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

Alsino Skowronnek

A StyleGAN trained on thousands of frames of a filmed sequence of images of graffiti from NYC in the late 70s/early 80s. The output is interpreted into a painting and an AR filter

StyleGAN

Memo Akten

A GAN collage of nature images starting with Bigbang to today

GAN

Gavin Shapiro, Jeremy Torman, cYsmix

Artistic Style Transfer for video applied to dancing flamingos in a recursive loop

Video StyleTransfer

Lulu xXX, Noj Barke

Use photogrammetry to extract vector points from images, and apply a Optical Flow based StyleTransfer with Noj Barke's dot paintings

Photogrammetry, Optical Flow, StyleTransfer, deepflow

Robbie Barrat, Acne

Train a GAN on Acne clothing, generate images with the GAN, and create physical products according to the GAN images

GAN

Memo Akten

Translate objects and hand movements to nature scenes with a Conditional GAN

pix2pix, GAN

Jonathan Fly

Apply GauGAN on Charlie Chaplin dressed as a tree

GauGAN, GAN

Lia Coleman

StyleGAN trained on blooming flowers with background removal using DaVinci Resolve, then interpolated with fleshdigressions and TouchDesigner's CHOP function according to cello music

StyleGAN, fleshdigressions, DaVinci Resolve, TouchDesigner, CHOP

Sofia Crespo

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

Style Transfer, Texture synthesis

Lulu xXX, Paradis

Apply Slow motion and fluid footage and Optical Flow based Style Transfer on Paradis's Recto Verso

StyleTransfer, Optical Flow, deepflow

Vibert Thio, Douglas Eck

An interactive room where you can create music with Magenta's javascript version of MusicVAE and MelodyRNN

Magenta, VAE, RNN

Shardcore

Apply First Order Motion to objects with faces

First Order Motion

Doron Adler

Overfit StyleGAN on 250 nonsensical images and then apply StyleTransfer

StyleGAN, GAN, StyleTransfer

Terence Broad

Generate GAN images without a training dataset

GAN

Jonathan Fly

Start with a video clip of a rollercoaster and then predict the next frame with a pix2pix model, feeding the previous frame

Pix2pix

Mario Klingemann

Extract face markers and use a pix2pix model to translate the face markers into paintings

GAN, pix2pix, Expression Detection

Sofia Crespo

Add DeepDream like patterns on 3D beatles and print the new specimens

DeepDream, 3D

Memo Akten

Pick random words from Word2Vec and look at their relationships to the words ‘man’ and ‘woman’

Word2Vec

Libby Heaney

Use voice and text features to match it with Britain's citizen test

Microphone, RNN, Classification

Simon Doury, Etienne Ferrier, Google Arts & Culture Lab

Cluster artworks based on color

UMAP

Christine Payne

A music generator trained on hundreds of thousands of MIDI files and trained with GPT-2

GPT

Kishi Yuma

GAN trained on pictures of hands

GAN

Google Creative Lab

Conduct your own orchestra by extracting your pose

PoseNet, Camera

Joanne Hastie

Paint 12 shapes, algorithmically combine the forms, use the Inception Classifier to select artworks, and then paint the final selection

CNN, Inception, Classification

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners