We used Generative Adversarial Networks to enable a machine to create portraits of the 18th century. Also, we believe AI is a great tool for Art. We want you to hear our story, put in the right context.
Art created by Algorithms
A word about Generative Adversarial Networks (GANs). Generative Adversarial Networks (GANs) are generative models created in 2014 by Ian Goodfellow, a researcher in Machine Learning. They put two algorithms in competition one with another to perform training.
A generator will create new images by mimicking characteristics of images from the training dataset, and try to fool a discriminator into thinking those images are “real”. The generator trains until no difference can be made by the discriminator.
Previous work on using GANs for Art
GANs started to receive attention from the art community, due to their potential to generate novel artworks. Until now, several projects produced inspiring images using GANs. Notably, we have the Quasimondo project by Mario Klingemann, an artist working with code, AI and data. He has worked with GANs numerous times, for instance you can see one of his artworks, that he created using a pix2pix model:
There are also research papers on using GANs for Art, and studying the creative potentiel of this algorithm. CAN (Creative Adversarial Networks) is a variant of GANs that are designed to produce “creative” artworks. In this study, being creative is defined by being able to produce an artwork that does not fit a classical art movement (at least, according to the discriminator).
In late 2017, a “Machine Learning for Creativity and Design” Workshop was organized at the most prestigious Machine Learning conference in the world: NIPS. Lots of submissions included work with GANs.
Notably, we also have the work of Robbie Barrat on nudes, landscapes and portraits generation with GANs, from which we were inspired. Check out his work : https://github.com/robbiebarrat/art-DCGAN.
There are a lot more examples of Art with GANs, such as the work of Michael Tyka, Samim, Alex Champanard, and several research papers on the topic…
What we do and why it is unique
We wanted to create a realistic portrait of the 18th century. We created a unique piece of art: “Le comte de Belamy”.
It is a 70x70 cm artwork, with a golden wooden frame. It is almost similar to a 18th century portrait that you would see in a classical museum. However, it is made by a machine.
We trained GANs on classical portraits and used super-resolution algorithms to produce this high-resolution painting. They say art is a way to send a message, and we wanted the world to hear ours.
We chose the name “Belamy” to make a reference to the creator name of GANs, I. Goodfellow, that roughly translate to “Bel ami” in French. Also, as the signature of the artist, we wrote the formula of the loss function of the original GAN model:
By doing this, we do not consider ourselves as the creator of this artwork. We’d rather give credit to the algorithm than created this painting.
Taking a step back: our perspective
We want to share our perspective on AI for Art.
A new movement is forming: GANism
GANism (the specific look and feel of seemingly GAN-generated images) may yet become a significant modern art trend.by François Chollet
This new creation process opens up new doors to current world of art, with a new movement François Chollet calls GANism. It offers new possibilities, such as the ability to place an artwork in a given space according to its visual characteristics, and the ability to travel in this space, through an infinite number of altered versions of an artwork. GANism brings, through the generation of art with machines, a new complexity, an increased attention for detail, and the multiplication of possibilities of interpretation to the very notion of art.
We want to send out an update of the state of the research in AI. We believe it raises philosophical as well as societal questions. Is an algorithm capable of creativity ? If so, how far could it be from self consciousness ?
Science is converging towards the hypothesis that human minds can be seen as a set of algorithms, trained over the evolution and during life, to best adapt and react to outside factors. We believe we possess something greater, a soul, that makes each of us special. Nevertheless, so far, no physical proof of such an attribute has been discovered.
So, is it reductive to say that mathematical formulas serve as a basis that guide our biological algorithms to learn how to create something entirely new ? If so, how is a computer algorithm any different, and how couldn’t it be able to create as well ?
Many questions are also raised in the field of Art. In contemporary art, the artist has always been at the center of the work, and the tool as a way for him to express, and pass on emotions. For the first time, the tool is at the center of the work, and the artist takes a step back. It disrupts the relationship of collaboration between human and machines, leading to a new way to create.
This new approach is likely to result in the appearance of a new type of art. Although it will not replace artists, it brings up a new perspective, in which the tool is the actor, and the artist is a facilitator.
Rather than the artwork itself, we believe that the value of this project lays in the debate it can create.
We also chose to put the artwork to auction, to finance further research. The money will be used to finance the computation power needed to produce this type of artwork, and maybe attend next NIPS conference.
New art, new rules, the full rights to the image will also be part of the package.
Conclusion: we want to hear about your perspective.
There is a lot to discuss about. We want to hear your take on the subject, it is a part of our common journey, as artists.