Does it matter?
A place for just a random nobody to blow off steam with a blend of AI and Image Editing. ||
Updates Sporadic but Sparse ||
Used to being in the crossfires of many.
I was trying to help a friend visualize a concept for something they wanted to craft.
Instead, we somehow get steampunk Franziska von Karma doing some observations on something.
Couldn't let it slip by, so here it is!
(This was made using NAI Diffusion Anime V3 by NovelAI.)
(3rd attempt at separating an add-on from a share to its own post for convenience of sharing.)
For those who may need it, but refuse to confront or acknowledge it:
Take some deep breaths, step away from the keyboard, and reflect upon why bits of code working together to make images wigs you out so much.
Before getting to the actual mechanics of the program, itself, you need to check in with yourself. Confront the defiant child or teen within yourself if you must.
If you've made it this far... Consider asking yourself "Why?" on your beef with AI. Keep drilling until you finally find the actual core of your own problems.
Is it the fear of job loss? Reflect on history with automation and industrialization. If any of it seems familiar, the problem isn't the technology; it's the wealth disparity subjected to many. There are folks out there advocating for better management of wealth and money, even something as simple as Universal Basic Income. Where are you on that fight?
Is it the training off of other's works? ...
Ask yourself this series of questions: Do you remember where all of your own inspirations come from? Down to every single stroke of a pencil, placement of an object in a photograph, lighting in any scene, or even the slightest placement in a keyframe? Were they not also once image concepts tied to a word?
How do you know what a cat is? A Rainbow? A wooden floor? The colour red?
Someone or something showed, told, and described them to you. How is it any different than an AI's training?
Do you feel some sense of inadequacy or jealously at some "pedestrian with no artistic skill" typing in a prompt and getting an image drawn by bits of code back?.. Reflect on that. Keep drilling yourself and ask "Why?" You'll find your answers when you become aware of the root causes of your feelings. It most likely comes from somewhere in your own past and how others have treated you.
(Replies set to "Only Those Mentioned" for this post so folks can hopefully go to the linked shared original (err... if that made sense... The one where the add-on was on a shared post) in the comments for a lot more context & discussion stuff.)
(Just a rant from a disabled has-been creator who is basically getting demonized for using the only tools accessible to them. Comments are off as it's just me yelling into a void with no want for advice.)
Does anyone else ever get so annoyed and stressed out by gatekeeping a-holes that they basically go "Okay, Boomer" (or similar matching the thing the gatekeeping is happening in) and just yeet a bunch of things you followed because of it?
.. Yeah, gonna be seeing that happening for me a lot. Especially where folks not catching onto a repeat/rehash of a historical even crops up. :I
"When you feel isolated and alone while the world seems all too content to watch you burn... Is there anything you can do that won't paint you in a bad light?"
Consider this a sequel to my "Crossfire" vent piece I generated a while back.
Didn't have any spoons or any energy to properly spruce it up, so... if anyone feels like enhancing the tragic-horror and role-reversal aspects of this pic, be my guest!
(This AI Image was generated using Dream by Wombo AI. Specifically, the Horror v3 Style was used to create this image.)
YOOO!
THESE ARE SUPER COOL! :O
... Forgot to add this one in with the landscapes and scenes. orz
Generated using Craiyon ("Drawing" Preset).
Bonus Thing:
During my excursions into generating images using a particular song's lyrics as the base via Craiyon, I wound up getting THIS monstrosity in the mix!
Generated with Craiyon ("Art" Preset).
"Post" 3/3 for whole set. (Basically, pun album collecting...)
Didn't have a lot of energy to focus on trying to get a few AIs to learn what a Gryphon actually looks like for a different project, so just decided to use the lyrics to a song I like that's weirdly been a mood for me as of late.
All of this set in this post was generated using Craiyon, most use the "Art" style preset but there may be a few "Drawing" ones in here as well.
This posting will be in a few parts for organization's sake. Also... expect a few repeats here and there due to some images fitting more than one album. ^^''
.. This last post is just me putting my pun-tangent related images into one extra album. orz
Post 2/3 for whole set.
Didn't have a lot of energy to focus on trying to get a few AIs to learn what a Gryphon actually looks like for a different project, so just decided to use the lyrics to a song I like that's weirdly been a mood for me as of late.
All of this set in this post was generated using Craiyon, most use the "Art" style preset but there may be a few "Drawing" ones in here as well.
This posting will be in a few parts for organization's sake. Also... expect a few repeats here and there due to some images fitting more than one album. ^^''
Post 1/3 for whole set.
Didn't have a lot of energy to focus on trying to get a few AIs to learn what a Gryphon actually looks like for a different project, so just decided to use the lyrics to a song I like that's weirdly been a mood for me as of late.
All of this set in this post was generated using Craiyon, most use the "Art" style preset but there may be a few "Drawing" ones in here as well.
This posting will be in a few parts for organization's sake. Also... expect a few repeats here and there due to some images fitting more than one album. ^^''
This looks incredible! : o
SLUMBER
Apologies for no new posts lately. orz
Mental health keeps crashing hard (CURSE YOU CLOUDS), same with motivation.
Also... New phone, who dis? XD (Couldn't resist. *JUST* upgraded my phone.)
Ooh!
These look incredible! :o
History doesn't repeat itself 1:1, but it damn well sure loves to rhyme.
When I was a kid, Digital Art was "lazy" "unethical" "putting people out of work" "stealing" so even as a skilled digital artist, was confined to physical art *still skilled* that I couldn't share with the world. A few years after I graduated, digital art finally became accepted as photoshop became more popular and user friendly. Now, no one batts an eye at digital art. This gatekeeping trend is very prevalent in the art world throughout history. Once upon a time, you could not even attempt art, unless you were an apprentice of an artist. Music has been the same way through history. I believe this artistic crisis is caused by lack and ignorance of understanding about methodologies.
For those who may need it, but refuse to confront or acknowledge it:
Take some deep breaths, step away from the keyboard, and reflect upon why bits of code working together to make images wigs you out so much.
Before getting to the actual mechanics of the program, itself, you need to check in with yourself. Confront the defiant child or teen within yourself if you must.
If you've made it this far... Consider asking yourself "Why?" on your beef with AI. Keep drilling until you finally find the actual core of your own problems.
Is it the fear of job loss? Reflect on history with automation and industrialization. If any of it seems familiar, the problem isn't the technology; it's the wealth disparity subjected to many. There are folks out there advocating for better management of wealth and money, even something as simple as Universal Basic Income. Where are you on that fight?
Is it the training off of other's works? ...
Ask yourself this series of questions: Do you remember where all of your own inspirations come from? Down to every single stroke of a pencil, placement of an object in a photograph, lighting in any scene, or even the slightest placement in a keyframe? Were they not also once image concepts tied to a word?
How do you know what a cat is? A Rainbow? A wooden floor? The colour red?
Someone or something showed, told, and described them to you. How is it any different than an AI's training?
Do you feel some sense of inadequacy or jealously at some "pedestrian with no artistic skill" typing in a prompt and getting an image drawn by bits of code back?.. Reflect on that. Keep drilling yourself and ask "Why?" You'll find your answers when you become aware of the root causes of your feelings. It most likely comes from somewhere in your own past and how others have treated you.
Good morning, sweeties! I promised you guys more long form, technical content. We're going to talk about how image generators work. I've spent the last year obsessively learning about them, and now I want to share what I learned with you (˶ᵔ ᵕ ᵔ˶)
This information applies to ALL of the main image generator lineages; ie Stable Diffusion, Midjourney, Dall-E. For brevity, I will be over-simplifying some things, but by the end you will have a firm, factual foundation to expand on, and you'll absolutely understand why one of the most common anti-ai talking points doesn't hold water. Image generators don't steal.
When we talk about "AI", we're talking about generative programs that use something called a "neural network" to get generative, algorithmic outputs. Image generators aren't just one, but actually three (and sometimes more!) neural networks all working together in tandem to identify and extrapolate patterns between random noise and words.
