Simulation / Modeling / Design

Say Cheese! Make Your Day “Flamin’ Hot” By Turning Your Photos into Cheetos With Artificial Intelligence

AI-Generated Summary

  • The Cheetos Vision app applies a Cheetos-inspired visual style to photos and videos using a convolutional neural network trained on Cheetos images.
  • Development relied on an NVIDIA GeForce GTX 1080 GPU and the cuDNN-accelerated TensorFlow deep learning framework.
  • The app debuted on the App Store during the SXSW conference in Austin in March 2018.

Next Steps

  • Download the Cheetos Vision app to transform photos and videos into Cheetos-style images.
  • Explore deep learning resources on the NVIDIA Developer site to learn about the underlying technology.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more

Have you ever thought what the world would look like if it was made out of Cheetos? Now you can. The popular snack is inviting their fans, and anyone else with an iPhone, to see the world in “Cheetos Vision.”
Based on the popular ‘style transfer’ algorithm that applies a unique style to the photo you’ve taken, the Cheetos team contracted the ad agency, Goodby Silverstein & Partners, to develop an application that uses deep learning to turn your photos and videos into Cheetos masterpieces.
Using an NVIDIA GeForce GTX 1080 GPU and the cuDNN-accelerated TensorFlow deep learning framework, the team trained their convolutional neural network on Cheetos images.
“We started with just still photos and were able to expand it to video for launch.” Rachel Ferdinando, vice president of marketing for Cheetos, told Chief Marketer.
The mobile app was released on the App Store during the SXSW conference in Austin last week.

Discuss (0)

Tags