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

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

Pix2pix

Ross Goodwin, Oscar Sharp

An LSTM generated screenplay trained on screenplays from several films and television series, and produced according to the screenplay

RNN, LSTM

David Ha

Use a CPPN to create shader-like images including a tutorial

CPPN, ANN

Mario Klingemann

Deleting weights in GANs to create glitches

GAN, Weights

Jessica In, George Profenza, Sam Price

A live, interactive drawing installation that facilitates collaboration between a human and a robot, the model is trained on the QuickDraw dataset and uses the QuickDraw Classifier, and a custom SketchRNN

Hardware, SketchRNN, QuickDraw, Classifier

Tal Shiri, Joel Simon

Train a DCGAN on Perlin Noise to generate shapes, cut the generated shapes from an Artbreeder image, the cutouts and placement are optimized with feature inversion over a face classifier

DLIB, CNN, Perlin Noise, DCGAN, Artbreeder, StyleGAN, BigGAN, GAN

Anna Ridler

A GAN trained on Maltese photography and as well as the GAN-generated images themselves

GAN

Alec Wright, Eero-Pekka Damskägg, Lauri Juvela, Vesa Välimäki, Keith Bloemer, Zak Jost

Real-time guitar amplifier emulation with deep learning

WaveNet

Javier Ideami

Visualizing the loss landscapes with real data using ResNet 20 architectures with batch sizes of 16 and 128 and the Adam optimizer

Loss, ResNet, Adam

Will Stedden

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

Story2Hallucination, CLIP, BigGAN

Ryan Putnam

A GAN interpolation of detailed oil painting strokes

GAN, StyleGAN

Refik Anadol

A StyleGAN generated image and painted on a canvas

GAN, ESR-GAN, StyleGAN

NaN, Production Type

A GPT model trained on ~30k font bios to generate descriptions of speculative fonts

GPT-2

Simon Doury, Google Arts & Culture Lab

Insert a few notes and the model improvises in the style of Bach

Magenta

Cyril Diagne

Use BASNet to extract an object from the environment and OpenCV SIFT to add it into photoshop

BASNet, OpenCV, SIFT, Camera

Naofumi Akimoto

Create a video with a conditional GAN using next frame predictions

GAN, pix2pix

Kishi Yuma

GAN inpainting of Guido Reni's Mary Magdalene

GAN, Inpainting

Tero Parviainen

Mix latent space of sounds using wheels

VAE, Magenta

Olga Vechtomova

Generate lyrics with an VAE trained with seven different styles

VAE

Lulu xXX

Optical Flow based Style Transfer of woman singing

StyleTransfer, Optical Flow, deepflow

Sey Min

Take a selfie and use a CNN to determine how likely you are to be a k-pop star

CNN, Classification

Google AI

Turn book paragraphs into an RNN features and match them with similar paragraphs

RNN, NNS

Xavier Snelgrove

Create a texture by combining two images with Style Transfer

Style Transfer, Texture synthesis

Albert Barqué-Duran

Use a 3D GAN to generate an Emoji, 3D print the generated Emoji, and paint it during a live performance

GAN, Height map

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners