E-Paper News Feed Illustrates The Headlines With AI-Generated Images

September 19, 2023 by Dan Maloney 7 Comments

It’s hard to read the headlines today without feeling like the world couldn’t possibly get much worse. And then tomorrow rolls around, and a fresh set of headlines puts the lie to that thought. On a macro level, there’s not much that you can do about that, but on a personal level, illustrating your news feed with mostly wrong, AI-generated images might take the edge off things a little.

Let us explain. [Roy van der Veen] liked the idea of an e-paper display newsfeed, but the crushing weight of the headlines was a little too much to bear. To lighten things up, he decided to employ Stable Diffusion to illustrate his feed, displaying both the headline and a generated image on a 7.3″ Inky 7-color e-paper display. Every five hours, a script running on a Raspberry Pi Zero 2W fetches a headline from a random source — we’re pleased the list includes Hackaday — and composes a prompt for Stable Diffusion based on the headline, adding on a randomly selected prefix and suffix to spice things up. For example, a prompt might look like, “Gothic painting of (Driving a Motor with an Audio Amp Chip). Gloomy, dramatic, stunning, dreamy.” You can imagine the results.

We have to say, from the examples [Roy] shows, the idea pretty much works — sometimes the images are so far off the mark that just figuring out how Stable Diffusion came up with them is enough to soften the blow. We’d have preferred if the news of the floods in Libya had been buffered by a slightly less dismal scene, but finding out that what was thought to be a “ritual mass murder” was really only a yoga class was certainly heartening.

GETMusic Uses Machine Learning To Generate Music, Understands Tracks

July 27, 2023 by Donald Papp 10 Comments

Music generation guided by machine learning can make great projects, but there’s not usually much apparent control over the results. The system makes what it makes, and it’s an achievement if the results are not obvious cacophony. But that’s all different with GETMusic which allows for a much more involved approach because it understands and is able to create music by tracks. Among other things, this means one can generate a basic rhythm and melody first, then add additional elements to those existing ones, leaving the previous elements unchanged.

GETMusic can make music from scratch, or guided from examples, and under the hood uses a diffusion-based approach similar to the method behind AI image generators like Stable Diffusion. We’ve previously covered how Stable Diffusion works, but instead of images the same basic principles are used to guide the model from random noise to useful tracks of music.

Just a few years ago we saw a neural network trained to generate Bach, and while it was capable of moments of brilliance, it didn’t produce uniformly-listenable output. GETMusic is on an entirely different level. The model and code are available online and there is a research paper to accompany it.

You can watch a video putting it through its paces just below the page break, and there are more videos on the project summary page.

Continue reading “GETMusic Uses Machine Learning To Generate Music, Understands Tracks” →

Text-to-Speech Model Can Do Music, Background Noises, And Sound Effects

July 24, 2023 by Donald Papp 8 Comments

Bark is a universal text-to-audio model that can not only create realistic speech, it can incorporate music, background noises, and sound effects. It can even include non-speech sounds like laughter, sighs, throat clearings, and similar elements. But despite the fact that it can deliver such complex results, it’s important to understand some of the peculiarities.

The model takes a prompt and generates the resulting sound from scratch. Results might sometimes be unexpected.

Bark is not a conventional text-to-speech program, and how it works has a lot more in common with large language model AI chatbots. This means that results can deviate from expectations, and outputs aren’t necessarily going to be studio-quality speech. As the project’s README points out, “(generated outputs can) be anything from perfect speech to multiple people arguing at a baseball game recorded with bad microphones.” That being said, there is some support for voice presets as a way to help guide the model with some consistency.

Bark was designed by a company called Suno for research purposes and is available under the MIT License. It can be installed and run locally, and has some demos available as well as an online implementation.

The ability to install and run Bark locally is promising territory for incorporating it into projects. And should you be more interested in speech-to-text instead, don’t forget about this plain C/C++ implementaion of AI-powered speech recognition.

Tree Supports Are Pretty, So Why Not Make Them Part Of The Print?

April 10, 2023 by Donald Papp 5 Comments

Here’s an idea that [Nephlonor] shared a couple years ago, but is worth keeping in mind because one never knows when it might come in handy. He 3D printed a marble run track and kept the generated tree supports. As you can see in the image above, the track resembles a roller-coaster and the tree supports function as an automatically-generated scaffolding for the whole thing. Clever!

As mentioned, these results are from a couple of years ago; so this idea should work even better nowadays. Tree supports have come a long way since then, and are available in more slicers than just Cura.

