AI Dreaming Of Time Travel

We love the intersection between art and technology, and a video made by an AI (Stable Diffusion) imagining a journey through time (Nitter) is a lovely example. The project is relatively straightforward, but as with most art projects, there were endless hours of [Xander Steenbrugge] tweaking and playing with different parts of the process until it was just how he liked it. He mentions trying thousands of different prompts and seeds — an example of one of the prompts is “a small tribal village with huts.” In the video, each prompt got 72 frames, slowly increasing in strength and then decreasing as the following prompt came along.

There are other AI videos on YouTube, often putting the lyrics of a song into AI-generated form. But if you’ve worked with AI systems, you’ll notice that the background stays remarkably stable in [Xander]’s video as it goes through dozens of feedback loops. This is difficult to do as you want to change the image’s content without changing the look. So he had to write a decent amount of code to try and maintain visual temporal cohesion over time. Hopefully, we’ll see an open-source version of some of his improvements, as he mentioned on Twitter.

In the meantime, we get to sit back and enjoy something beautiful. If you still aren’t convinced that Stable Diffusion isn’t a big deal, perhaps we can do a little more to persuade your viewpoint.

Continue reading “AI Dreaming Of Time Travel”

laser cut acrylic coaster with rgb leds inside

Your Mug Will Like This Glowy Coaster

[Charlyn] wanted to highlight their friends beautiful mug collection, so the Glowy Coaster was born.

The coaster is made up of six layers of laser cut acrylic. The top and bottom layer are cut out of clear acrylic, providing a flat surface for the coaster. A top pattern layer made of pearl acrylic has a thin piece of vellum put underneath it to provide diffusion for the LED strip sandwiched inside. The middle layers are made of peach acrylic and have their centers hollowed out to provide room for the electronics inside. The top pearl acrylic layer gives the coaster, as [Charlyn] writes, a “subtle touch of elegance”. The coaster itself is screwed together by an M3 screw at each point of the hexagon that feed through to heat-set inserts.

inside of glowy coaster with electronics exposed

The electronics consist of a short NeoPixel strip, cut to include 12 LEDs pointed in towards the center of the coaster. The LEDs are driven by a Trinket M0 microcontroller with a LiPo “backpack” to provide power, attachment points for the exposed power switch and recharging capability to the 110 mAh 3.7 V battery. The code is a slightly modified NeoPixel “rainbow” wheel loop (source available as a gist). The design files are available through Thingiverse.

Creations like these highlight how much care and work goes into a project with minimal beauty, where decisions, like the opacity and thickness of the acrylic or countersinking the M3 screws, can have huge consequences for the overall aesthetic. [Charlyn] has an attention to detail that brings an extra touch of professionalism and polish to the project.

Coasters are a favorite for laser cutting and we’ve covered many different types, including
coaster bots, coaster engravers and even a color changing, drink sensing coasters.

Continue reading “Your Mug Will Like This Glowy Coaster”

CMOS Oscillator Circuit Gets An Eatable Input

In interaction designer [Leonardo Amico]’s work Processing Decay, lettuce is used as an input to produce sound as an element within a CMOS circuit. 

We’ve all seen lemons and potatoes doubling in science-fairs as edible batteries, but lettuce is something else.  [Leandro]’s circuit uses alligator clips to insert lettuce into oscillators in this audio generating circuit — we think they’re behaving like resistors. Without refrigeration, the resistance of the lettuce changes, and so does the oscillation in the circuit. In a matter of hours, days, and weeks the cells degrades slowly, modulating the system and its sonic output. What a way to make music!

This hack isn’t the freshest — the video dates from nine years ago — but this is the first lettuce circuit we’ve seen. Of course, we love other food hacks like these multi-wavelength lasers used to cook 3D-printed chicken, or maybe the circuit can make use of this neural net detecting fruit ripeness. 

Robots Chase Down Balls In Fun Outdoor Game

Art installations aren’t always about static sculpture or pure aesthetics. In the case of Operation Kiba, they can be fun games for everyone to enjoy.

