Generative software art

Activation Atlases — create an explorable atlas of features a network has learned. What neural networks see — visualization of layers in a neural network by Gene Kogan. Also see Feature Visualization by Distill. Visualizing high dimensional space — visualize how machine learning works. Teachable machine - Teach a machine using your camera, live in the browser without code. FontJoy — Generate font combinations with deep learning. Font Map — Surface new relationships between fonts with machine learning.

Our friend Arthur Miller is considered the authority on the intersection of technology and art. He recently published a fantastic book highlighting how artists are using AI:.

If you're interested in using AI in your creative practice, the apps, software and tools above are a great place to start. Even if you have no machine learning experience, you can start with some of the simpler tools and expand from there. As tools to make AI art become more mainstream, AI artworks will increasingly embed themselves in our culture.

By mastering the tools to create AI generated art, and creating works while this field is in its infancy, you can help push the boundaries of human creativity forward. How will your neural network and AI experiments transform our creative potential? Now let's start to dig into the nitty gritty details about how to create generative art yourself.

Generative art can be made with the vast majority of programming languages. In other words, if you already know how to program, you should already have the ability to create generative art. The most popular tool used to create generative art is Processing.

If generative art is your first introduction to programming, I really recommend starting with Processing due to the plethora of documentation surrounding its usage. Furthermore, I'd recommend using the Python version of Processing since the popularity of the Python programming language is growing so fast. I've only barely dipped my toes in those waters, and I already can tell it is a powerful tool to create stunning visuals. This tool certainly has a steep learning curve!

A program that has some scripting functionality with a fantastic array of tools is Adobe Illustrator. Many artists use Illustrator to create professional graphics, but it isn't as great as making generative art explicitly. The last method I'll discuss is the method that I personally use. If you haven't already guessed it, I'm a big supporter of Python. When I started learning generative art, I didn't know about the existence of Processing. PyQt is included in most standard Python distributions, such as Anaconda, which I linked in the supplies section of this Instructable.

As you may have learned by now, generative art relies on some sort of pattern to create beauty. One way to create patterns is via mathematical formulas. However, sometimes we want to introduce randomness across our canvas instead of using formulas, which may have more predictable results.

If we consider pure randomness, you get an image such as the one below, where every pixel's red, green, and blue components are the same choice of a random number between zero and Unfortunately, this level of randomness isn't overly useful, as the pixel-to-pixel transitions are often abrupt.

This abruptness doesn't generally lead to beautiful artwork. But generative artists are not the first people to encounter this issue. In fact, Ken Perlin, frustrated by the unnatural look of pure randomness created Perlin Noise.

At its core, Perlin Noise still uses randomness, but zoomed in and smoothed. To create Perlin Noise, begin by constructing a grid over your image canvas with nx number of columns and ny number of rows. From each corner of each grid square, add unit vectors at random angles unit vectors have a magnitude of 1.

These vectors are called gradient vectors. For each pixel in the canvas determine which grid square that pixel falls into and construct "offset vectors" from each corner of the grid square, pointing at the pixel. Next, compute the dot product for each pair the grid square's vectors. The result is four values, one for each corner D1, D2, D3, D4. With each of the four values in hand, compute the two dimensional linear interpolation based on the pixel position relative to each corner, and voila, Perlin Noise!

Ken Perlin later enhanced his creation and coined it Improved Perlin Noise. Improved Perlin Noise doesn't perform pure two-dimensional linear interpolation, but instead computes the interpolation factor via a fade function.

The below graphic shows the fade function and a graph of the fade function. The graph shows how an interpolation factor term maps to the fade function factor. Note that the difference the fade function introduces is a smooth transition between your endpoints, which can yield more natural results.

Perlin noise is the foundation of many generative art pieces, and there are ways you can further manipulate it yet! Now that you have all of the foundations, you can generate Perlin Noise! If you use Processing, Perlin Noise is already implemented via the noise function, but if you choose to program in other languages, you may need to write your own Perlin Noise implementation. I have included a Python implementation of Perlin Noise below the graphic to help!

This code is also found on my Github. In my first example, I will demonstrate how to use Perlin Noise to create what's called a flow field. The simplest way I can explain the concept is as follows. Imagine the Perlin Noise image above as a terrain map, where lighter colors represent peaks and darker colors represent valleys. Now imagine placing a marble anywhere on the image and watching it travel across the terrain, eventually setting in a valley. A flow field is basically a way to represent how the marble will travel, only with flow fields, the marble's momentum is not taken into account.

As such, the underlying mechanism of a flow field is a vector field, and the flow field is basically playing connect-the-dot. Let's decompose this visually:. That's how to make a basic flow field! The code to create these three images is found on my GitHub here.

From here, the possibilities are really endless, you can add color based on certain conditions, adjust the line lengths, make curves thicker or thinner, modify where the curves begin, customize the image dimensions, etc.

Below are a few examples of some outputs from this flow field function I wrote. I encourage you to copy this code and make it your own! Learning from examples is a great way to start creating art from code. This second example is another flow field example, except for one glaring change.

