Excerpts from The Other Book, Vernon Chambers, Esq.. 1866

Pages form Chapter One: Trespassers of a Celestial Nature. One of seventeen known copies of Chambers’ the Other Book recently came into the possession of the Uncanon Valley History Museum thanks to a generous donation by the  Melinoë Foundation.  Top persons are currently working to decode Chambers’ unique shorthand. 

Additional pages from another chapter may be seen in this post

In actuality, this is all AI-generated art produced with Midjourney, mostly with variations of the following prompt: 

a victorian naturalist's illustration of a grey alien, labels and notes, high detail, ultrasharp detail 

Prepare yourself for the magic, the glamour, the action, the music of...

DAVID BOWIE AND THE DRAGON LORDS (1981)

Featuring the vocal talents of David Bowie, Rene Auberjonois, Vincent Price, Farrah Fawcett, Bea Author and featuring Alice Cooper as the DragonLord Morrath.  

--

I don’t have Dall-E 2 yet, but but Dall-E Bot on twitter was kind enough to run this prompt. While I will aim to get more stills from the actual film in future sets (when I get Dall-E 2 access, most likely) these serve as a good start for the concept.

The logo was based on one generated in Dall-E mini, I used a font-matcher program to find the closest font match (ad Hoc Bis)

School Days

AI Artowrk by Pumpkin Empress I hated high-school. On the other hand, I took a Russian History class which to this day has served me well- I understand the politics, I have a deep admiration for their music and literature. I also got to apply for and was granted credit for Writing because way way way back in the early 1980’s creative writing class wasn’t a thing so it was only taught to the…

View On WordPress

Context

Following from my previous post and expanding on my contextual research, I came across the sculpture Dio from artist Ben Snell. As explained on the article on neural.it, the artist has fed a computer and its algorithmic learning network with images of classical and modern sculptures, so that the AI could design a new one, product of what was input. When the sculpture is designed, the artist grinds down to a powder the computer used for the design and reassembles it to give life to the sculpture. This is incredibly relevant for me, as I have been researching and producing on the interaction between sculpture, images and computer networks, and Dio is an incredible confirmation of this relationship. As stated in the article- He freezes the computational clock in its most daring form, which will never be recalculated by the same machine again, but fully amalgamated in its own materiality-. My work is currently lateral to this approach, because sculpture interacts with computers to mutate its physicality, instead of confirming it as seen with Dio. However, the two aren’t as far from each other; Dio allows for physicality through the interaction sculpture/computer, Dislocations allows for physical and remote extension through the same interaction. Also, Dio is unique and unrepeatable artifact, and Dislocations is unique and unrepeatable as every enactment of it is subject to the diverse elements that come together for each performance (interaction, location, connectivity). I also think it is really interesting how the aesthetic value of a computer generated sculpture is very much similar to the biomorphic and modernist sculptural work I have been studying so far and that I have adopted as my own representational device. This seems to say there is a natural connection, visually and ideologically, between form and computers. That is however explained by the fact that computers are in fact programmed by humans, therefore processing through natural standards.

source: http://neural.it/2020/01/dio-a-definitive-ai-sculpture/

https://www.theverge.com/tldr/2019/4/12/18306090/ai-generated-sculpture-shredded-remains-ben-snell-dio

Expanding on my research on Telepresence, I have been reading about Paul Sermon, pioneer of Telepresent art and performance art. While visiting his incredibly populated website, I came across interesting documentation. In regard to his Dissociative Identities, Sermon explains there are two identical installations in a gallery connected together through a network. Users in the installation spaces  blend together as video signal shown on screens. The users share together a telepresent space. As Sermon explains -The users of this installation are able to monitor and control their interacting body in an exploded montage of their individual identity. Extracted elements of the users body language will be observed through telepresent portals, by providing the performer with four sets of eyes, relocated around the installation; views from above, close up, face on, profiles and from below.- It’s crucial how the telepresent extension is not used only for space, but it becomes an extension of perception. The installation itself follows a simple yet effective modality. Two installations where the users are physically, and an octagonal space, where the users are telepresent with their expanded and blending perception.

In Telematic Vision, Sermon links together two locations, live through ISDN telephonic line. Comprising of two identical separate rooms, in each are present a blue sofa, in front of it a camera and a monitor, and on the sides two additional monitors. The viewer, one in each room, sits down on the sofa and their image is live fed to the other room. Their image is mixed together through an effect processor. As Sermon explains as the viewers sit down on the sofa to watch their own image they become functional to the installation. Moreover, as the artist explains - They start to explore the space and understand they are now in complete physical control of a telepresent body that can interact with the other person. The more intimate and sophisticated the interaction becomes, the further the users enter into the telematic space. The division between the remote telepresent body and actual physical body disappears, leaving only one body that exists in and between both locations.- This is very much relevant to my current practice and I will be developing on this further in the near future.

source

http://www.miriad.mmu.ac.uk/storyrooms/sermon.html

http://www.paulsermon.org/vision/

Furthermore in regard to my research about telepresence I came across David Bowen’s work, Tele-Present Water. The artwork, a tele-kinetic installation, features a computer-controlled mechanism and a mesh to simulate the movement of the ocean in Alaska. The mechanism receives live data of the intensity and movement of the ocean waves from the National Oceanic and Atmospheric Administration data buoy station 46075 Shumagin Islands Alaska. The installation was presented in the Polish National Gallery in Wroclaw. The artwork extends the visual information of the Alaskan Ocean in a remote location. In an interview the artist explains how, the mechanism that moves the mesh, is fully visible and is part of the visual composition of the artwork. Another aspect I have noticed, in the video documentation of the artowrk,   is that the the perimeter around the artwork is circumscribed with poles and ropes, so to avoid any unwanted physical interaction with the artwork from general public. This is done only before the public is allowed in the gallery, before that moment the poles weren’t there, so I assume that wasn’t a decision from the artist but rather a safe presentational necessity.

source

https://www.youtube.com/watch?v=FDbMTBInDIY&t=128s

TheCourse | Multipurpose Education PSD Template

New Post has been published on https://www.uberbuyer.com/2018/07/29/thecourse-multipurpose-education-psd-template/

TheCourse | Multipurpose Education PSD Template

LIVE PREVIEWBUY FOR $11

TheCourse.net is clean PSD designed for school, online courses, university, library, training center and other education related websites.

It comes with concise 56 PSD files and 5 AI Artworks, which are easy to edit and customize to fit your needs.

Designed with a simplicity in mind, based on Bootstrap 1170px grid. This Template has dark & light versions , singlepage & multipage versions. TheCourse is a great start for an education personnel or organization to start the online business.

56 Stunning Perfect Pixel / Detail Layered PSDs.

Based on standard 1170px Grid System

Unique Retro Style.

Elegant Dark and Light version

6 Homepage design with Single page and Multiple page version

6 Multi Layout Great & Clear Blog design

4 Amazing Portfolio Design with Dark and Light version

5 Beautiful Illustraton Artworks including Logo, Banner, and background

8 Header & 5 Footer variation

9 Full Amazing Detail Reusable UI Kit Elements.

Marketing Email templates included

Easy to find the files name, folder, layers, goups.

Clear and Effective Documentation.

Standard Branding including Logo, Color Pallete and Graphic Artowrks

Icons Used Free Icon By Icomoon.io

Fonts OpenSans by Google Fonts

Images Used Unsplash BUY ON ENVATO

Saw this weird seal down by the Loch. Nature is healing.

Not sure how it got there tho.

Midjourney AI:  real photograph of the loch ness monster emerging from the water, roaring, terrifying, choatic scene, frothing water, verdant scottish hills in the distance, journalistic photography, 4k

This Toy Does Not Exist: ManBeasts of Xor

Short lived but memorable. The regrettably sculpted and named “SteelHog” sank the whole premise, sadly.

An experiment with image prompting in Midjourney. Boring technical stuff about how AI tokens work below.

Prompt:  a battle beast action figure from Hasbro (1987)

For these, most prompts were a variant of the above line, with 1-4 Battle Beast toy photos used as image prompts. An example:

These were an experiment with image-prompting, mainly, seeing if I could get a highly accurate result for an obscure concept if backed up with image prompt support. The answer, not unexpectedly, is “no.” The ManBeests are clearly of a similar genre, but they aren’t remotely close to the trademark aesthetics of the line. Why so?

Say it with me “AI often doesn’t work how we assume it does.”

In the simplest terms, Midjourney, SD, Dall-E2, etc, all use a process by which two AI bounce JPEG compression noise back and forth until it looks like something. One AI is based on object recognition, the other primarily in image generation. The latter modifies the JPG noise with its series of learned patterns (more on that later) and the former tells it to do it over if it’s estimation of the “match” of image to prompt is worse than it was previously. Once they reach consensus, you’ve got a picture.

The process is more complicated than that in practice. There’s other AI processes looking for things the programmers don’t want, like porn and gore in the case of Midjourney, and correct against it. There’s general processes that influence composition. AIs with an ‘overpaint’ feature let you substitute an existing image for the random JPG noise as a starting point, etc.

The information the AI used to refine this JPG noise is gathered from the dataset, largely the LIAON sets scraped from the web. This information is not stored as pixel data. Instead, the AI breaks down the images into patterns based on similarities with other images sharing common tags. These “tokens” are what the AI builds its images out of.

When you type a prompt into the AI, that sentence is broken down into the associated tokens, and then the AIs get to work building the new image from that “vocabulary” of concepts. Essentially, the AI looks at a bit of JPG noise, goes “if this part looks like this, what’s the part around to it likely to look like, based on the weighted models of similar items I’ve seen in the past?” and then fills that in, repeating as its checked and re-checked by the image-assessment half of its function.

The use of abstract patterns rather than raw pixel data is why when you see the AI recreate a jibberish signature or watermark, it’s in generally the correct spot. Were the AI designed to collage bits of existing images together, as is often the assumption, you’d get chunks of signatures in random places and watermarks would be broken into randomly distributed chunks.

Instead, the pseudo-signatures tend to be in the right place. Because the AI learns from what it observes, and it’s learned that in a lot of pictures, there’s a bit of writing in the lower right-hand corner, and that its presence and prominence varies based on other tokens in play. It’s learned this the same way it learned where nostrils go.

So why is it that even with direct name and image prompting, the results we’re getting here are so... new?

Midjourney’s image prompting isn’t the overpainting process I mentioned above. Instead, the image is examined to see what tokens it recognizes, and it prompts for those as if it were part of the text prompt. (This does not add to the dataset, that would be a different process)

The thing is, no human laid down the token language. The AIs build them as they need them, and they form new tokens based on associations humans would not recognize, much less intend.

In a case where someone was able to back-engineer part of the token language of one of these image-AIs, they found that it had invented a new “word” that was associated with flying animals. A general catch-all term that grabbed all flying animals regardless of species, (funnily enough, very similar to the way “bird” is applied in the Bible.). This new term would be introduced into prompts as they were converted from English into the token language, based on what the text-parser deemed appropriate.

So it might know Battle Beasts, but doesn’t have a lot there. But it also has everything BB is associated with, even if its not explicitly called out in the prompt or images. I expect that either through the dataset, or just through aesthetic observation, it’s connected the concept of “Transformer” and the concept of “Battle Beasts” given the flourishes, but everything from the general concept of an action figure to the general idea of an animal is getting involved there.

In essence, no prompt is ever “pure”, and every generation involves far more influences than you’d imagine. Even taking every effort to narrow down the variables, the results were still unexpected.

Just what... is it?

Midjourney AI Prompt:  render of a, hyper realistic, 4k, artistic, ultra detailed, octane render, photorealistic, glowing, ultra realistic, crystal, transparent

Incursion

If only they would do us the courtesy of communicating in language.

Girlboss

Business is... good?

Prompt: a woman combining the traits of Gillian Anderson, Jennifer Aniston and Sophia Loren wearing 80s-style business suit with large shoulderpads, mirroed sunglasses, bob haircut, girlboss, businesswoman, in G.I.Joe (1983), cel animated cartoon by toei animation, blu-ray transfer 5k

She’s doing that laugh again.

Niji-Journey Beta Prompt: a beautiful, mysterious woman, half green, half purple, vibrant colors, laughing

Dogs O’ War

An attempt at using image prompting to make toy concepts of my sister’s dog.

Prompt: <https://s.mj.run/URDGWmuWowA> <https://s.mj.run/z0m9I-97ZsA> <https://s.mj.run/heIbU4yfpxA>  a small, cute and adorable terrier warrior in mecha-armor

This Action Figure Vehicle Does Not Exist (Yet), Part 1

By now you may know the deal, but in case you don’t, this is “This Toy Does Not Exist” continuing to filter toys from teh Uncanon Valley Flea Market into this reality via Looking Glass AI. 

These are also free for anyone to base their own new creaitons on. So if you want to sculpt a figure or do some fanart, you’re good to go. These tokens are entirely, nay, exceptionally fungible. so save and share to your heart’s content.

I’ve got action figures, Transformers, you name it.  Check ‘em out, make derivivates, have fun.

Edit: Almost forgot the unsorted directory.

This Toy Does Not Exist - Action Figures Wave 3 

While I wait for the 2000 same full figure set to fully finetune, here’s the 1700 set, which includes a small smattering of keshi in the mix, on top of the wave 2 batch. 

These figures are all created using Lookingglass AI and pictures of real action figures. You are free to use them for your own projects and as the basis of derivative works.

Previous This Toy Does Not Exist installments:

Transformers Gen AI - Part 1

Transformers Gen AI - Part 2

This Toy Portrait Does Not Exist 1 

This Toy Portrait Does Not Exist 2

This Action Figure Does Not Exist 1 

This Action Figure Does Not Exist 2

This Keshi Does Not Exist

The unsorted output of this run is here.

That Doctor Scully is One Classy Dame!

Keep in mind, it’s the 1920s, and I’m saying this in an old timey raido voice.

Midjourney AI: a stylized 1920s comic book illustration of dana scully, high-res scan

At last my hideous, atonal piping has driven this postmodern Azathoth to dance, and its groove is FUNKY!

Please enjoy some soft serve courtesy of this friendly demon.

These are mere previews. The true madness is to come. But we’ve breached 2000 samples in the database for the LookingGlass AI behind This Toy Does Not Exist...

The results speak for themselves.

Though not literally, obviously. That was a metaphor.

Just wordplay.

See you soon.