The aim of Operation Kiba is for the players to collect all the “balls” on the playing field, which are intended to represent scoops of ice cream. Collecting the balls is done via robot. Each player is ostensibly tasked with collecting one color of ball or the other, but players often decide to work together in harmony instead. The balls are released at the start of the game by tipping over a big bowl. This is half the fun, and is achieved by tugging a string which upends the vessel and scatters the balls.

The remote-control robots themselves come from an earlier art installation the group built called Bubble Blast. They’re built using a 3D printed chassis, with wheels on each side driven by DC gear motors. With tank-style steering, they can rotate on the spot, providing good maneuverability. An Arduino Nano runs the show, receiving commands over a 433 MHz radio link. Power is via DeWalt cordless drill batteries, and the robots are controlled via arcade sticks. They’re color-coded to match the balls in the game.

As far as art installations go, it may not be fancy or pretentious, but it certainly looks like a lot of fun. We’re sure it could eventually guide many players towards the exciting world of antweight combat robotics. Video after the break.

Continue reading “Robots Chase Down Balls In Fun Outdoor Game”

AI Midjourney Imagines “Stairway To Heaven”

This modern era of GPU-accelerated AI applications have their benefits. Pulling useful information out of mountains of raw data, alerting users to driving hazards, or just keeping an eye on bee populations are all helpful. Lately there has been a rise in attempts at producing (or should that be curating?) works of art out of carefully sculpted inputs.

One such AI art project is midjourney, which can be played with via a Discord integration bot. That bot takes some textual input, then “dreams” with it, producing sometime uncanny, often downright disturbing images.

You can have a tinker with it for free, for a short while, but there is monthly cost if you want to use it ‘for real’ whatever that means. YouTuber [Daara] has been feeding the lyrics from Led Zeppelin’s “Stairway to Heaven” into it, producing a video tour of the resulting outputs for your perusal. Continue reading “AI Midjourney Imagines “Stairway To Heaven””

Stable Diffusion And Why It Matters

You might not have heard about Stable Diffusion. As of writing this article, it’s less than a few weeks old. Perhaps you’ve heard about it and some of the hubbub around it. It is an AI model that can generate images based on a text prompt or an input image. Why is it important, how do you use it, and why should you care?

This year we have seen several image generation AIs such as Dall-e 2, Imagen, and even Craiyon. Nvidia’s Canvas AI allows someone to create a crude image with various colors representing different elements, such as mountains or water. Canvas can transform it into a beautiful landscape. What makes Stable Diffusion special? For starters, it is open source under the Creative ML OpenRAIL-M license, which is relatively permissive. Additionally, you can run Stable Diffusion (SD) on your computer rather than via the cloud, accessed by a website or API. They recommend a 3xxx series NVIDIA GPU with at least 6GB of RAM to get decent results. But due to its open-source nature, patches and tweaks enable it to be CPU only, AMD powered, or even Mac friendly.

This touches on the more important thing about SD. The community and energy around it. There are dozens of repos with different features, web UIs, and optimizations. People are training new models or fine-tuning models to generate different styles of content better. There are plugins to Photoshop and Krita. Other models are incorporated into the flow, such as image upscaling or face correction. The speed at which this has come into existence is dizzying. Right now, it’s a bit of the wild west. Continue reading “Stable Diffusion And Why It Matters”

Solar Cells As Art Form

When most of us approach a project, we have a certain problem to solve. 3D printing, microcontrollers, batteries, and all kinds of technologies are usually tools to accomplish some task. This is not necessarily true in the art world, though, where the intrinsic nature of these tools can be explored for their own sake rather than as a means to an end. The latest one that came across our desk is this light-powered sound generator.

The art piece looks a bit like a mobile with rotating arms, holding various small solar cells each connected to a speaker. As the arms pivot, the light falling on the cells changes which drives a specially-designed circuit connected to a speaker. The circuit acts as an oscillator, passing the changing voltage from the cell through various capacitors and transistors to produce changing tones in the speaker.

The effect of the rotating solar panels is not only oscillations from the speakers as the light changes, but oscillations in the sound of the speakers as they rotate towards and away from the observer. It’s a unique project and perfect for the art show it was in. It’s also not the only sound-focused art installation we’ve ever seen before, be sure to check out this one based on an ESP32.