MIT researchers developed an algorithm trained to generate horrifying images in an attempt to find the scariest faces and locations possible, and then rely on humans to see which approach makes the freakiest images.
Using TITAN X GPUs and cuDNN to train their deep learning models, the researchers used the infamous style transfer technique and generative adversarial networks to curate the ghoulish images.
“We use state-of-the-art deep learning algorithms to learn what haunted houses, ghost towns or toxic cities look like,” said MIT Media Lab researcher Pinar Yanardag Delul. The algorithm extracts elements — such as a bruised-black palette — from scary templates and implants them in the landmarks.
The researchers also used Google’s DeepDream method to develop ghastly portraits and voters can rate the images on the Nightmare Machine website to teach the system to make images even scarier.
Read more >
AI-Powered ‘Nightmare Machine’ Generates Horrifying Images
Oct 27, 2016
Discuss (0)

Related resources
- GTC session: Unlocking AI to Build the Metaverse (Spring 2023)
- GTC session: Learn How Artists Use Generative AI in their Workflows (Spring 2023)
- GTC session: Generating Modern Masterpieces: MoMA Dreams Become a Reality (Spring 2023)
- Webinar: Optimizing AI Image and Video Generation Tools with NVIDIA and Runway
- Webinar: Isaac Developer Meetup #2 - Build AI-Powered Robots with NVIDIA Isaac Replicator and NVIDIA TAO
- Webinar: NVIDIA Inception: Maximize Your Benefits