Tree supports without an interface layer is easy mode for “generate me some weird-looking scaffolding”

If you’re going to do this, we suggest reducing or eliminating the support interface and distance, which is the spacing between the supports and the rest of the model. The interface makes supports easier to remove, but if one is intending to leave it attached, it makes more sense to have a solid connection.

And while we’re on the topic of misusing supports, we’d like to leave you with one more trick to keep in mind. [Angus] of Maker’s Muse tucked a great idea into one of his videos: print just the support structure, and use it as a stand for oddly-shaped objects. Just set the object itself to zero walls and zero infill, and the printer will generate (and print) only the support structure. Choose an attractive angle, and presto! A display stand that fits the object like a glove.

You can watch a brief video of the marble run embedded below. Again, tree supports both look better and are available in more slicers nowadays. Have you tried this? If so we’d love to hear about it, so let us know in the comments!

Continue reading “Tree Supports Are Pretty, So Why Not Make Them Part Of The Print?” →

Let Machine Learning Code An Infinite Variety Of Pong Games

February 21, 2023 by Dan Maloney 7 Comments

In a very real way, Pong started the video game revolution. You wouldn’t have thought so at the time, with its simple gameplay, rudimentary controls, some very low-end sounds, and a cannibalized TV for a display, but the legendarily stuffed coinboxes tell the tale. Fast forward 50 years or so, and Pong has been largely reduced to a programmer’s exercise to see how few lines of code can stand in for what [Ted Dabney] and [Allan Alcorn] accomplished. But now even that’s too much, as OpenAI Codex can generate a playable Pong from just a few prompts, at least most of the time. Continue reading “Let Machine Learning Code An Infinite Variety Of Pong Games” →

Sight And Sound Combine In This Engaging Synthesizer Sculpture

October 23, 2022 by Dan Maloney 2 Comments

We’ll always have a soft spot for circuit sculpture projects; anything with components supported on nice tidy rows of brass wires always captures our imagination. But add to that a little bit of light and a lot of sound, and you get something like this hybrid synthesizer sculpture that really commands attention.

[Eirik Brandal] calls his creation “corwin point,” and describes it as “a generative dual voice analog synthesizer.” It’s built with a wide-open architecture that invites exploration and serves to pull the eyes — and ears — into the piece. The lowest level of the sculpture has all the “boring” digital stuff — an ESP32, the LED drivers, and the digital-to-analog converters. The next level up has the more visually interesting analog circuits, built mainly “dead-bug” style on a framework of brass wires. The user interface, mainly a series of pots and switches, lives on this level, as does a SeeedStudio WIO terminal, which is used to display a spectrum analyzer of the sounds generated.

Moving up a bit, there’s a seemingly incongruous vacuum tube overdrive along with a power amp and speaker in an acrylic enclosure. A vertical element of thick acrylic towers over all and houses the synth’s delay line, and the light pipes that snake through the sculpture pulse in time with sequencer events. The video below shows the synth in action — the music that it generates never really sounds the same twice, and sounds like nothing we’ve heard before, except perhaps briefly when we heard something like the background music from Logan’s Run.

Hats off to [Eirik] for another great-looking and great-sounding build; you may remember that his “cwymriad” caught our attention earlier this year.

Continue reading “Sight And Sound Combine In This Engaging Synthesizer Sculpture” →

Perlin Noise Helps Make Trippy Typographic Art

March 10, 2021 by Donald Papp 8 Comments

Perlin noise is best explained in visual terms: if a 2D slice of truly random noise looks like even and harsh static, then a random 2D slice of Perlin noise will have a natural-looking blotchy structure, with smooth gradients. [Jacob Stanton] used Perlin noise as the starting point for creating some interesting generative vector art that shows off all kinds of different visuals. [Jacob] found that his results often exhibited a natural quality, with the visuals evoking a sense of things like moss, scales, hills, fur, and “other things too strange to describe.”

The art project [Jacob] created from it all is a series of posters showcasing some of the more striking examples, each of which displays an “A” modified in a different way. A few are shown here, and a collection of other results is also available.

Perlin noise was created by Ken Perlin while working on the original Tron movie in the early 80s, and came from a frustration with the look of computer generated imagery of the time. His work had a tremendous and lasting impact, and was instrumental to artists creating more natural-looking textures. Processing has a Perlin noise function, which was in fact [Jacob]’s starting point for this whole project.

Noise, after all, is a wide and varied term. From making generative art to a cone of silence for smart speakers, it has many practical and artistic applications.