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

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

Item 1 of 2

Nuntinee Tansrisakul, Yuguang Zhang

A GAN-generated video is rendered with a digital pinhole camera process, the negatives are printed, and then processed in a darkroom to restore the aesthetic of analog photos in a digital-first world

GAN

Vadim Epstein

CLIP with a custom FFT-based generator turning phrases into paintings in the format of a meditative story from famous art titles

CLIP, FFT

Synflux, Hatara

A GAN trained on 2 million birds and converted to double Jacquard knit format

GAN

Cunicode

A StyleGAN trained on thousands of public domain beetle illustrations

StyleGAN, GAN

Tatiana Zobnina, Alonso Vázquez

Using DDSP to translate a Beluga whale voice into a violin

Spleeter, DDSP, BigGAN

Stefan Sietzen

Realtime Interactive Visualization of Convolutional Neural Networks in Unity

CNN, Unity

Ryan Putnam

A GAN interpolation of detailed oil painting strokes

GAN, StyleGAN

Julia Vergazova, Nikolya Ulyanov

Feeding surveillance camera images into a 3d-photo-inpainting network

3d photo inpainting

Lin Fei Fei, Vadim Epstein

Several CV processing techniques have been applied to the paintings of Lin Fei Fei to turn them into an animated story

3D photo inpaint, First Order Motion, StyleGAN2, ConSinGAN, Video interpolation

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

Real-time guitar amplifier emulation with deep learning

WaveNet

Michael Friesen

Create images in the style of Beksinski with CLIP and BigGAN

Big Sleep, CLIP, BigGAN

Elijah M

Using Portraitai and Deepart.io to create a style and then use EbSynth to apply it to a video

Portraitai, deepart.io, EbSynth, Style Transfer

Sam Lavigne

Using semantic segmentation trained on Figaro-1k to extract all the haircuts of Mark Zuckerberg

Semantic segmentation, Figaro-1k

Vadim Epstein

Music video, created with Feature Inversion (successor of DeepDream) and enhanced with Neural Video Interpolation (slow motion).

DeepDream inversion, Video interpolation

Steve Savage

Self-organising textures of fruits using Neural Cellular Automata

Self-organising textures, Neural Cellular Automata

Minne Atairu

A StyleGAN model trained on portraits

StyleGAN, GAN

Yotam Mann

Resynthesized audio from YouTube with neural nets trained on vocal and instrumental recordings

WaveGAN, GAN

Zihou Ng

A browser-based exploration of real-time latent space navigation of GAN at higher resolutions with WebGL

GAN

Hans Brouwer

Audio-reactive latent interpolation with StyleGAN2 created by modulating latent and noise inputs with musical features

StyleGAN2

Will Stedden

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

Story2Hallucination, CLIP, BigGAN

Yuguang Zhang

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

GAN, Hardware

Yotam Mann

A WaveGAN-inspired model trained on the acapella vocal ensemble in Košice, Slovakia, translating Glenn Gould's piano into a Gregorian Choir

WaveGAN, GAN

Ryan Murdock

Maximize the perceptual difference between each image and minimize the difference between the outputs and images from a dataset

Min-Max

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners