Lexus Uses AI to Help Customers Envision Their Crossover Anywhere

With the help of AI, these Lexus vehicles don't actually need to be in Antarctica to be pictured there!

By Brett Foote - April 14, 2023
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere
Lexus Uses AI to Help Customers Envision Their Crossover Anywhere

Imaginary World

Artificial intelligence is everywhere these days, helping us make fancy pictures and even conjure up recipes or other ideas. Thus, it's no surprise that automakers also plan on incorporating AI into their vehicles, though Lexus is currently utilizing this technology in a different way - to allow visitors to the New York Auto Show envision the Lexus RX or Lexus RZ 450e in their own desired surroundings. 

Photos: Lexus

Creating an Image

During the course of the auto show, visitors can type in a prompt and place the RX or RZ450e anywhere their imagination desires, thanks to the power of artificial intelligence. They can do this via a 98-inch screen, which uses their input to generate an image of either crossover in any backdrop they can fathom, which guests can even email themselves after they're complete.

Photos: Lexus

Teaming Up

To develop the AI art tool, Lexus collaborated with data scientists and machine learning engineers at Toyota Connected North America (TCNA), a data, cloud, artificial intelligence, machine learning and software center of excellence headquartered in Plano, Texas. TCNA leveraged state-of-the-art Generative AI models such as Stable Diffusion and ControlNet architectures to train a proprietary Generative AI model to generate photorealistic or artistic style images - all by way of text input.

Photos: Lexus

Complex Mission

The model was trained on more than 500 photos of each vehicle, capturing every detail imaginable. Additionally, the stable diffusion model was trained on LAION-5B dataset from non-profit organization LAION to use for backgrounds, artistic styles, and detailing.

Photos: Lexus

Creating a Bond

"At TCNA, we are always looking at new ways to leverage data, artificial intelligence, machine learning, and other cutting-edge technologies to deliver value to our customers and engage with them," said Shravanthi Denthumdas, vice president of Engineering, Mobility & Emerging Technologies, TCNA. "Generative AI is such a new field for most of the companies, and we're enthusiastic for our partnership with the Lexus marketing team and utilize this technology to develop strong bonds with guests."

Photos: Lexus

Follow Up

This next-level engagement follows up on last year's successful launch of Lexus Performance Driving School's first non-fungible token (NFT), which provided guests who completed the program a digital keepsake. Embedded with performance data and hero images, more than 60 guests minted their NFTs to their cryptocurrency wallets, where they can keep them in perpetuity or use them to potentially unlock future experiences with the Lexus brand.

Photos: Lexus

Connecting With Guests

"Lexus is focused on creating innovative ways to connect with our guests, and this time, we're using Generative AI technology at the New York International Auto Show to engage with them in a unique and very personalized way," said Vinay Shahani, vice president of Lexus Marketing. "As we’ve shown with the recent launches of the all-new Lexus RX and RZ, intuitive technology is a key pillar of the brand, and this experience featuring these two vehicles provides guests the opportunity to explore what it would look like to have the RX and RZ as a part of their everyday lives and their dreams."

Photos: Lexus

>>Join the conversation about these AI-generated images right here at ClubLexus.com.

For help with your maintenance and repair projects, please visit our How-to section in the forum.

NEXT
BACK
NEXT
BACK