Artificial intelligence
LG's AI designer debuts at New York Fashion Week
The LG-developed hyperscale AI Exaone created Tilda, which can be commercialized in the visual design field
By Feb 16, 2022 (Gmt+09:00)
2
Min read
Most Read
LG Chem to sell water filter business to Glenwood PE for $692 million


Kyobo Life poised to buy Japan’s SBI Group-owned savings bank


KT&G eyes overseas M&A after rejecting activist fund's offer


StockX in merger talks with Naver’s online reseller Kream


Mirae Asset to be named Korea Post’s core real estate fund operator



South Korean fashion label Greedilous showcased its 2022 Fall-Winter collection on the main stage of the New York Fashion Week on Monday local time.
Beyonce and Paris Hilton are both fans of the Greedilous label by Park Youn-hee.
The Greedilous by Tilda – Flowers on Venus collection is a collaboration between Park and an artificial intelligence designer named – you guessed it – Tilda, developed by LG Corp.
On Dec. 14 last year, LG’s artificial intelligence research institute unveiled a hyperscale AI engine called Exaone.
Scientists at the research center have been developing Exaone into an AI system that can think, learn, and make judgments like a human by learning large-scale data on its own.
Tilda is Exaone’s first AI-based human.
For the biggest fashion gala in North America, Tilda designed some 200 outfits based on its own machine learning of more than 3,000 patterns and images.
This is how it works.
Once the images are generated, Park begins her designing process based on them.
“In the past, I had to work with dozens of designers for months to get inspiration and prepare a collection,” Park said. “With Tilda, I finished the work in a month and a half.”
The South Korean-born designer said the collection is the result of Tilda’s creativity and human emotions.
The Greedilous New York collection is the first time hyperscale AI entity has succeeded in the visual design field. Until now, AI was mostly used to create text-based content using natural language processing (NLP.)
LG explained that Tilda uses "multi-modal" AI, which allows it to comprehend not just the text but also its context. That in turn translates into the ability to create completely new images.
Exaone has some 300 billion parameters and is equipped with multi-modal capabilities to acquire and process information related to nearly all aspects of human communication, not just written and spoken languages.
The research institute has trained Exaone to study 600 billion text corpus and 250 million images simultaneously.
Parameters refer to where AI’s learned data via deep learning gets stored, and is often used as a measure of how well a model is performing. In human physiology, they are somewhat comparable to synapses.
“The latest collaboration has shown that AI can work with humans in areas that require creativity and imagination,” said chief of LG AI Research Bae Kyung-hoon. “Later this year, fashion items designed by Tilda will be available for sale offline and at metaverse events.”
Write to Su-Bin Lee at lsb@hankyung.com
Jee Abbey Lee edited this article.
More to Read
-
StartupsKAIST Holdings to open US offices with $8.4 bn value in mind
Feb 15, 2022 (Gmt+09:00)
3 Min read -
-
Artificial intelligenceNaver recruits two AI scholars based in US
Jan 25, 2022 (Gmt+09:00)
3 Min read -
Artificial intelligenceLG unveils multimodal ‘supergiant AI’ with unprecedented parameters
Dec 14, 2021 (Gmt+09:00)
2 Min read
Comment 0
LOG IN