Playing Around With A Family of Arty-Bots

ArtyBots Remix Collage

I don’t remember how or when I stumbled upon the collection of Twitter bots by B.J. Best but I suspect it have been during one of the handful of Networked Narrative projects I engaged with (in one session, we all created our own bots and mine is still rolling along as the PeaceLove&Bot). The Artybots collection by Best, a poet and designer, are fascinating, particularly because they were released before this latest wave of AI Art platforms.

Here is my video collection of remixes from the ArtyBot Family:

You can learn more about his project in this podcast interview at Design Notes.

The way the ArtyBots work is that you tweet an image to the bot and then it generates an artistic response, using the original image as the base of its operations. Some of the bots are also programmed to respond to each other, connect within what he calls the Bot Family.

I decided to play with his various bots with a single image. I choose an image that was an interesting zoomed-in shot of some moss on a pavement curb. I then fed the image to the various bots, and took the results, pulling them together into the slideshow. Not all of his bots fed me back an image to use, for whatever reason, but I enjoy seeing the remixed images that did come back fade into one another in the video compilation.

Is this art? Are the computer programs artists? Who knows, anymore. (Best suggests yes, the bots are artists in his podcast interview).

Peace (and Bots),
Kevin

Book Review: The Storyteller’s Handbook

mg_cream_TheStorytellersHandbook-CASE-BB-fnl

What to say about The Storyteller’s Handbook? It’s glorious, and packed with the most strange and wondrous illustrations, and very few words, and all in the service of sparking stories for the reader. (And an introduction by Neil Gaiman doesn’t hurt to set the stage for something magical unfolding in the pages).

It’s impossible not to look through this collection of art by Elise Hurst and not wonder about what happened before the moment, in the moment and then beyond the moment, and so, as a tool for sparking writing, The Storyteller’s Handbook does a fine job.

Every one of the 52 illustrations has something intriguing, and as I was wandering through, I began to wonder if there were narrative threads connecting some, if not all, of the illustrations together (or maybe it is just that I was mesmerized by Hurst’s artistic vision). She plays with scope and dimensions, of turning the mundane into something extraordinary, of placing the fantastical within a jar to looked at and then released.

All that, and more. See Hurst chat about the book in this short video:

At the book’s website, there is even a detailed Teacher’s Guide to use with the book in the classroom, and it is packed full of interesting ideas, prompts and activities (including a scavenger hunt!).

Peace (and Stories),
Kevin

PS — I am sucker for stories of how books came to be, and Hurst gives an evocative telling of where she came up with the idea for The Storyteller’s Handbook:

CLMOOC Collaborative Calendar: Welcoming 2023 With Art

In what has become a beautiful tradition of sorts, the CLMOOC community has come together again to create a calendar of original art and design for the coming year. With Wendy T overseeing the effort, the new calendar is ready and available in a few different formats, including free downloadable PDF or as a web-based Google Slideshow or as a video (see above).

More information about contributors, etc, is available at the CLMOOC website.

As always, I appreciate the global reach of CLMOOC (many contributors are from many different countries) and the way that making art and collaboration is a thread that binds us together, even after many years. The calendar project is a way to stay connected throughout the year.

Peace (and Hope Ahead),
Kevin

Rusty, The Rock And Roll Robot: From AI Art to AI Story with AI Music

Maybe I went a little overboard here but I was curious about what would happen if I merged the output of a variety of different AI-infused sites to create an AI story from an AI image with a computer-generated narrator voice backed with an AI soundtrack. The result was a tale about Rusty the Guitar-playing, Rock-and-Roll Robot.

Here’s how it worked: This all began with an interactive article in the Washington Post about how AI engines create art from text prompts. The article is excellent and the tool to play with was worth tinkering with, so I used the prompt to guide my experiment along: A robot playing guitar in outer space in style of a cover of a magazine.

AI Art via WashPo

I had an interesting image that I downloaded but now wanted a story. So I opened up ChatGPT and typed in this prompt: Write a funny story of a robot making the cover of a magazine for playing guitar in outer space.

Within seconds, I had the text of a story about a robot named Rusty who was rocking the space jam and ending up going viral and landing on the cover of a magazine. I took a screenshot the story.

Story via ChatGPT

I went into LunaPic to merged the Art image with the story, and added a border. Neat.

AI Art Meets ChatBotGPT

Now I wanted some voice narration. I used a text-speech site that wasn’t AI, really, but the computer-generated voice worked for what I needed: a “narrator” reading the text of the story of Rusty as an audio file.

Knowing this would become a video project, I wanted some soundtrack music. I went into a site called Melobytes, which takes an image and used AI to convert it to music. I used the combined Rusty Art/Story from LunaPic, and got a soundtrack. (I remain a little skeptical and unsure of how Melobytes really works its AI magic, but I stayed with it because I could not find an alternative for this activity).

I also used Audacity to mix the music with the narration, and then went into SoundSlides to pull everything together into one project, with an image backed by audio.

Is it any good?

Well, it’s interesting as an experiment, I think, and it shows how more and more AI projects could become collaborations across platforms.

Is it writing?

I don’t think so, but it was an act of “composition” as I tried to weave different threads of the story, generated by machine, into a coherent media project.

And you know, it’s likely that some company will surely bring all of these AI tools — art, text, music — under one umbrella at some point, and I am not even sure if that is a good development or bad idea when it comes to the world of stories.

Peace (press Play),
Kevin

Before The WMWP/SPAR WriteOut Event

Sun Shade Temperature Data Collage

Later today, the Western Massachusetts Writing Project and the Springfield Armory National Historic Site is hosting a live event for the national Write Out project. We’ll be at the Springfield Armory grounds, facilitating activities for educators on Climate Change, STEAM, Data Journals and more. It’s going to be a beautiful day and our two hour session will be outdoors, using the park property as our classroom.

One of the activities will be centered on understanding the impact of tree plantings as part of heat mitigation efforts and Urban Tree Canopies. We’ll be doing some measuring of temperatures, and creating data charts. I figured I should try it out myself, so yesterday, I did a little research around my own home. (see above).

There really is a huge difference between shade and sun areas, even during this Autumn time of year when things are cooling off.

Meanwhile, this morning’s Daily Create for DS106 was to design a launcher for Seed Bombs, which are made of special clay and hyperlocal seeds. We’re going to be making and launching Seed Bombs today at our event, but I went creative with another saxophone music seed for the design prompt.

Sax Seed Bomb Launcher

Peace (and plantings),
Kevin

Open AI, Algorithms and Art

Dalle-E Collection

I had forgotten I had signed up for an account with the DALL-E art site, which has gotten a fair share of notice for how it uses AI software to create art from written prompts. So when I saw an email yesterday, telling me my account was now active, I went in and played around. I used music themes for all of my prompts for the AI. The more specific the writing, the more interesting the image that the AI kicks out, I found.

I decided to create a “band” of musicians, with different settings and textual descriptions. It was an interesting experiment, and I used the “variations” tab quite a bit to see what the AI might generate in a second variation but for the most part, these come from the first round of algorithmic art by the platform.

I’ve included the text I used for the AI to generate the images.

DALL·E trumpet
DALL·E saxophone
DALL·E piano
DALL·E guitar
DALL·E drummer
DALL·E bass

You get a certain number of “credits” and then it costs some money to generate art.

Overall, I found the experience rather interesting, and yet I wondered how the AI was using my text descriptions to make itself “smarter” and was curious about what was going on underneath all of the code. There is a research paper available and the “about page” is full of positive elements of AI and the DALL-E site. It acknowledges the worries about AI, too, which I appreciated.

From the site:

Preventing Harmful Generations

We’ve limited the ability for DALL·E 2 to generate violent, hate, or adult images. By removing the most explicit content from the training data, we minimized DALL·E 2’s exposure to these concepts. We also used advanced techniques to prevent photorealistic generations of real individuals’ faces, including those of public figures.

Curbing Misuse

Our content policy does not allow users to generate violent, adult, or political content, among other categories. We won’t generate images if our filters identify text prompts and image uploads that may violate our policies. We also have automated and human monitoring systems to guard against misuse.

 

I am also curious about this part of the Mission Statement:

Our hope is that DALL·E 2 will empower people to express themselves creatively. DALL·E 2 also helps us understand how advanced AI systems see and understand our world, which is critical to our mission of creating AI that benefits humanity.

Let’s hope so, eh?

Peace (and Art),
Kevin

DALL·E music note

Marks on Wood: Filtered Effect Artwork

My students recently finished up working with a visiting artist — a woodcarver named Elton Braithwaite, who has been coming to our school now for 22 years — and their two pieces of collaborative carvings are very impressive. One has a tree theme. The other, a book theme.

The pieces have yet to be painted, so I took pictures of both carvings in their unpainted state, and began to play around with app filters (inspired by a friend of mine, Simon). One filter app I used (on the tree) is called Olli and the other (on the read) is Painteresque. The gif maker site is called Gif Maker.

I wanted to see the same image, fading in and out with filters. This approach worked better in another space, where Simon and I and others are sharing writing and art and more. The fade there was more natural. But here, I just used the online gif maker and layered the photos. The transitions are more abrupt, and a bit too quick (maybe I should have tinkered more with the settings on the gif creator).

It’s still kind of neat. The tree one works best, I think, for the app brings to the surface more of the textures of the carving piece. It’s a more natural piece of art. The read one is sort of distracting with the filters I used — at times giving it a sort of metallic sheen that goes counter to the concept of this being a carving on wood.

Peace (in the carving),
Kevin