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

Fadi Al-Ghawanmeh and Kamel Smaïli

Translating voice to RNN generated MIDI files to improvise Arab maqamic music in real-time

CNN, RNN

Erik Swahn

GAN trained on Defra's Lidar data of London, then visualize the height maps in Aeriolod

StyleGAN, GAN, Aeriolod

Mario Klingemann

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

Camera, Face Alignment, pix2pix

Alexander Mordvintsev

DeepDream applied to Klimt's Adele Bloch-Bauer

DeepDream

Billie Eilish, Google Creative Lab, YouTube Music, IYOIYO, Plan8

An interactive, gradient-based audio and video alignment of thousands of covers of Billie Eilish’s “Bad Guy”

Google Arts & Culture Lab, Cyril Diagne

Take a selfie, extract the CNN features, and match them with features from portraits

CNN, NNS, Camera

Refik Anadol

Extract CNN features from images and organize images with cuml-UMAP, create a device to explore the space with hand motions

cuml-UMAP

Baum & Leahy

Blend sounds from Wavenet trained on field recordings, and NSynth tuned on nature sounds from British Library Wildlife and Environmental Sounds archive

Magenta, VAE, NSynth, Wavenet

Vadim Epstein

Painting by Viktor Vasnetsov, animated with 'Animating Landscape' and Multi-Domain Multi-Modality I2I translation

Multi-Domain Multi-Modality I2I translation, Animating Landscape

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

Will Stedden

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

Story2Hallucination, CLIP, BigGAN

Helena Sarin

Apply CycleGAN to a Sketch of the Fonthill Castle

CycleGAN, GAN

Matt Groh, Ziv Epstein, Manuel Cebrian, Iyad Rahwan

Use GAN paintings and Object Detection to remove objects from a video

Object Detection, GAN, Inpainting

Kishi Yuma

GAN interpolation

GAN

Shan Carter, David Ha, Ian Johnson, Chris Olah, Google Creative Lab

An RNN model generates handwriting based on your style

RNN

Gael Hugo, Google Arts & Culture Lab

Cluster books with UMAP and create imaginary islands to visualize them

UMAP

Alexander Mordvintsev

Visualize features in a neural network using Gradient Ascent

CNN, Activations

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 inpainting of Guido Reni's Mary Magdalene

GAN, Inpainting

Google Creative Lab

Device to collect a few categories of data at home and automatically train a model to classify them

AutoML, CNN, Hardware

Alexander Reben

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

DeepDream, Wavenet

Alexandre Devaux

Using BodyPix to segment people and WebXR to create holograms on-the-fly

BodyPix, Tensorflow.js

Helena Sarin

GAN trained on personal pictures of leafs

GAN

Shortcut

A portrait created in ArtBreeder and augmented with a AICAN popart model

Artbreeder, AICAN

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners