Generative AI to revolutionise fashion design: Research
Large language models (LLMs) like ChatGPT and AI image generators like DALL-E have shown promising results across industries and popularised the use of AI. In fashion, LLMs can help designers and non-experts understand past styles and predict future fashion trends. These insights can then generate prompts for AI image generators to produce real fashion collections. As such, it is 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 visualising 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," explained. Lee. "In this study, we studied how effective prompt engineering can be used to generate realistic fashion collection images through AI."
A study by Pusan National University shows that generative AI, using tools like ChatGPT and DALL-E 3, can help visualise and predict fashion trends. By analysing past data and crafting precise prompts, AI generated realistic Fall/Winter 2024 men's fashion images. While effective, limitations remain, highlighting the need for expert input.
Using ChatGPT-3.5 and ChatGPT-4, the researchers first analysed men's fashion trends, based on historical data up to September 2021. From this, they used ChatGPT to predict men's fashion trends for Fall/Winter 2024. Design elements from these predictions 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 as 'codes from literature'. These were then 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 customisation of event details, 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 per cent of the time. Prompts with adjectives demonstrated a high implementation rate. Some generated images closely resembled actual 2024 Fall/Winter Men's fashion collections. However, there were errors—most leaned toward ready-to-wear fashion, and DALL-E struggled with 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," added 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."
The study shows 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.
Fibre2Fashion News Desk (RR)
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Mint
2 minutes ago
- Mint
OpenAI's $500 billion ambition puts it in elite club—and in the crosshairs
Just a week after OpenAI secured fresh funding at a $300-billion valuation, reports emerged of potential share sales at $500 billion. If it goes through, that kind of valuation would place OpenAI among only around 20 companies valued at over half a trillion dollars globally. OpenAI's latest funding round, worth $8.3 billion, was oversubscribed five times. The investor appetite reflected their confidence in the AI startup's ability to dominate a market that the UN Trade and Development projects will explode by 25 times in size in a decade. OpenAI's momentum is undeniable. The company has continuously upgraded its flagship ChatGPT product, recently launching GPT-5, which it claims can provide PhD-level expertise. Financially, its revenues have doubled in seven months, reaching $1 billion a month, with projections to hit $20 billion in annualised revenue by the end of the year. The capital influx will primarily help OpenAI scale its compute infrastructure, particularly Stargate, a joint venture with Japanese investment firm SoftBank and technology company Oracle to build the world's largest AI supercomputing infrastructure. OpenAI is also setting up its first data centre in Europe next year, which will house 100,000 Nvidia processors. This infrastructure investment is critical as companies race to control the data centres and AI chips essential for training and operating advanced artificial intelligence models. The numbers reflect this reality. Global data centre capacity surged from 20GW in 2016 to 57GW in 2024, with Goldman Sachs projecting 122GW by 2030. While OpenAI's valuation reflects investor confidence, the fundraising itself underscores the infrastructure investments needed to maintain leadership in the AI market. Challenger pack OpenAI faces growing competition from well-funded AI startups. Anthropic, founded by former OpenAI employees, is nearing a $5 billion funding round that would value it at $170 billion, up from $61.5 billion in March. Elon Musk's xAI has raised $10 billion at an $80 billion valuation and is seeking additional funding at a potential $200 billion valuation. Venture capital funding to AI companies has exceeded $40 billion in each of the past three quarters, according to Crunchbase. This financial backing is translating into competitive model performance. On the GPQA Diamond benchmark, which tests PhD-level science questions, xAI's Grok 4 Heavy scored 88.9% and Anthropic's Claude Opus 4.1 scored 80.9%. The landscape shifted when Chinese startup DeepSeek released powerful open-weight models available for free. OpenAI released its own open-weight models in response. The competition now spans both proprietary and open-source approaches. Incumbent advantage OpenAI also faces pressure from the Big Tech firms. Meta, Google, Amazon, and Microsoft have collectively spent $291 billion over the past year, largely for AI infrastructure. Last month, in a $2.4 billion deal, Google hired key executives from Windsurf, an AI coding company that OpenAI wanted to acquire. Google has also integrated 'AI Overviews' with its search engine, turning it into an 'answer engine" that directly competes with the core function of chatbots like ChatGPT. This strategy leverages Google's 2 billion monthly users and its market dominance. Meta, meanwhile, is restructuring its AI division into Meta Superintelligence Labs. It has also acquired top-tier AI researchers from OpenAI, with multi-million-dollar compensation packages. Partner paradox OpenAI's relationship with Microsoft, however, has turned complicated. Microsoft, OpenAI's primary backer with a $13.75 billion investment, is also a direct competitor seeking to lead the AI revolution. Copilot, Microsoft's AI platform, boasts over 100 million monthly users. Microsoft's server products and cloud services revenue jumped 27% year-over-year in the three months ended 30 June, driven by growth in Azure, its cloud or remote computing platform. Microsoft holds crucial leverage as OpenAI attempts to convert into a for-profit company—a prerequisite for unlocking SoftBank funding and IPO plans. However, Microsoft has been withholding approval as both companies negotiate revising their contract, set to expire in 2030. A major sticking point is a clause that could terminate Microsoft's access to future OpenAI technology if the startup's board declares that artificial general intelligence—AI's capacity to learn and understand like humans and apply that knowledge to execute tasks—has been achieved. This friction has real consequences: OpenAI's attempt to acquire AI coding startup Windsurf failed because Microsoft's IP rights would have extended to the new technology, which Windsurf rejected. OpenAI needs capital to overcome these structural challenges and funding obstacles. is a database and search engine for public data
Time of India
2 minutes ago
- Time of India
OpenAI announces million-dollar bonuses to nearly 1,000 employees to retain AI talent
Academy Empower your mind, elevate your skills ChatGPT maker OpenAI has announced massive bonus payouts for about 1,000 employees, which is approximately one-third of its full-time the eve of GPT-5's launch, OpenAI CEO Sam Altman sent a surprise message to employees via communication platform Slack. A quarterly bonus for two years was awarded to researchers and software engineers in the firm's applied engineering, scaling, and safety domains, according to The payouts vary by role and seniority. Top researchers will receive mid-single-digit millions as bonus, while engineers will get hundreds of thousands. Bonuses will be distributed quarterly for two years and can be received in stock, cash, or a combination of informed that the rise in compensation was a result of market dynamics, likely driven by the demand for AI talent."As we mentioned a few weeks ago, we have been looking at comp for our technical teams given the movement in the market," The Verge cited Altman's message to employees as saying."We very much intend to keep increasing comp as we keep doing better and better as a company," he wrote. "But we wanted to be transparent about this one since it's a new thing for us," he giants and well-funded startups in Silicon Valley are intensifying competition for AI expertise, announcing bonuses to attract talent. Altman has recently lost several key researchers to Meta, while Elon Musk's xAI is also seeking to attract is OpenAI's second-largest market in the world after the US, and it may well become its biggest market in the near future, according to its CEO Sam is available to all users, with Plus subscribers getting more usage, and Pro subscribers getting access to GPT‑5 pro, a version with extended reasoning for even more comprehensive and accurate answers."GPT‑5 is a unified system with a smart, efficient model that answers most questions, a deeper reasoning model (GPT‑5 thinking) for harder problems, and a real‑time router that quickly decides which to use based on conversation type, complexity, tool needs, and your explicit intent," the company noted.
Indian Express
32 minutes ago
- Indian Express
OpenAI's GPT-5 is now free for everyone: Here's what's new and how to access it
The race to create the most advanced AI chatbot is on – and it's brutal. Earlier this week, OpenAI unveiled its latest LLM model, GPT-5, which it claims can provide PhD-level expertise in areas such as coding and writing. That's a bold claim. Even Elon Musk made a similar statement about his own AI chatbot, Grok, which is integrated into X (formerly Twitter). With GPT-5, the general-purpose model offers improved reasoning capabilities and strong coding skills. However, some experts argue that the launch is more about keeping the hype alive than delivering a significant leap over previous versions. Whether or not Sam Altman's claims about GPT-5 hold true remains to be seen. But if you are curious about GPT-5, here's a quick rundown of what's new in the latest AI model including its key features and functions. GPT-5 is free to access (available to 700 million weekly users); however, usage on the free version of ChatGPT is capped. OpenAI generates revenue by offering subscriptions to more powerful versions of the chatbot and by integrating its models into enterprise IT systems. For example, with the $20 per month ChatGPT Plus subscription, users receive 'significantly higher usage' limits compared to free users. Meanwhile, ChatGPT Pro subscribers, who pay $200 per month, get unlimited access to GPT-5 and can use GPT-5 Pro, an even more advanced version of the model. OpenAI has stated that Enterprise and Education users will receive 'generous limits.' Many beginner programmers and developers use ChatGPT for coding, and with GPT-5, OpenAI claims the new AI model is even better at writing code. With 'vibe coding' becoming increasingly popular, GPT-5 has the potential to become your go-to coding partner. During a demo, company executives demonstrated how GPT-5 can be used to create custom, interactive applications such as websites, apps, and games on demand using a simple prompt. Of course, GPT-5 isn't perfect and will still make mistakes, but the model represents a major leap forward compared to previous versions, especially in terms of coding capabilities. When you now log in to ChatGPT powered by GPT 5, the AI chatbot will let you choose from four different preset 'personalities' when they interact with it: 'cynic,' 'robot,' 'listener,' and 'nerd.' The idea behind these personalities to make the chatbot feel more natural. You can also adjust them in ChatGPT settings. OpenAI says the new personalities were specifically designed to reduce the sycophancy issue with GPT-4o. One of the most interesting use cases of ChatGPT has always been its integration with external apps like Google Drive. Now, with GPT-5, it integrates with Gmail and Google Calendar to assist with scheduling, reminders, email follow-ups, and other productivity tasks. Going forward, ChatGPT will automatically pull information from these apps and reference it as needed. Think of it as your personal AI agent. This feature, however, will initially be available only to Pro users and is expected to start rolling out next week. OpenAI said the main improvements in GPT-5 include fewer factual errors, or 'hallucinations,' compared to earlier models. Hallucinations have been a persistent issue in AI systems. Researchers have concluded that completely eliminating hallucinations is impossible, meaning AI companies must focus on reducing their frequency as much as possible. In GPT-5's case, responses are about 45 per cent less likely to contain factual errors than those generated by GPT-4o, according to OpenAI. That said, GPT-5 can still hallucinate, even during common tasks. More and more people are using ChatGPT to answer health-related questions instead of doing a Google search, reflecting a shift in user behavior. In fact, OpenAI says GPT-5 scores higher than any of its previous models on the HealthBench test and acts more like 'an active thought partner,' proactively flagging potential concerns and asking questions to provide more helpful answers. To be clear, an AI chatbot is not a substitute for a doctor and never will be. It is always recommended to consult a doctor or seek professional medical help before making any health-related decisions, even in emergencies. OpenAI emphasised that its new model, GPT-5, is easier to use. The key differentiator between GPT-5 and other OpenAI models is the real router feature, which allows GPT-5 to automatically determine which model to use based on the conversation, the complexity of the prompt, and more. GPT-5 is certainly an interesting model, especially because it's now powered by what's called a reasoning model, meaning it thinks harder about solving problems. However, OpenAI's new model is more of an evolution than a revolution. That's similar to what every new iPhone or smartphone release has become. While GPT-5 may be more 'intelligent,' the company has yet to find a clear path toward artificial general intelligence (AGI), the ultimate goal for every AI company, including OpenAI. Anuj Bhatia is a personal technology writer at who has been covering smartphones, personal computers, gaming, apps, and lifestyle tech actively since 2011. He specialises in writing longer-form feature articles and explainers on trending tech topics. His unique interests encompass delving into vintage tech, retro gaming and composing in-depth narratives on the intersection of history, technology, and popular culture. He covers major international tech conferences and product launches from the world's biggest and most valuable tech brands including Apple, Google and others. At the same time, he also extensively covers indie, home-grown tech startups. Prior to joining The Indian Express in late 2016, he served as a senior tech writer at My Mobile magazine and previously held roles as a reviewer and tech writer at Gizbot. Anuj holds a postgraduate degree from Banaras Hindu University. You can find Anuj on Linkedin. Email: ... Read More
