It's all a game of construction — some with a brush, some with a shovel, some choose a pen.
Jackson Pollock
…and some, including myself, choose neural networks. I’m an artist, and I've also been building commercial software for a long while. But art and software used to be two parallel tracks in my life; save for the occasional foray into generative art with Processing and computational photography, all my art was analog… until I discovered GANs (Generative Adversarial Networks).
Since the invention of GANs in 2014, the machine learning community has produced a number of deep, technical pieces about the technique (such as this one). This is not one of those pieces. Instead, I want to share in broad strokes some reasons why GANs are excellent artistic tools and the methods I have developed for creating my GAN-augmented art.
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/
Repaint your picture in the style of your favorite artist.
About
Our mission is to provide a novel artistic painting tool that allows everyone to create and share artistic pictures with just a few clicks. All you need to do is upload a photo and choose your favorite style. Our servers will then render your artwork for you. We apply an algorithm developed by Leon Gatys, Alexander Ecker and Matthias Bethge. The website was originally created by Łukasz Kidziński and Michał Warchoł. We have now joined forces to provide you with the latest technology in even more accessible way.
Our Team
Five researchers from the Bethge lab at University of Tübingen (Germany), CHILI Lab at École polytechnique fédérale de Lausanne (Switzerland) and Université catholique de Louvain (Belgium).
processing_cheat_sheet_english.pdf
An anatomical case study of the Amazon echo as a artificial intelligence system made of human labor
Thoroughly updated, this fourth edition focuses on modern techniques used to generate synthetic three-dimensional images in a fraction of a second. With the advent of programmable shaders, a wide variety of new algorithms have arisen and evolved over the past few years. This edition discusses current, practical rendering methods used in games and other applications. It also presents a solid theoretical framework and relevant mathematics for the field of interactive computer graphics, all in an approachable style. New to this edition: new chapter on VR and AR as well
An open source machine embroidery design platform based on Inkscape.
Ink/Stitch aims to be a full-fledged embroidery digitizing platform based entirely on free, open source software. Our goal is to be approachable for hobbyists while also providing the power needed by professional digitizers.
RACHEL is a portable plug-and-play server which stores educational websites and makes that content available over any local (offline) wireless connection. RACHEL makes deploying a library of digital content as easy as pushing a button.
Then simply turn it on. While RACHEL is on, take your device and connect to "RACHEL" as you would any wifi network. Then open a web browser and type the web address (a number listed on the front sticker of your RACHEL).
Once you're connected to RACHEL, you can instantly access offline versions of the world's best free educational websites including Wikipedia, Khan Academy, and over 100 more.
Demo :
http://rachelfriends.org/previews/rachelpi_64EN_4.0/
http://rachelfriends.org/previews/rachelpi_64FR_3.0/
http://rachelfriends.org/previews/rachelpi_64ES_3.0/
Build your own here : http://rachelfriends.org/rachel-pi-howto.html
Use the idle time on your computer (Windows, Mac, Linux, or Android) to cure diseases, study global warming, discover pulsars, and do many other types of scientific research.
You can choose to support projects such as Einstein@Home, IBM World Community Grid, and SETI@home, among many others. If you run several projects, try an account manager such as GridRepublic or BAM! .
https://boinc.berkeley.edu/projects.php
Copying an element from a photo and pasting it into a painting is a challenging task. Applying photo compositing techniques in this context yields subpar results that look like a collage --- and existing painterly stylization algorithms, which are global, perform poorly when applied locally. We address these issues with a dedicated algorithm that carefully determines the local statistics to be transferred. We ensure both spatial and inter-scale statistical consistency and demonstrate that both aspects are key to generating quality results. To cope with the diversity of abstraction levels and types of paintings, we introduce a technique to adjust the parameters of the transfer depending on the painting. We show that our algorithm produces significantly better results than photo compositing or global stylization techniques and that it enables creative painterly edits that would be otherwise difficult to achieve.
The Aziz! Light Crew Freeliner is a live geometric animation software built with Processing. The documentation is a little sparse and the ux is rough but powerfull.
Also known as a!LcFreeliner. This software is feature-full geometric animation software built for live projection mapping. Development started in fall 2013.
It is made with Processing. It is licensed as GNU Lesser General Public License. A official release will occur once I have solidified the new architecture developed during this semester.
Using a computer mouse cursor the user can create geometric forms composed of line segments. These can be created in groups, also known as segmentGroup. To facilitate this task the software has features such as centering, snapping, nudging, fixed length segments, fixed angles, grids, and mouse sensitivity adjustment.
Chataigne is made with one goal in mind : create a common tool for artists, technicians and developers who wish to use technology and synchronize softwares for shows, interactive installations or prototyping. It aims to be as simple as possible for basic interactions, but can be easily extended to create complex interactions
Modular Video Plugins for Ableton Live
VIZZable is developed with love and released free to the community in the hopes of advancing the art of live audio-visual performance. If you get something out of VIZZable, please give something back to support its development.
All the bandcamp album made with Pure Data.
MoviePy is a Python module for video editing, which can be used for basic operations (like cuts, concatenations, title insertions), video compositing (a.k.a. non-linear editing), video processing, or to create advanced effects. It can read and write the most common video formats, including GIF.
Wildfire is a free and user-friendly image-processing software, mostly known for its sophisticated flame-fractal-generator. It is Java-based, open-source and runs on any major computer-plattform. There is also a special Android-version for mobile devices.
Spek (IPA: /spɛk/, ‘bacon’ in Dutch) helps to analyse your audio files by showing their spectrogram. Spek is free software available for Unix, Windows and Mac OS X.
Features
Supports all popular lossy and lossless audio file formats thanks to the FFmpeg libraries.
Ultra-fast signal processing, uses multiple threads to further speed up the analysis.
Shows the codec name and the audio signal parameters.
Allows to save the spectrogram as an image file.
Drag-and-drop support; associates with common audio file formats.
Auto-fitting time, frequency and spectral density rulers.
Adjustable spectral density range.An extensive and extendable painting application with an extensive range of features, including: both bitmap and vector graphics; multiple layers; five kinds of color picker; patterns, textures, and gradients; dashed lines and arrowheads; a spirograph generator; and even a cellular automaton tool (pictured below).
Gifski converts video frames to GIF animations using pngquant's fancy features for efficient cross-frame palettes and temporal dithering. It produces animated GIFs that use thousands of colors per frame.
Release : https://github.com/ImageOptim/gifski/releases
Usage
I haven't finished implementing proper video import yet, so for now you need ffmpeg to convert video to PNG frames first:
ffmpeg -i video.mp4 frame%04d.png
and then make the GIF from the frames:
gifski -o file.gif frame*.png
See gifski -h for more options. The conversion might be a bit slow, because it takes a lot of effort to nicely massage these pixels. Also, you should suffer waiting like the poor users who will be downloading these huge files.
Fractorium and its associated command line tools can render fractal flames using the CPU, or OpenCL. In order to use OpenCL, you must have an nVidia card that has the Fermi architecture or later, or a recent AMD card. If you attempt to use an unsupported card, you will receive an error message and the CPU renderer will be used instead.
Chaotica is a next-generation fractal art application, designed for both novices and professional artists.
Novice users can enjoy editing randomised fractals to produce stunning HD wallpapers and animations.
Professional users will particularly value the fast, modern rendering engine. High quality animations and huge images for print are easily produced, with real-time imaging controls that will dramatically accelerate your workflow.
What is fractal art?
Fractal art is a digital art medium with a very rich creative space, based on geometry and recursion.
Chaotica's user interface abstracts much of the maths away to provide a fluid artistic process.
Since its invention in 1981, IFS fractals have been popularised by Flam3 and Apophysis. Chaotica extends the creative possibilities of these programs in a powerful, production-oriented environment.
Some example here : https://www.tfmstyle.com/fractality-project
SpaceEngine is a realistic virtual Universe you can explore on your computer. You can travel from star to star, from galaxy to galaxy, landing on any planet, moon, or asteroid with the ability to explore its alien landscape. You can alter the speed of time and observe any celestial phenomena you please. All transitions are completely seamless, and this virtual universe has a size of billions of light-years across and contains trillions upon trillions of planetary systems. The procedural generation is based on real scientific knowledge, so SpaceEngine depicts the universe the way it is thought to be by modern science. Real celestial objects are also present if you want to visit them, including the planets and moons of our Solar system, thousands of nearby stars with newly discovered exoplanets, and thousands of galaxies that are currently known.
This is the official on-line repository for the code from the Graphics Gems series of books (from Academic Press). This series focusses on short to medium length pieces of code which perform a wide variety of computer graphics related tasks. All code here can be used without restrictions. The code distributions here contain all known bug fixes and enhancements.
