y.-L.; Yan, M.-R. Supporting technology-enabled design education and practices by DFuzzy decision
model: Applications of cultural and creative product design. Int. J. Technol. Des. Educ. 2022, 32, 2239–2256. [CrossRef]
45. Sun, X.; Jin, W.; Li, C. Research on the design of Nanjing museum cultural and creative product from the perspective of experience.
In Proceedings of the Design, User Experience, and Usability: Understanding Users and Contexts: 6th International Conference,
DUXU 2017, Held as Part of HCI International 2017, Vancouver, BC, Canada, 9–14 July 2017; Part III 6. pp. 529–539.
46. Lee, K.-P. Design Methods for Cross-Cultural Collaborative Design Project. In Proceedings of the Futureground—DRS Interna-
tional Conference 2004, Melbourne, Australia, 17 November 2004.
47. Wu, J.; Ju, L.-H.; Lin, P.-H.; Lyu, Y. The Relationship between Form and Ritual in Cultural Sustainability. Sustainability 2022,
14, 9157. [CrossRef]
48. Hsu, C.-H.; Lin, C.-L.; Lin, R. A study of framework and process development for cultural product design. In Proceedings
of the Internationalization, Design and Global Development: 4th International Conference, IDGD 2011, Held as Part of HCI
International 2011, Orlando, FL, USA, 9–14 July 2011; pp. 55–64.
49. Gong, B.-H.; Yuan, R. Study of Contemporary Jewelry Design Emotional Expression Skills. J. Arts Humanit. 2017, 6, 57–61. [CrossRef]
50. Shi, M.; Zhang, C.; Ting, Y.; Lin, P.-H. Application of Auspicious Cultural in Metalworking Jewelry Design. In Proceedings of the
Cross-Cultural Design, Applications in Health, Learning, Communication, and Creativity: 12th International Conference, CCD
2020, Held as Part of the 22nd HCI International Conference, HCII 2020, Copenhagen, Denmark, 19–24 July 2020; pp. 548–558.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.

From Image To Imagination Exploring The Impact of Generative AI On Cultural Translation in Jewelry Design

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

From Image To Imagination Exploring The Impact of Generative AI On Cultural Translation in Jewelry Design

Uploaded by

Copyright:

Available Formats

sustainability

Academic Editor: Yoshiki Shimomura

Received: 5 November 2023

Sustainability 2024, 16, 65. https://doi.org/10.3390/su16010065 https://www.mdpi.com/journal/sustainability

2.1. Computer-Aided Design

2. The workflow in generative

2.2. Activities in Human–AI Collaboration

Figure 3. The workflow of

2.4. Research Framework

3.2. Experimental Procedure

3.3. Analytical Methods

AI- Chiba Red

Type of Design Encoding

Table 3. Changes in jewelry design actions for embedded culture.

Category Design Levels Design Actions

inability 2024, 16, 65

Category Design Levels Design Actions

There are •significant differences in the cultural translation levels (F

Table 4. Categories of feedback for AI-empowered ideation.

Levels Shape Craft

Table 4. Categories of feedback for AI-empowered ideation.

Levels Shape Craft Material

4.3. Evaluation of the Outputs

Type of Design Encoding

To further analyze the distribution characteristics in AI-added value, the regular

Sustainability 2024, To further

5.2. Effects of Generative AI in Augmenting the Imagination

5.3. Challenges in Collaborating with Generative AI

You might also like