IIT Roorkee Breakthrough Blends Artificial Intelligence and Design to Power Sustainable Fashion of the Future  

Roorkee, Uttarakhand, January 30, 2026: The Indian Institute of Technology Roorkee (IIT Roorkee) has achieved a pioneering milestone in artificial intelligence and creative design with the development of the FLORA dataset and NeRA adapter, two groundbreaking innovations that redefine the way AI understands, interprets, and generates fashion. The study, titled “Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and a Novel NeRA Adapter for Enhanced Feature Adaptation,” showcases India’s-first framework that enables AI models to generate detailed, high-fidelity outfit sketches from their textual descriptions.
 
Fashion thrives on imagination; however, designers have to spend a lot of time in translating creative ideas or concepts into sketches. Fashion designers also need to adapt to the latest fashion trends and propose personalized apparel designs. In previous times, customers would search for a dress using simple keywords such as a "blue shirt". However, modern customers and designers work with complex vocabulary such as “a minimalist, cropped rayon blouse with a Mandarin collar and raglan sleeves”. Many current AI tools struggle to understand this kind of professional fashion language. This research helps solve that problem by teaching AI to understand detailed clothing terms and translate them into fashion sketches.
 
The research, led by Prof. Sparsh Mittal (Department of Electronics and Communication Engineering, Joint Faculty in Mehta Family School of Data Science and Artificial Intelligence,  IIT Roorkee), represents a major leap in India’s pursuit of AI-driven, precise and expressive design in the fashion industry.

Most existing fashion datasets rely on photographs or catalog images. These are helpful for shopping websites, but they don’t capture what designers usually draw in their sketchbooks. FLORA is different: it includes pairs of professional fashion sketches and their textual descriptions, using the kind of terms designers use, such as silhouettes, materials, textures, and overall style. When an AI model is trained on the FLORA dataset, it can learn to connect detailed words with the right visual features. Thus, this AI model can understand not just simple terms like a “blue dress” but “a cobalt blue evening gown with a soft draped cowl neckline and ruched bodice.”
 
Along with FLORA, the NeRA (Nonlinear Expressive Representation Adapter) adapter is a new method that helps AI models learn these design connections faster and more accurately. The open-source release of FLORA and NeRA will empower researchers and designers globally to collaborate and innovate at the intersection of art, technology, and sustainability.
 
Prof. Sparsh Mittal, the lead researcher, stated, “Our work brings AI and design together to make creativity easier, faster, and more sustainable. Modern fashion includes small details that many AI models could not understand well. With FLORA and NeRA, we help AI understand a designer’s ideas through detailed sketches and precise design terms. This can speed up new developments in fashion, retail, and other areas. This research connects creativity and technology, supporting the vision of a self-reliant and digitally strong India.”
 
Prof. Kamal Kishore Pant, Director, IIT Roorkee, congratulated the team, saying, “This remarkable achievement underscores IIT Roorkee’s commitment to cutting-edge interdisciplinary research. Innovations like FLORA and NeRA demonstrate how AI can be harnessed to enhance India’s creative economy and bolster its global leadership in design and technology.
 
This innovation directly supports India’s national missions, including Digital India, Make in India, and the National AI Mission, by fostering indigenous technologies that empower creative industries and promote sustainable design solutions. By integrating AI into fashion design, it shortens the design cycle and democratizes fashion design creating scalable innovation opportunities in India’s rapidly growing fashion and textile sectors. It unlocks a new level of personalized shopping by allowing customers to use highly descriptive language to search hyper-specific products or virtual try-on outfits. This research offers transformative implications across various industries, including personalized fashion design, virtual retail, gaming, metaverse applications, and sustainable manufacturing.
 
The study also reinforces India’s leadership in AI-based innovation that aligns with the United Nations Sustainable Development Goals (SDG 9: Industry, Innovation, and Infrastructure) and SDG 12 (Responsible Consumption and Production). It reflects IIT Roorkee’s growing contribution to advancing AI technologies that are not only technically superior but also socially and environmentally responsible.
 
The research paper is co-authored by Gayatri Deshmukh (Independent Researcher), Somsubhra De (IIT Madras), Chirag Sehgal (Delhi Technological University), Jishu Sen Gupta (IIT BHU), and Prof. Sparsh Mittal (IIT Roorkee).
 
This innovation establishes IIT Roorkee as a frontrunner in generative AI research with a profound societal impact, where technology serves imagination, sustainability, and the future of design.