Embroidermodder is a free machine embroidery software program which allows editing, scaling, and translating sewing machine embroidery files to a variety of formats. It allows the user to add custom modifications to their embroidery designs.
The user interface has been written from scratch using C++. It harnesses the powerful Qt framework to achieve platform independence. The 3 major desktop operating systems (Windows, Mac and Linux) will be targeted.
In addition to the desktop, it already works with the Raspberry Pi and we have a working demo of our code running on an Arduino. This will pave the way for low cost open source embroidery machines. We would also like to collaborate with the creators of the Smoothieboard so anyone who has one of those boards could also benefit from our work.
Very few other embroidery applications are cross-platform, with most only able to natively run on Windows. Our interface is very consistent across all platforms we support so there is no need to re-learn the interface when using it on a different operating system.
The interface itself is a CAD/CAM software but tailored for embroidery. This is intentional since both CAD and embroidery use vector formats and the embroidery machines are really just specialized CNC equipment (I.E. 3D Printers, CNC Laser Cutters, CNC Routers, CNC Lathes). So if you are interested in or familiar with CAD/CAM, then it will be possible to use it in that fashion also.
The interface is very similar to existing CAD applications so existing CAD users should be able to start using it immediately with little or no learning curve. It also incorporates additional features which are typically present in less precise graphics applications, such as the auto-adjusting ruler and an easily accessible undo history.
The first commercially available brainwave to synthesizer (both CV and MIDI) interface on the worldwide market.
By using the Neurosky Mindwave headset you can coax your brain activity to change every parameter of sound, light and video devices in your performance or studio.
PatterNodes is a procedural design to for creating graphical patterns, animations or illustrations based on repetitions. This is done by defining a sequence of steps that describes the design, using nodes and connections between them. PatterNodes is designed from the start to make it easy to tweak things to see how they turn out. Therefore the resulting design output is always shown in the bottom preview view, repeated for patterns and updating in real time with any changes, giving you instant feedback of what the end result will be.
While the software can be used to create many types of illustrations and animations it's primarily aimed at pattern creation. To make pattern creation easier PatterNodes also includes a lot of nodes that automatically perform common tedious tasks like repeating elements at the tile edges to make the pattern seamless, or randomizing different aspects (like color, position, rotation..) of the elements in a pattern to give it a little more life.
https://creativepro.com/review-patternodes/
https://www.behance.net/lostminds
Lumen is a Mac App that makes it easy for you to create engaging visuals in real time. Use the same process with Lumen as you would with a hardware video synth, but with modern features only software can provide. With a semi-modular design that is both playable and deep, Lumen is the perfect way to get into video synthesis.
A free and open-source intermedia sequencer
Enables precise and flexible scripting of interactive scenarios. Control and score any OSC-compliant software or hardware : Max/MSP, PureData, OpenFrameworks, Processing...
An open source collection of 20+ computational design tools for Clojure & Clojurescript by Karsten Schmidt.
In active development since 2012, and totalling almost 39,000 lines of code, the libraries address concepts related to many displines, from animation, generative design, data analysis / validation / visualization with SVG and WebGL, interactive installations, 2d / 3d geometry, digital fabrication, voxel modeling, rendering, linked data graphs & querying, encryption, OpenCL computing etc.
Many of the thi.ng projects (especially the larger ones) are written in a literate programming style and include extensive documentation, diagrams and tests, directly in the source code on GitHub. Each library can be used individually. All projects are licensed under the Apache Software License 2.0.
Open Stage Control is a libre desktop OSC bi-directionnal control surface application. It's built with HTML, JavaScript & CSS on top of Electron framework
Download here : https://github.com/jean-emmanuel/open-stage-control/releases
PabloDraw is an Ansi/Ascii text and RIPscrip vector graphic art editor/viewer with multi-user capabilities.
Artificial Neural Networks have spurred remarkable recent progress in image classification and speech recognition. But even though these are very useful tools based on well-known mathematical methods, we actually understand surprisingly little of why certain models work and others don’t. So let’s take a look at some simple techniques for peeking inside these networks.
We train an artificial neural network by showing it millions of training examples and gradually adjusting the network parameters until it gives the classifications we want. The network typically consists of 10-30 stacked layers of artificial neurons. Each image is fed into the input layer, which then talks to the next layer, until eventually the “output” layer is reached. The network’s “answer” comes from this final output layer.
One of the challenges of neural networks is understanding what exactly goes on at each layer. We know that after training, each layer progressively extracts higher and higher-level features of the image, until the final layer essentially makes a decision on what the image shows. For example, the first layer maybe looks for edges or corners. Intermediate layers interpret the basic features to look for overall shapes or components, like a door or a leaf. The final few layers assemble those into complete interpretations—these neurons activate in response to very complex things such as entire buildings or trees.
One way to visualize what goes on is to turn the network upside down and ask it to enhance an input image in such a way as to elicit a particular interpretation. Say you want to know what sort of image would result in “Banana.” Start with an image full of random noise, then gradually tweak the image towards what the neural net considers a banana (see related work in [1], [2], [3], [4]). By itself, that doesn’t work very well, but it does if we impose a prior constraint that the image should have similar statistics to natural images, such as neighboring pixels needing to be correlated. 
Automatic Cinema aims at an artistic audience. The software can be used for exhibitions or installations, where a variety of media are served on various screens and channels – syncronized or not. Since all media assets are stored in a database, Automatic Cinema is also useful for documentarists and researchers with a structural approach to their material. And last but not least, Automatic Cinema is open source and can be developed by anybody. Instead of cutting a bunch of videoclips the hard way, Automatic Cinema generates countless versions based upon predefined styles. Probably, you'll end up seeing a movie you've never been thinking of — serendipity in it's best way.
Playscii is an open source ASCII art program, the successor to EDSCII. It runs on Windows and Linux, and will run on Mac OSX soon after a bit more work.
More info: http://vectorpoem.com/playscii/
Please note that Playscii is open source, still in early development, and is offered as a pay-what-you-want download here on itch. Testing and bug reports are appreciated!
Echo Nest Remix is the Internet Synthesizer. Make amazing things from music, automatically.
Turn any music or video into Python or JavaScript code.
Echo Nest Remix lets you remix, re-edit, and reimagine any piece of music and video, automatically and algorithmically.
Remix has done the following: played a song forever, walkenized and cowbellized hundreds of thousands of songs in a week, reversed basically everything, beat matched two songs, split apart DJ mixes by their individual tracks, made new kinds of video mashups, corrected sloppy drumming, synced video to a song, transitioned between multiple covers of the same song, made a cat play piano, and taught dogs to play dubstep. Check out all the examples here.
Remix is available as an open source SDK for you to use, for Mac, Linux, and Windows:
Install for Python: sudo pip install remix. Full installation details, packages for Mac and Windows, and complete Python documentation are here.
Try JavaScript: Test out remix.js here.
Download JavaScript: remix.js. Full JavaScript install details and documentation are here.
Fragmentarium is an open source, cross-platform IDE for exploring pixel based graphics on the GPU. It is inspired by Adobe's Pixel Bender, but uses GLSL, and is created specifically with fractals and generative systems in mind.
We describe a novel algorithm for extracting a resolution-independent vector representation from pixel art images, which enables magnifying the results by an arbitrary amount without image degradation. Our algorithm resolves pixel-scale features in the input and converts them into regions with smoothly varying shading that are crisply separated by piecewise-smooth contour curves. In the original image, pixels are represented on a square pixel lattice, where diagonal neighbors are only connected through a single point. This causes thin features to become visually disconnected under magnification by conventional means, and it causes connectedness and separation of diagonal neighbors to be ambiguous. The key to our algorithm is in resolving these ambiguities. This enables us to reshape the pixel cells so that neighboring pixels belonging to the same feature are connected through edges, thereby preserving the feature connectivity under magnification. We reduce pixel aliasing artifacts and improve smoothness by fitting spline curves to contours in the image and optimizing their control points. 
Spacebrew is an open, dynamically re-routable software toolkit for choreographing interactive spaces. Or, in other words, a simple way to connect interactive things to one another. Every element you hook up to the system is identified as either a subscriber (reading data in) or a publisher (pushing data out). Data is in one of three standardized formats: a boolean (true/false), a number range (0-1023) or a string (text); it can also be sent as a custom format you specify. Once these elements are set up, you can use a web based visual switchboard to connect or disconnect publishers and subscribers to each other.
Rekall est un logiciel destiné à l’ensemble des arts de la scène (théâtre, danse, musique, cirque, marionnettes, performance…) et aux installations interactives.
Rekall permet de :
Rekall est conçu pour :
Rekall documente un spectacle à plusieurs moments de sa vie :
