MITB Banner

Making A Case For Art With GANs

Share

Does art stop being art once it is deprived of its human connection; its creator? Where can one draw the line?  Should art created by non-human entities like AI be given the same stature as that of Picasso or Van Gogh?

Questions such as these have surfaced ever since the advent of GANs.

Source: MARIO KLINGEMANN, MEMORIES OF PASSERSBY I

Artists like Mario Klingemann have been at the forefront of this new-age GAN-powered art. The works of Klingemann have garnered a lot of attention over the past couple of years and have been honoured with auctions by the likes of Sotheby’s.

Klingemann gave away with the application of traditional methods in creating paintings. Instead, he trained his neural network with thousands of portraits from around the 18th century and tweaked in his own layer of aesthetics by using the same preference model that social media applications like Tinder use for facial recognition.

The results of such an unconventional process were considered by the art lovers as being both attractive and repulsive at the same time. The mystics of this convulsive aesthetics might have almost created a genre of its own. If invoking an emotional journey fueled by imaginations, is what art is for then AI might have just made a case for itself.

Making A Case For AI Art Using GANmade Tulips

Anna Ridler, a researcher and most importantly an artist, has experimented with GANs in her recent artistic endeavours and created surreal imagery of Tulips. The popularity of tulips rose in the mid 17th century when a tulip-specific mosaic virus invaded the Dutch gardens.

This resulted in a peculiar intense dual coloured stripes on the petals which sparked the world’s first speculative bubble. At its peak, a single bulb of Viceroy tulip was worth twelve fat sheep, 1000 pounds of cheese and many other vanities which could satiate the needs of a humble village.

The rising tulip-fever nudged the prices into unreachable heights and with, it the disappearance of buyers. The rise and fall of the popularity of tulips do remind us of many other man-made speculative bubbles incentivised by the fear of missing out. And, one such mania of the modern era is that of the bitcoins. At its peak, Bitcoin witnessed a value of nearly $ 20,000 followed by a slump to $ 3,000.

So, Anna Ridler, who also works as a researcher in tapping the uncovered potential of machine learning, did what a creative genius would naturally of; create a meaningful art out of hazy, mistranslated imaginations of the human mind.

The training set consisted of 10,000 labelled photos of handpicked tulips throughout the Dutch spring. She then arranged the flowers based on their state of decay, colour and other such visible classifications.

And to cater to the unpredictable colour combinations of the Mosaic virus, Ridler, used the fluctuating Bitcoin prices to control the appearance of the flower. The stripes on the flower are in direct relation with the Bitcoin values.

What is even more remarkable about this project is, it doesn’t just stop at a visual depiction of a cryptic analogy but also introduces the botanical impossibilities or all the appearances tulips could have been- an artistic rendition of alternate reality.

Ills Of Condensing Creativity

In the case of Anna Ridler, right from the selection of the flowers from the Dutch floral markets to deploying GANs to draw a parallel between and entwine a visual story out of speculative bubbles, blossoming tulips and bitcoins is indeed as human as it gets.

Such a laborious process for an artistic endeavour surely matches that of any other traditional methods of creative art. In fact, to use traditional and creative in the same sentence is a sin on its own.

One might make an argument for AI by saying that it has only augmented human creativity. But there is something more to that than mere augmentation; the human subjectivity.

The aesthetically pleasing realistic faces were overshadowed by Picasso’s Cubism movement. Not that the people have started evolving into cubes but because of the triumph of imagination. Just like Einstein’s theory of relativity or composition of Vivaldi’s two violins in a minor.

Should we still abstain from considering AI generated art as art?

Check the video here

Share
Picture of Ram Sagar

Ram Sagar

I have a master's degree in Robotics and I write about machine learning advancements.
Related Posts

CORPORATE TRAINING PROGRAMS ON GENERATIVE AI

Generative AI Skilling for Enterprises

Our customized corporate training program on Generative AI provides a unique opportunity to empower, retain, and advance your talent.

Upcoming Large format Conference

May 30 and 31, 2024 | 📍 Bangalore, India

Download the easiest way to
stay informed

Subscribe to The Belamy: Our Weekly Newsletter

Biggest AI stories, delivered to your inbox every week.

AI Courses & Careers

Become a Certified Generative AI Engineer

AI Forum for India

Our Discord Community for AI Ecosystem, In collaboration with NVIDIA. 

Flagship Events

Rising 2024 | DE&I in Tech Summit

April 4 and 5, 2024 | 📍 Hilton Convention Center, Manyata Tech Park, Bangalore

MachineCon GCC Summit 2024

June 28 2024 | 📍Bangalore, India

MachineCon USA 2024

26 July 2024 | 583 Park Avenue, New York

Cypher India 2024

September 25-27, 2024 | 📍Bangalore, India

Cypher USA 2024

Nov 21-22 2024 | 📍Santa Clara Convention Center, California, USA

Data Engineering Summit 2024

May 30 and 31, 2024 | 📍 Bangalore, India

Subscribe to Our Newsletter

The Belamy, our weekly Newsletter is a rage. Just enter your email below.