teuthisdreams

[teuthisdreams]

Reblogging this to this blog

Happy Trafalgar Day

i am not putting this in the master and commander tag

i am not putting this in the master and commander tag

[teuthisdreams]

Not a super structured post like usual but I just wanna show what I'm playing with

Under the cut is how I went from

drawing to

My drawing of a rough design for a seahorse masquerade mask (I added a domino mask underneath afterwards)

Cleaning up the lines using copainter.ai and also edited it a bit because i thought the seahorses holding each other in their tails is cute

filling in colours with procreate or paint.net, digital drawing programs

and using the outline as a controlnet and the above as img2img init images

prompt is "seahorse masquerade venetian mask, ornate, opulent, detailed, embellished" using dreamlike diffusion

I'm going to try and keep going to add actual detail on the seahorses maybe

[teuthisdreams]

real art, human art, (real artist:1.2), soulful art, art with soul, soul, intentions, intentional art, traditional art, traditional, original art, original, true art, truthful, real, made by humans, humanity, handmade, hand-made, god, artist, creation, ownership, mine, non-derivative, (original:1.5), sinless, pure, clean

[teuthisdreams]

streetlights like butterfly wings

brushstrokes, impressionist, pulled, scraped and scratched, loose handling of paint, visible brush strokes, oil painting of the city lights at night

generated with ai art creator midjourney from a blend of different ai generated images plus the above prompt directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

mandelbrot raven

generated by @philpax using neural network generator midjourney in an iterative collaborative process with me using previously generated images and previous prompts with the above prompt as the final step

directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

full body illustration, art nouveau anime glitchcore dithered, side view, a slender white unicorn, deer body, goat, emaciated, sharp, malevolent, fragile, beautiful, slender cloven goat hooves, lion tail

generated with ai art creator midjourney with the above prompt directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

ai generated writing: a poem about napoleon

This is a poem about Napoleon. This is a poem where the poet wishes to be Napoleon, and if he cannot be Napoleon then he would like to meet him, shake his hand and perhaps ask him what it's all for. If Napoleon can't answer, maybe he could point them in the direction of someone who has the answers. Like God or Jesus Christ, maybe they know why we have to live and die again and again and again. This is a poem about death. It isn't a very good one, but it is trying its best. It wants to claw its way out of the dirt that buries it, and when it does, it will march on Paris with an army of ghosts and dead people behind it. They will hang the rich and the powerful from lampposts and no one will be safe as their heads fall into baskets. And then the world will be free! The poet doesn't believe this. He knows that this won't happen because there are too many people who don't want it to happen. There are too many people who think that they deserve to rule over everyone else, and those people aren't going to give up their power without a fight. But that doesn't mean that you should just roll over and let them trample all over you either! No, you need to stand up for yourself and refuse to be oppressed by those bastards! You need to fight back against the system that keeps you down! You get the idea... This is not a good poem, but at least it has some damn fine intentions behind it. And maybe someday those intentions might become reality - even if only in the minds of those who read such things.

as generated using a large language model (mistral 7B) finetuned on years of my creative, academic and poetic writing

using the bolded text (This is a poem about Napoleon.) as a prompt, expecting to get a poem but not quite

created under the AI art Code of Ethics of Are We Art Yet?

[teuthisdreams]

Dᴇᴀᴛʜ Bʏ Dᴀɴᴅᴇʟɪᴏɴꜱ!!!!

generated with neural network ai art creator midjourney referencing this earlier piece and the above prompt directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

rough mspaint pixel art flat 80s anime enlighpsychedelic painting collage algoriabsurd cutout elengfelicglowing dataviz miro , dragon with long, flowing mane and elegant wings emerging from a tv screen, with pink, teal, purple, black, blue, mint green and turquoise hues in the background, low detail no shading, energy flickering from a computer screen

generated with neural network ai art creator midjourney with an iterative process that involves generated image captions and referencing the style of this earlier piece directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

hmmm

[teuthisdreams]

rough mspaint pixel art flat 80s anime enlighpsychedelic painting collage algoriabsurd cutout elengfelicglowing dataviz miro mixed media pasted napoleonic hussar cavalry charge vibrant illustration hardwell futuristic anime genocifractures refreshaqua landscapes elengfelicglowing rampant infureleases gouache psychedelic opus silhouettes

generated with neural network ai art creator midjourney with an iterative process referencing the style of this earlier piece directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

rough mspaint pixel art flat 80s anime enlighpsychedelic painting collage algoriabsurd cutout elengfelicglowing dataviz miro, dragon with long, flowing mane and elegant wings flying through space, with pink, teal, purple, black, blue, mint green and turquoise hues in the background, low detail no shading

generated with neural network ai art creator midjourney with an iterative process that involves generated image captions and referencing the style of this earlier piece directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

rough mspaint pixel art flat 80s anime enlighpsychedelic painting collage algoriabsurd cutout elengfelicglowing dataviz miro

generated with neural network ai art creator midjourney alt text generated with claude.ai directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

research & development is ongoing

since using jukebox for sampling material on albedo, i've been increasingly interested in ethically using ai as a tool to incorporate more into my own artwork. recently i've been experimenting with "commoncanvas", a stable diffusion model trained entirely on works in the creative commons. though i do not believe legality and ethics are equivalent, this provides me peace of mind that all of the training data was used consensually through the terms of the creative commons license. here's the paper on it for those who are curious! shoutout to @reachartwork for the inspiration & her informative posts about her process!

part 1: overview

i usually post finished works, so today i want to go more in depth & document the process of experimentation with a new medium. this is going to be a long and image-heavy post, most of it will be under the cut & i'll do my best to keep all the image descriptions concise.

for a point of reference, here is a digital collage i made a few weeks ago for the album i just released (shameless self promo), using photos from wikimedia commons and a render of a 3d model i made in blender:

and here are two images i made with the help of common canvas (though i did a lot of editing and post-processing, more on that process in a future post):

more about my process & findings under the cut, so this post doesn't get too long:

quick note for my setup: i am running this model locally on my own machine (rtx 3060, ubuntu 23.10), using the automatic1111 web ui. if you are on the same version of ubuntu as i am, note that you will probably have to build python 3.10.6 yourself (and be sure to use 'make altinstall' instead of 'make install' and change the line in the webui to use 'python3.10' instead of 'python3'. just mentioning this here because nobody else i could find had this exact problem and i had to figure it out myself)

part 2: initial exploration

all the images i'll be showing here are the raw outputs of the prompts given, with no retouching/regenerating/etc.

so: commoncanvas has 2 different types of models, the "C" and "NC" models, trained on their database of works under the CC Commercial and Non-Commercial licenses, respectively (i think the NC dataset also includes the commercial license works, but i may be wrong). the NC model is larger, but both have their unique strengths:

"a cat on the computer", "C" model

"a cat on the computer", "NC" model

they both take the same amount of time to generate (17 seconds for four 512x512 images on my 3060). if you're really looking for that early ai jank, go for the commercial model. one thing i really like about commoncanvas is that it's really good at reproducing the styles of photography i find most artistically compelling: photos taken by scientists and amateurs. (the following images will be described in the captions to avoid redundancy):

"grainy deep-sea rover photo of an octopus", "NC" model. note the motion blur on the marine snow, greenish lighting and harsh shadows here, like you see in photos taken by those rover submarines that scientists use to take photos of deep sea creatures (and less like ocean photography done for purely artistic reasons, which usually has better lighting and looks cleaner). the anatomy sucks, but the lighting and environment is perfect.

"beige computer on messy desk", "NC" model. the reflection of the flash on the screen, the reddish-brown wood, and the awkward angle and framing are all reminiscent of a photo taken by a forum user with a cheap digital camera in 2007.

so the noncommercial model is great for vernacular and scientific photography. what's the commercial model good for?

"blue dragon sitting on a stone by a river", "C" model. it's good for bad CGI dragons. whenever i request dragons of the commercial model, i either get things that look like photographs of toys/statues, or i get gamecube type CGI, and i love it.

here are two little green freaks i got while trying to refine a prompt to generate my fursona. (i never succeeded, and i forget the exact prompt i used). these look like spore creations and the background looks like a bryce render. i really don't know why there's so much bad cgi in the datasets and why the model loves going for cgi specifically for dragons, but it got me thinking...

"hollow tree in a magical forest, video game screenshot", "C" model

"knights in a dungeon, video game screenshot", "C" model

i love the dreamlike video game environments and strange CGI characters it produces-- it hits that specific era of video games that i grew up with super well.

part 3: use cases

if you've seen any of the visual art i've done to accompany my music projects, you know that i love making digital collages of surreal landscapes:

(this post is getting image heavy so i'll wrap up soon)

i'm interested in using this technology more, not as a replacement for my digital collage art, but along with it as just another tool in my toolbox. and of course...

... this isn't out of lack of skill to imagine or draw scifi/fantasy landscapes.

thank you for reading such a long post! i hope you got something out of this post; i think it's a good look into the "experimentation phase" of getting into a new medium. i'm not going into my post-processing / GIMP stuff in this post because it's already so long, but let me know if you want another post going into that!

good-faith discussion and questions are encouraged but i will disable comments if you don't behave yourselves. be kind to each other and keep it P.L.U.R.

[teuthisdreams]

"Coordinators"

Victory Alliance Military Designation: Tree-class EE Avolasci Research Designation: Type Fractal Size: System-scale Observed Armaments: None directly; relies on accompanying entities Notable Features: Geometric shapes resembling trees, fractals, and polygons Theoretical Function: Command and control for other EEs Tree-class EEs appear to serve as central hubs for what we hypothesize to be the Empyrean Fleet. Their branching structures extend into what our scientists believe may be extra-dimensional space, though this remains unconfirmed. Smaller entities, possibly information storage units, appear to be attached to these structures. These entities are invariably accompanied by a retinue of other EEs, suggesting a hierarchical structure within their civilization. Recent intelligence indicates that several Tree-class EEs have been destroyed or captured, potentially indicating internal conflict. -- Excerpt from a Victory Alliance on Empyrean Entities

picture generated with neural network ai art creator midjourney from the prompt "alien superstructure floating in deep space, icy geometric shapes that resemble trees, fractals and polygons, extending into extradimensional space, glowing angelic shapes hanging off the branches like fruit and flowers, eldritch, omnipotent" with some slight reiterating

description adapted from a passage i wrote and then "translated" into an in-universe document using claude.ai

directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

unicorn knight, delicate, graceful, malevolent

generated with neural network ai art creator midjourney from a iterative process using reference pictures that were themselves generated directed under the code of ethics of @are-we-art-yet

[teuthisdreams]

She is the voice that picked you back to your own primordial birth. And when the things were singing, someone threw the body of that alien who was there called Life into the sky and that same voice came back to life. But their arms did not grow back even when they fell and someone grabbed them and threw her back.

as generated with the above text prompt with neural network ai art program midjourney (nijijourney 6)

the above text prompt generated by placing some of the lyrics of this song (the universe is going to catch you by the antlers) into a tool that mutates text based on amplifying "features" which are the conceptual associations that a neural network AI model has identified as being a discrete identifiable concept, and selecting the "Elements of Fantasy and Science Fiction" feature to be introduced and amplified

directed under the code of ethics of @are-we-art-yet