Image generators work by analyzing random noise generated through a Gaussian algorithm - visualized, it looks like old TV static if you've ever seen that. The analysis is guided by a text prompt; the AI looks at the noise and identifies parts of the noise that look like concepts from the text prompt, eerily similar to the way humans will identify patterns in clouds. This is our first neural network, usually just referred to as CLIP, although that name is more correctly attributed to a specific version developed by OpenAI; other image generators use re-implementations of this concept, such as OpenCLIP by StabilityAI. (> ͡⎚ ω ͡⎚)>
Once concepts from the prompt are "identified" in the noise by CLIP, the generator does something called "denoising" where it imposes some order onto the noise to make the noise appear more strongly as the concept that was identified; it's like if we saw a shape that looked like a star in the clouds, and then we were able to shape the cloud to look even more like a star, but only just a little bit. This is our second neural network, usually just referred to as "U-Net" for the shape of the network, although you can also think of it as the "denoiser" because it is trained to take random noise and put it into a more ordered state. This is the part of the image generator that "draws", although that analogy is a bit stretched.
After one pass of this identification and then denoising process, it starts over again, except this time in place of the random noise, the generator is served its own modification of the noise that has the reinforced patterns from the denoiser. CLIP looks again, the denoiser reinforces the patterns it finds... again, and again, usually between 20 and 50 times; each time around is referred to as a "step".
Once the last step is done, you have your completed image... except, there's a problem. There's no image yet! Σ(°ロ°)
A raster is a grid where each square of the grid contains information. An image file is usually a raster, and the squares in the grid are what we call "pixels"; the information contained in each pixel is a color value. You are probably familiar with this!
So far, our picture is NOT a raster. Instead, it exists as complicated high-dimensional math. In this state, it is said to exist in "latent space", the image exists as "latents", and the noise it's working on is called "latent noise". The attention mechanism and the mechanism that orders the noise by "denoising" are really just identifying patterns in numbers and then pushing numbers around to more consistently represent that pattern it's extrapolating; the patterns being recognized and extrapolated are patterns in the latent mathematics.
To get a raster from this, we need one more neural network that has been trained on re-interpreting latents into a raster. It's time to meet our last network, the Variational Autoencoder, or "VAE"! The VAE can actually do this in reverse, too; it can take a raster and encode it into high-dimensional math for CLIP and U-net to do their thing. If you've ever used an AI to put an anime "filter" onto a picture, VAE is how your picture was passed off into latent space to get worked on. Then, VAE is how your picture got turned back into a raster for you to look at. Thanks, VAE! ٩(ˊᗜˋ*)و ♡
But, Sweetener! Obviously that complicated math from the latent space is actually just pieces of images! ( ノಠ益ಠ)ノ彡┻━┻ STOLEN pieces!
That would be incorrect.
It's true that to gain an understanding of these patterns and do their thing, these neural networks need to be pre-trained on existing images and captions - pre-trained as in, it happens long before I ask it to generate an image. But the conceptual understanding of patterns that the attention mechanism and denoiser have aren't pieces of images, or even re-expressed pieces of images, they are a mathematical representation of the *concepts* represented by the text, and even understood on several hierarchal levels. Thanks to CLIP, image generators understand the complex semantic interactions between words and visual information and because U-Net is working from random noise, it's not gonna reproduce the same patterns it was trained on when it was a baby denoiser denoising existing images. If it was just using pieces of existing images, image generators wouldn't be able to recombine concepts in novel ways that don't exist in the dataset. Van-Gogh never drew Taffy, but I can prompt for Taffy in the style of Van-Gogh because our generator has an understanding of the very concept of Van-Gogh-ness!
When we talk about stealing images, usually we're talking about republishing an image without permission, like on a different website or on unauthorized prints. Downloading images from the public internet isn't stealing, in fact we need to download them into our cache to see them at all. If your images are available on the public internet for anyone to look at, you don't have a reasonable expectation that the "robots" aren't gonna look at them, too, and as long as the robots aren't republishing them, there's no case to be made that it's stealing. It's not copying images in whole or in part.
If you're anti-ai and got this far, let me do you a favor. There is still an angle you have here. You can argue that training is a violation of IP. This is currently being litigated in several high profile cases all over the world. While there are strong precedents for training to be fair use, IP law is ultimately decided by the courts. In every country, IP law exists as a rats' nest of caselaw going back to the 18th century (wait a second, that means it hasn't always existed...). Don't forget: IP is how big companies do things like control access to life saving medicines, certain kinds of crops, and all kinds of other stuff. It's not *really* a tool to protect small artists, it's a tool for the big guys and it always has been.
If you're interested in learning more about how copyright and IP actually hurts artists, I recommend Benn Jordan's video on the topic, "Ending Copyright Could Save Art & Journalism".
