Full Stack AI for Media & Culture

Research and rapid deployment of Artificial Intelligence and generative systems for creative applications.

faceØff

Real-time Deepfakes

f

faceØff showcases our in-house deep learning architecture and production pipeline, blending multiple neural networks and objective functions by using AI to transform your face in real-time. Unlike AR apps that apply a generic mask to everyone, faceØff completely reconstructs your face with a model’s likeness to generate a result that is unique to you!

faceØff enables users to record videos or photos with their choice of face and shock their friends with their own live deep fake creations.

faceØff

Real-time Deepfakes

f

faceØff showcases our in-house deep learning architecture and production pipeline, blending multiple neural networks and objective functions by using AI to transform your face in real-time. Unlike AR apps that apply a generic mask to everyone, faceØff completely reconstructs your face with a model’s likeness to generate a result that is unique to you!

faceØff enables users to record videos or photos with their choice of face and shock their friends with their own live deep fake creations.

genmo

Create AI-powered curiosities from your photos and videos

genmo_straight

Genmo (short for Generative Mosaic) is an AI-powered app that recreates any photo or video using an entirely separate set of images. No original video content remains after processing - and no filters - the new clip is completely synthesized by our neural network. Take a picture or video, select a dataset to render it with, and get your recreated piece back in seconds!

We use our own deep neural network architecture, which hybridized a generative adversarial network (GAN) with other neural network models. It’s fast (relatively!) and, unlike other popular AI-based image manipulation tools, we do not use a pre-trained classification network. Image and video is redrawn at near real-time speed from an arbitrarily chosen image set on-demand.

genmo

Create AI-powered curiosities from your photos and videos

genmo_straight

Genmo (short for Generative Mosaic) is an AI-powered app that recreates any photo or video using an entirely separate set of images. No original video content remains after processing - and no filters - the new clip is completely synthesized by our neural network. Take a picture or video, select a dataset to render it with, and get your recreated piece back in seconds!

We use our own deep neural network architecture, which hybridized a generative adversarial network (GAN) with other neural network models. It’s fast (relatively!) and, unlike other popular AI-based image manipulation tools, we do not use a pre-trained classification network. Image and video is redrawn at near real-time speed from an arbitrarily chosen image set on-demand.

Art on the Mart - Homage in Between

Art on the Mart
Homage in Between

This projection-mapped video (with audio track) was commissioned by the Terra Foundation for the inauguration of a public art program called Art on the MART. It was projected on the Merchandise Mart's 2.5 acre south wall in downtown Chicago from Sept 29, 2018 to Dec 31, 2018.

about us

Our group explores the creative potential of generative systems and AI.With an emphasis on real world production, we build deep neural networks to engage with the problems and opportunities of creating original art through computational means. Our work is currently based at the University of Chicago and supported by Jason Salavon Studio.

We are artists, programmers, and researchers investigating how deep learning and other generative systems can impact creative production. We welcome opportunities & partnerships to collaborate in this endeavor.

Contact us at hey@latentculture.com