The complete sample code for this section can be found here. When using just a black and white color palette, the results from this one change are fantastic! In this third and final example, we will take a little different approach.

Consider a system of points arranged in a circle. Each point connects to the adjacent point, thereby tracing out a circle. Consider now that each of these points, already having a defined position, is now assigned a unique velocity. Now, step through time, adjusting the position and possibly velocity of each point until a certain amount of time has passed. For each time step, draw the "circle" body's shape on the same canvas such that you can see how the shape transforms with time.

What would be the result? Well, that would depend on how we assign the velocity to each point. Note that these patterns are Probably not what most people would call appealing. Clearly the sharp transitions between velocity values is an issue. The good news is we've solved this problem before with Perlin Noise.

Instead of pure randomness, if we multiply a maximum velocity by the value of an underlying Perlin Noise field, we can add order to the disorder! Jon McCormack is an artist and professor who uses algorithms in his work to tap into the inherent wisdom of nature. Each plant-like form was derived from the starting graphic elements of oil company logos. Jon McCormack, Fifty Sisters, Series of fifty evolved digital plant images using oil company logos as building blocks. McCormack employs a process similar to selective breeding that evolves aesthetic and behavioral traits.

The computer is able to find nuances and complexity that he could never imagine. It acts as a creative partner, a way to make the unimaginable tangible. His work is a prime example of code art. This environment is affected by the other agents and the colors they produce. An evolutionary software ecosystem. Colors enter into complex feedback cycles, presenting an evolving palette of shifting hues.

Different configurations emerge based on the strategies the ecosystem discovers for co-existence and co-dependency. At Monash University in Melbourne, Australia, McCormack directs SensiLab , a multidisciplinary research group studying topics such as programmable matter, interactive space, and creative AI.

McCormack also wrote the book Computers and Creativity. NASA used evolutionary algorithms to design this antennae. The software did this much faster than any human being could… through a process patterned after Darwin's 'survival of the fittest,' the strongest designs survive and the less capable do not.

Scientists are starting to use these Darwinian techniques to enhance their own creativity. For example, biochemical labs in universities and pharmaceutical companies are using evolutionary programs to design new molecules for use in basic research and medicine. Even the brains and bodies of robots can now be evolved instead of being designed. Michael Noll at Bell Labs An algorithm is like a recipe.

This is also sometimes called code art or procedural art, because it is created by computer following a set of procedures laid out in code. For example, there are dozens of fractal art generators that make it easy to produce your own fractal images, without a background in math. In the early s, researchers at Bell Labs were pioneering the use of computers for creativity.

One of the most active researchers was Michael Noll. In the late nineties, Eno was already using algorithmic principles to create compositions. Generative music apps by composer Brian Eno and Peter Chilvers.

Courtesy of GenerativeMusic. Roelof Pieters and Samim Winiger, co-founders of Creative. The Mandelbrot Set is a mathematical formula that has stunning aesthetic properties when visualized.

It expresses repeating patterns at all levels of scale — no matter how much you zoom in or out, you can find the same exact geometric patterns repeating over and over — so it is considered a fractal.

The pair explain how a milestone was set in by Benoit Mandelbrot, with the discovery of the Mandelbrot set. By doing so, he was able to show how visual complexity can be created from simple rules. Fractals had a profound effect on our perception of creativity and machines. This event helped begin what Pieters and Winiger call the code art revolution, which continues today.

Scott Draves is a pioneering software artist best known for creating Electric Sheep , a collective intelligence consisting of , computers and people that uses mathematics and genetic algorithms to create an infinite abstract animation. We consider the animated output of Electric Sheep some of the best fractal and algorithmic art out there. Draves earlier work called Bomb was one of the first interactive software artworks and also the first Open Source code artwork.

The game lets you explore interactive, generative digital landscapes that change based on your input, and embarking on a visual and musical adventure. Instead of controlling an avatar, you use a game controller, MIDI controller, or mouse-and-keyboard combo to shape both the world and the music together.

Worlds are algorithmically combined; the audio and visual fabric are sewn together with code. The game is a breathtaking creative experience spanning 18 audiovisual dimensions. Two days after launching, someone even made their own touch interface and projected it on a foot shipping container.

Silk is a generative art app that makes it easy to create stunning designs with a few swipes of your finger. Generative tools are not just being used to create art, architecture and music. Some organizations that require a lot of creative assets like video game graphics are using a method called Procedural Modeling to rapidly generate ideas, saving time and money.

Major video game studios spend hundreds of millions of dollars to develop a single game. You can configure a layer rarity so it is applied only a certain percent of times. Similarly to layer rarity, you can configure certain attributes to be more rare than others. You will be able to easily tell what are the change for an attribute to be applied.

The metadata Viewer page also allows you to update your metadata after you generated your collection. We automatically save your project in the browser, so when your come back, your layers, configuration and files are still present. NFT Art Generator.