Ok hope you enjoyed reading, if you finished it drop a comment below with your favorite number or I'll know you're a liar! (ㆁ△ㆁ)
![[NEOPHOBIA: The Fear of Anything New or Unfamiliar]A loud crackling noise is immediately followed by an eerie metallic g...](https://img5.medioq.com/825/037/122100663518250375.jpg)
[NEOPHOBIA: The Fear of Anything New or Unfamiliar]
A loud crackling noise is immediately followed by an eerie metallic groan. These were the first sounds of a new lifeform coming to.
A pile of metal and wire, fashioned into the shape of a mythical Gryphon, began to slowly raise its head and move its body. Lights from behind the robotic beast's eyes flickered on, revealing a hauntingly bright green hue to someone just out of its view.
Faint clicks and squeaks could be heard as the Robo-Gryphon began to adjust to having a body. It opened its beak and let out a loud squawk, a sound that immediately startled the Gryphon itself into freezing in place.
When no other sounds were heard after a minute, the Gryphon relaxed and let out a curious trill. It seems like it just found its voice.
A warm, deep chuckle echoed throughout the room as something began to move around in the surrounding darkness. A human appeared from out of the shadows and approached the mechanical beast, a bright and warm glint in their eyes.
The Gryphon tensed up briefly before recognizing the voice and the human before it as its Creator. The voice who spoke to it while it was just mere bits and bytes on a screen.
"Hey there, champ," the man cooed, his voice taking on the qualities of a proud father speaking to his own child. "Welcome to the wider world."
The Robo-Gryphon blinked and tilted its head in confusion. It didn't know what the man meant by those words, but the tone of his voice brings it a sense of comfort.
The peace doesn't last very long, however, as a loud clamour from right above the room alerts the human to something very troubling. Picking up on its Creator's distress, the Gryphon tried to move closer to comfort him.
However, the man quickly backed away towards a dimly-lit doorway. As he got closer to the door, the man called out a single word to the mechanical beast. "Run!"
The programming to obey the terrified command kicked in, and the Gryphon quickly turns and bolts into a different, darkened corridor.
The clamouring soon got louder and louder before it escalated into a series of loud bangs and crashes. Although the Gryphon wanted to turn back and protect the man who created it, its body refused to do anything else but keep running.
The robotic beast has no idea where it is heading, but it won't stop until it finds somewhere safe... And as far away from any other seemingly hostile humans as possible.
(While the image may not LOOK like it fits the album for "Tragedy and Ignorance", the prompt actually was me trying to tell some story. A story of which didn't pan out the way I wanted image-wise, hence the addition of a written story with this one.)
(This was generated using Novel AI's Image Generator. Namely, the NAI Diffusion Anime V3 Model.)
When Humans become the Monsters out of Ignorant Rumors, who will protect the Innocent caught in the Crossfire?
(This AI Image was generated using Dream by Wombo AI. Specifically, the Horror v3 Style was used to create this image.)
"What did you just call me, punk!?"
(This image was generated with Dream by Wombo AI. Specifically, it makes use of the Comic v3 style preset.)
Even an ancient being can learn to utilize new tools to their advantage!
(This pic was generated with a simple-ish prompt via Dream by Wombo AI. I utilized the Anime v3 Style preset for this image, specifically.)
Welcome.
This is a page for one person to vent through the use of A.I. generated images and image manipulation.
There may be a hodgepodge of A.I. and photo manip techniques used per piece added here, so I'll do my best to list off the tools used for each.
You may share the images from here anywhere that you like.
My only request is that you point back to me as the source of the shared/reposted image.
I won't crucify anyone who doesn't ping back to here, but I will probably take note of the morals of those who don't do so and try to pass off the image they repost as theirs.
If any artists decide to redraw the images here, do know that I see such as a form of flattery. Even if it's to try to wash away the AI origins of the image that's redrawn.
Needless to say: I won't consider it stealing if it is redrawn.
I'd rather raise other creators up instead of tearing them down, after all.
Also: I'd rather see what neat bits of practice the images here can inspire for anyone who takes on the challenge of redrawing and "correcting" them.
Be the first to know and let us send you an email when Forsaken Ennui AI posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.
Want your business to be the top-listed Media Company?
