Submit a Project

ML x ART

A showcase with creative machine learning experiments

👋 I'm Emil, a resident at the Google Arts & Culture Lab. I've curated this collection.

Year
Artist
Technology
Theme
Medium
Default order

Jonathan Fly

Apply GauGAN on Charlie Chaplin dressed as a tree

GauGAN, GAN

J. Rosenbaum

GAN-generated roman statues with generative music and descriptions

GAN

David Ha

Use K-means to segment and colorize an image, inspired by Warhol

K-means

Kishi Yuma

GAN interpolation

GAN

Manny Tan, Kyle McDonald, Google Creative Lab

A visual map of drum sound made by extracting the features and clustering them with t-SNE

t-SNE

Alexander Reben

DeepDream applied to Bob Ross's video and sound synthesized with Wavenet

DeepDream, Wavenet

Stanislas Chaillou

StyleGAN interpolation, trained on Karl Blossfeldt's herbarium (1928)

StyleGAN

Monolesan

Using PoseNet to create art using your body parts like eyes, hands, chest and knees

PoseNet, Camera, TensorFlow.js

Mario Klingemann, Albert Barqué-Duran

Generate a pose, use a pix2pix model to turn the pose into an artwork and then paint it live

PoseNet, pix2pix, GAN

Xander Steenbrugge

GAN generated textures and post processing in B3D with meditative music

GAN, B3D

Tony Beltramelli

Translate image features from a graphical user interface to RNN generated website

Image Captioning, pix2code, RNN, LSTM, CNN

Jürgen Schmidhuber

Create an artwork with the shortest algorithm while at the same time captures the essence of an object, using Kolmogorov Complexity

Occam's razor, Kolmogorov complexity

Yotam Mann, Google Creative Lab

A tool to mix the latent space of two instruments

VAE, Magenta

Alexander Mordvintsev, Nicola Pezzotti, Ludwig Schubert, Chris Olah

3D Style Transfer

Style Transfer, 3D

François Quévillon

Visualize the Object Detection ability of footage from a self-driving car

Object Detection

Michael Friesen

Create images in the style of Beksinski with CLIP and BigGAN

Big Sleep, CLIP, BigGAN

Sofia Crespo

CNN generated blend of nature posters

CNN

Yuguang Zhang

A GAN trained on the artists sleeping patterns and then interpolated by a custom sheet folding machine

GAN, Hardware

Harshit Agrawal

GAN created on images of surgical dissections

GAN

Ross Goodwin, Oscar Sharp

An LSTM generated screenplay trained on sci-fi screenplays, and produced according to the screenplay

RNN, LSTM

NaN

An interactive demo to type with StyleGAN-generated letterforms

StyleGAN

Sofia Crespo

Use Style Transfer from creatures and plants, to create new creatures, printed

Style Transfer, Texture synthesis

Annie Dorsen

Create a text model, potentially using Markov Chains, based on the debate between Michel Foucault and Noam Chomsky and performed as a theatre piece

Markov Chains

Sofia Crespo

Lenticular print of images made with a CNN

CNN, Lenticular Print

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners