(Press-News.org)
Generative artificial intelligence (AI) has the potential to revolutionize fashion design. By recognizing patterns in data and generating new text and images, AI models powered by deep learning algorithms can help fashion designers develop new catalogues, expanding their creativity, with added efficiency, helping to bring products to the market faster.
Large language models (LLMs) like ChatGPT and AI image generators like DALL-E have already shown promising results for many industries and have popularized the use of AI. In fashion, LLMs can help designers and even non-experts understand past styles and predict future fashion trends. These insights can then be used to generate prompts for AI image generators for producing real fashion collections. As such, it is becoming increasingly important to understand how AI can be effectively integrated into fashion.
In a recent study, Professor Yoon Kyung Lee and Master’s student Chaehi Ryu, from the Department of Clothing and Textiles at Pusan National University, South Korea, explored how generative AI can contribute to visualizing seasonal fashion trends. “To use AI effectively in fashion, we must understand the characteristics of generative AI models and make informed judgements of where they can be applied,” explains Prof. Lee. “In this study, we studied how effective prompt engineering can be used to generate realistic fashion collection images through AI.” Their study was published online in the Clothing and Textiles Research Journal on June 22, 2025.
Using ChatGPT-3.5 and ChatGPT-4, the researchers first analyzed men’s fashion trends, based on historical data up to September 2021. From this analysis, they further used ChatGPT to predict men’s fashion trends for fall/winter 2024. Design elements from these predicted trends were classified as “initial codes”. In addition, design elements from Vogue’s 2024 Fall/Winter Men’s Fashion Trend data were used as “modified codes”, and those from literature on fashion design concepts, as “codes from literature”. These elements were then analyzed and regrouped into six final codes: trends, silhouette elements, materials, key items, garment details, and embellishments.
Using these codes, they created 35 prompts for DALL-E 3, each describing a unique outfit. The prompts followed a consistent template featuring a male model walking down a runway at a 2024 Fall/Winter fashion show. The template allowed customization of different details of a real fashion collection event, including aspect ratios, events, camera angles, model appearance and height, runway design, background, and audience details, and moods. Each prompt was run three times, generating a total of 105 images.
DALL-E 3 was able to perfectly implement the prompts 67.6% of the time. Specifically, prompts with adjectives demonstrated a high implementation rate. Some images in the generated collection were very similar to the actual 2024 Fall/Winter Men’s fashion collections. However, there were errors—most images leaned toward ready-to-wear fashion, and DALL-E struggled to incorporate trend elements like gender fluidity. Trend keywords alone were insufficient to generate accurate results, indicating a need for further learning.
“Our results show that expertly worded prompts are necessary for accurate fashion design implementation of generative AI, highlighting the important role of fashion experts,” remarks Prof. Lee. “With further learning and improvements, generative AI models like DALL-E 3 will help fashion designers create entire fashion collections more efficiently, while supporting their creativity, and also help non-experts understand fashion trends.”
Overall, demonstrates that generative AI can be a powerful tool not just for professionals but also for the general public, making it easier than ever to explore, predict, and style the upcoming season’s fashion with confidence.
***
Reference
DOI: 10.1177/0887302X251348003
About Pusan National University
Pusan National University, located in Busan, South Korea, was founded in 1946 and is now the No. 1 national university of South Korea in research and educational competency. The multi-campus university also has other smaller campuses in Yangsan, Miryang, and Ami. The university prides itself on the principles of truth, freedom, and service and has approximately 30,000 students, 1,200 professors, and 750 faculty members. The university comprises 14 colleges (schools) and one independent division, with 103 departments in all.
Website: https://www.pusan.ac.kr/eng/Main.do
About the Prof. Yoon Kyung Lee
Prof. Yoon Kyung Lee is an Assistant Professor at Pusan National University, specialising in creativity and sustainability in fashion design, with a focus on AI, digital technology, and neuroscience. She holds an MSA and Ph.D. in dress aesthetics from Seoul National University, where her dissertation explored Eastern and Western philosophies through the concept of the “Hyperspace Paradigm.” A former designer in Milan, she ran her own brand, UginiO, showcasing at Seoul Fashion Week and Prêt-À-Porter Paris. She has taught at major Korean universities and was a postdoctoral and visiting scholar at the University of Minnesota with Dr. DeLong.
Lab website: https://fashiondesign.pusan.ac.kr/fashiondesign/index.do
ORCID id: 0000-0002-5118-3789
END
Microbial contaminants like airborne bacteria and fungi can make up more than a third of indoor air pollution. Yet, while many countries regulate chemical pollutants, most have no legally binding thresholds for microbial exposure, particularly fungi. This lack of toxicological benchmarks leaves a major gap in indoor air safety policy.
Addressing this gap, a new study led by Professor Wonsuck Yoon of Korea University provides the first species-specific health risk estimates for indoor airborne microbes based on animal toxicity data. This study was made available online on June 9, 2025, and was published on Sep 5, 2025, ...
Aspergillus is a fungus that is commonly found in the environment, both indoors and outdoors. This fungus species can cause aspergillosis—a respiratory infection affecting the lungs. A. fumigatus, A. nidulans, and A. niger are some of the common species within the Aspergillus genus that cause aspergillosis. In high-risk populations, such as immunocompromised individuals, aspergillosis can be life-threatening and lead to poor patient outcomes.
Previous research studies have identified A. latus as an allodiploid hybrid species containing gene sequences from two distinct species: A. spinulosporus and an unknown species related to A. quadrilineatus. Owing to its allodiploid hybrid ...
Patients with heart failure and atrial fibrillation (AF) at the time of mitral transcatheter edge-to-edge repair (M-TEER) for severe mitral regurgitation are more than twice as likely to die or be rehospitalized for heart failure, compared to patients without AF. These are the findings from a Mount Sinai Fuster Heart Hospital study that links the presence of AF at the time of the procedure to worse outcomes following the procedure.
The results, published July 17 in the Journal of the American Heart Association, suggest that AF may have to be treated more aggressively before patients undergo this type of transcatheter procedure in order ...
A team of scientists has developed a powerful new way to detect subtle magnetic signals in common metals like copper, gold, and aluminium—using nothing more than light and a clever technique. Their research, recently published in the prestigious journal Nature Communications, could pave the way for advances in everything from smartphones to quantum computing.
The Longstanding Puzzle: Why Can’t We See the Optical Hall Effect?
For over a century, scientists have known that electric currents bend in a magnetic ...
Scientists have used an AI model to reassess the results of a completed clinical trial for an Alzheimer’s disease drug. They found the drug slowed cognitive decline by 46% in a group of patients with early stage, slow-progressing mild cognitive impairment – a condition that can progress to Alzheimer’s.
Using AI allowed the team to split trial participants into two groups: either slowly or rapidly progressing towards Alzheimer’s disease. They could then look at the effects of the drug on each group.
More precise selection ...
A new study from the Hebrew University of Jerusalem reveals that Neanderthals living in two nearby caves in northern Israel—butchered their food in noticeably different ways. Despite using the same tools and hunting the same prey, groups in Amud and Kebara caves left behind distinct patterns of cut-marks on animal bones, suggesting that food preparation techniques may have been culturally specific and passed down through generations. These differences cannot be explained by tool type, skill, or available resources, and may reflect practices such as drying or aging meat before butchering. The findings provide rare insight into the ...
Did Neanderthals have family recipes? A new study suggests that two groups of Neanderthals living in the caves of Amud and Kebara in northern Israel butchered their food in strikingly different ways, despite living close by and using similar tools and resources. Scientists think they might have been passing down different food preparation practices.
“The subtle differences in cut-mark patterns between Amud and Kebara may reflect local traditions of animal carcass processing,” said Anaëlle Jallon, ...
Magnets and shot glasses serve as fun holiday souvenirs, but certain foods synonymous with a country’s identity can make for extra meaningful gifts for friends and loved ones; think French cheese, Dutch Stroopwafels and Canadian maple syrup.
According to new research, communities that lived in western Iran about 11,000 years ago during the Early Neolithic period took a similar approach when it came to gift-giving.
They invested significant effort to bring wild boars hunted in dispersed parts of ...
Niigata, Japan – A group led by the Department of Neurosurgery at the Brain Research Institute, Niigata University, has successfully treated a patient with a brainstem glioma harboring a rare IDH2 mutation. The patient initially presented with a gradual loss of hearing in the left ear, and MRI showed a lesion at the left side of the brainstem, near the root exit zone of the left acoustic nerve. Initially, a brainstem glioma with H3K27M mutation was suspected. However, the gradual clinical course and unusual location of the brainstem glioma were considered atypical. The patient underwent magnetic resonance spectroscopy in which 2-hydroglutarate, a marker for IDH ...
Recently, Professor Dong Eon Kim from POSTECH's Department of Physics and Max Planck Korea-POSTECH Initiative and his research team have succeeded in unraveling for the first time the mystery of the 'electron tunneling' process, a core concept in quantum mechanics, and confirmed it through experiments. This study was published in the international journal Physical Review Letters and is attracting attention as a key to unlocking the long-standing mystery of 'electron tunneling,' which has remained unsolved for over 100 years.
While the idea of teleporting ...
