“Art needs an audience, and their tastes vary. Computer programmers have not made art. They have made objects, media, performance, software work. What makes art is an audience as it is an artist who does work, and it is the audiences who turn that work into art through appreciation”, says Mike Rugnetta of PBS Idea Channel.
AI art can be made using Generative Adversarial Networks (GAN), where two Artificial Neural Networks (ANN) are trained at the time in different ways to generate AI art. Now, developers have built various tools that help you create AI art easily. Most of these tools comply with the basic grounds of GAN with a few variations of their own.
So, what is AI Art?
Sign up for your weekly dose of what's up in emerging technology.
Artificial intelligence art, or AI art, is any artwork created with the assistance of AI. It can be created autonomously by AI systems or created in collaboration with humans and an AI system.
In 2018, British auction house Christie’s sold its first piece of computer-generated art, titled “Portrait of Edmond Belamy”, made by a French art collective named Obvious, sold for a whopping $ 432,500, about 45 times more than its estimated worth.
Download our Mobile App
Portrait of Edmond Belamy
AI art has been creating a lot of buzz among the artists’ community, and whether art enthusiasts fancy it or not, it is here to stay and will evolve continuously. Here is a look at some of the online tools available to create mind-blowing AI artwork:
Magenta is an open-source research project tool that trains ML models to generate AI art and music. It does so by manipulating source data like music and images. Magenta was started by the Google Brain team, which developed new deep learning and reinforcement learning algorithms for generating songs, images, drawings, and other materials. It is also exploring building smart tools and interfaces that allow artists and musicians to extend their processes using these models. Magenta uses TensorFlow and releases the models and tools in open-source on GitHub.
Google Deep Dream
Google engineer Alexander Mordvintsev created the AI art generator Deep Dream. This AI generator creates dream-like hallucinogenic pictures and uses a convolutional neural network to find and enhance patterns in images. Check out the experimental video of Deep Dream below.
Runway ML is an easy, code-free tool that makes it simple to experiment with ML models creatively. Primarily a video-photo editing and ML software for creatives, it can also create AI art and morph photos and videos.
Runway ML tool
This AI art generator can create AI pictures by mixing two images. Formerly known as Ganbreeder, it is a collaborative, machine learning-based art website. Using the models StyleGAN and BigGAN, the app allows users to generate and modify images of faces, landscapes, and paintings, among other categories. Check out the video about “Introduction to Artbreeder” below:
Chimera painter is an AI art tool that changes a simple drawing and creates an impressive picture. The tool works by adding features and textures to a drawing by giving it a realistic look. Though aimed at game developers, this GoogleAI powered tool can be used by anyone who wants to create a realistic-looking AI picture.
Fotor GoArt is an AI art generator that can change any picture into stunning pieces of art in seconds without manual photo editing. Just upload your picture and choose a painting filter you like, and GoArt will automatically analyse and convert your original picture into a spectacular painting within seconds. GoArt gives an experience of a new innovative way of creating art.
Image: GoArt (Pinterest)
NVIDIA AI Playground
This AI playground is named after the post-Impressionist painter Paul Gauguin. It can create realistic landscapes and bring life to rivers, rocks and clouds using basic tools rendering high-quality AI art. The tools are easy to use and don’t require expertise or background. Check out their “GauGAN: Changing Sketches into Photorealistic Masterpieces” video below:
AI Art Machine by Google Colab
This is an art machine where you can text and get AI art. This notebook is by Hillel Wayne based on the notebook by Katherine Crowson. The platform is simplified to make it more accessible for nonprogrammers.
There are learning videos about “How to generate Mind-Blowing AI Art in 5 minutes for free” on YouTube uploaded by Anant Vijay Soni from AVSTech and the A.I. Whisperer. Check out the video links below: