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

Helena Sarin

SNGAN trained on doodles and upscaled and colorized with CycleGAN

GAN, CycleGAN, SNGAN

Sofia Crespo

Lenticular print of images made with a CNN

CNN, Lenticular Print

Lulu xXX

DJ video with video texture advection with flipfluids and Optical Flow based Style Transfer

StyleTransfer, Optical Flow, deepflow

Max Braun

A StyleGAN trained on eBoy's database of pixel art

GAN

Will Stedden

Translate artist's 3500-word story into a video using CLIP-based Story2Hallucination

Story2Hallucination, CLIP, BigGAN

Mike Tyka

RNN generated tweets trained on US political bots and printed like Tweets

RNN

Scott Eaton

Custom pix2pix HD turning sketches into bodies

pix2pix, GAN

Max Frenzel

Visualize how variables in a music VAE are updated on a 2D surface

VAE

Nouf Aljowaysir

Using U-2 Net, the artist removed ‘oriental’ stereotypical figures in the dataset and then trained it on StyleGAN2 to signify the eradication of her ancestor’s collective memory

U-net, U-2 Net, StyleGAN

Manny Tan, Kyle McDonald, Google Creative Lab

Thousands of bird sounds visualized using an RNN model

RNN

Parag K. Mital

Corpus-based visual synthesis applied to Miley Cyrus's Wrecking Ball

Corpus-based synthesis

Andeep Singh Toor, Fred Bertsch, Google Research, Brain Team

An interactive web app that turns scribbles into monsters using CreatureGAN

CreatureGAN, GAN

Xavier Snelgrove and Matthew Tesfaldet

Generate shader-like animations with CPPN using microphone prompts

CPPN, Microphone

Erik Swahn

StyleGAN trained on floor plans and stacked on top of each other

StyleGAN, GAN

Alexander Mordvintsev

DeepDream applied to Klimt's Adele Bloch-Bauer

DeepDream

Parag K. Mital

Corpus-based audio synthesis on Michael Jackson’s Beat It using Nature Recordings

Corpus-based synthesis

Alsino Skowronnek

A Conditional GAN trained on a data set of ~1,000 annotated street tag images from Germany. The model can generate new graffiti tags based on any textual input from the audience

Pix2Pix

Kishi Yuma

GAN interpolation

GAN

Michael Kelly

GAN generated images of Edo woodblock art

GAN

Sterling Crispin

A Facial Recognition model guides a 3D genetic algorithm to create a mask. The masks are 3D-printed with nylon

Facial Recognition, Genetic Algorithm

Parag K. Mital

Extract features from 4.7M audio segments and create a tool to play and visualize the audio files

t-SNE

Es Devlin, Ross Goodwin, Google Arts & Culture Lab

Say a word and an RNN generates a poem which is displayed

Voice detection, RNN, Microphone

Xavier Snelgrove

Create a texture by combining two images with Style Transfer

Style Transfer, Texture synthesis

Maryna Taiberman, Meredith Thomas

Train GAN on maps and project on naked bodies

GAN

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners