Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Midlibrary: Library of 4000 Midjourney artistic styles

midlibrary.io

Post reply on HN
Print view View original

91–100 of 143 posts

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#91

Post by kaetemi »

criley2 wrote: post #81
BadHumans wrote: post #73

Earlier quoted context omitted.

Being immortalized doesn't suddenly mean you stop paying bills

This is all so wild to me. All of human art is derivative of other art and all human artists wildly steal from one another. Further, "style" isn't copyrightable or sellable. Artists don't sell a style, they sell artwork. I just think it's wild that the entire human art scene is allowed to blatantly rip each other off (all pop sounds the same, all anime looks the same, all comic books look the same, etc etc) and it's…

A model that could reliably match up your work with similar artists and similar works (and point out the details) would be cool the have, tbh. Especially in music, where it's so easy to subconsciously copy some tune you vaguely heard somewhere before. Could set aside that worry of accidental copying, as well as give an objective measure in trying to steer towards a more unique niche.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#92

Post by GaggiX »

gumballindie wrote: post #89
The_Colonel wrote: post #86

Earlier quoted context omitted.

Generative AI are trained on "stolen property" the same way as human artists are trained on "stolen prolerty". Both study previous masters, learn to copy their styles, "inspire" their own art from some combination of existing styles.

Perhaps you are not familiar with how ai and machine learning work, and that’s okay, but ai doesn’t “study” and most certainly doesn’t “inspire” itself. It builds token databases that it then regurgitates. There no resemblance of human behaviour, just a simulation. Software always did that.

>you are not familiar with how ai and machine learning work

>It builds token databases

Well, you don't seem to know either.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#93

Post by GaggiX »

jakearmitage wrote: post #66

How can I use this? For example: if I have a picture of my wife, how can I apply one of these styles to her picture? I've downloaded InvokeAI and it runs, but I can't get it to just apply a style to an existing picture. I wanted to give her a birthday present and her picture using the style of her favorite artist in a frame would be amazing.

The best way to do this is to train a LoRA so that the model knows the person's likeness.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#94

Post by CamperBob2 »

WA wrote: post #41
imhoguy wrote: post #18

Dunno, I feel sad about artists a bit. I hope they won't stop creating. I am sick of these flashy AI fakes.

Imagine you are an artist and have a specific style and one day you wake up and the computer program that ripped off your style gets credit for that particular style, as in "4000 midjourney artistic styles". Horrible.

Art is a bit like technology in that respect. If you got into it expecting everything to stay the same, well... that was a bad call, wasn't it.

The cracks forming around you aren't fault lines, they're growth rings.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#95

Post by The_Colonel »

gumballindie wrote: post #89
The_Colonel wrote: post #86

Earlier quoted context omitted.

Generative AI are trained on "stolen property" the same way as human artists are trained on "stolen prolerty". Both study previous masters, learn to copy their styles, "inspire" their own art from some combination of existing styles.

Perhaps you are not familiar with how ai and machine learning work, and that’s okay, but ai doesn’t “study” and most certainly doesn’t “inspire” itself. It builds token databases that it then regurgitates. There no resemblance of human behaviour, just a simulation. Software always did that.

> It builds token databases that it then regurgitates.

Isn't pretty much all human art just regurgitation, recombination of prior art, audiovisual experience, emotions, human experience?

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#96

Post by The_Colonel »

chmod775 wrote: post #74
imhoguy wrote: post #18

Dunno, I feel sad about artists a bit. I hope they won't stop creating. I am sick of these flashy AI fakes.

Our vision of the future used to be one where every unpleasant job is automated, and humans are free to pursue higher callings such as art. It's increasingly looking we'll all be working in construction, scrubbing floors, or performing maintenance on the machines that took our pleasant jobs. The saving grace is it'll probably be just 10 hour work-weeks.

I don't see how generative AI changes the situation.

Most people would always face an uphill battle, producing mediocre art which only a few (likely with some personal connection) would appreciate.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#97

Post by The_Colonel »

omnimus wrote: post #62
gfodor wrote: post #61

Earlier quoted context omitted.

See it’s weird since I would consider this a form of immortalization. Some artists are seeing this way, but very few. It seems crazy to me more artists aren’t being amazed that their entire style is now “canon”

See it’s weird when somebody is upset when corporation steals and uses their code I would consider this a form of immortalization. Some programmers are seeing this way, but very few. It seems crazy to me more programmers aren’t being amazed that their entire codebase is now “canon”

That's a bad analogy. Artist style can be compared to a software pattern, neither of them are copyrightable. A finished artwork to a software project.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#98

Post by GaggiX »

CharlesW wrote: post #90
CaptainFever wrote: post #77

Earlier quoted context omitted.

- Spiderman: Into The Spiderverse (slightly, seems to be in-house): https://www.youtube.com/watch?v=7n12kHKvesc - Everything Everywhere All At Once (Runway AI): https://variety.com/2023/artisans/news/artificial-intelligen... Two massively popular films recently that used generative AI.

> seems to be in-house This is key. The unethical part is not the use of AI (which is neutral), but corpos taking billions in profits from creators using creators' own copyrighted works. BigAI currently feels entitled to simply take these works for their own use, without permission or licensing. This isn't hard stuff. Adobe Firefly is an example of an ethical, safe AI-powered art product that has been trained on owne…

>Adobe Firefly is an example of an ethical

For many people Adobe Firefly is almost as ethical as Stable Diffusion or Midjourney, as the authors of the images were not let to decide.

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#99

Post by CharlesW »

GaggiX wrote: post #98
CharlesW wrote: post #90

Earlier quoted context omitted.

> seems to be in-house This is key. The unethical part is not the use of AI (which is neutral), but corpos taking billions in profits from creators using creators' own copyrighted works. BigAI currently feels entitled to simply take these works for their own use, without permission or licensing. This isn't hard stuff. Adobe Firefly is an example of an ethical, safe AI-powered art product that has been trained on owne…

>Adobe Firefly is an example of an ethical For many people Adobe Firefly is almost as ethical as Stable Diffusion or Midjourney, as the authors of the images were not let to decide.

It's completely different because the artist explicitly sold or otherwise granted the rights to their creation(s).

Re: Midlibrary: Library of 4000 Midjourney artistic styles

#100

Post by ben_w »

makomk wrote: post #27
Der_Einzige wrote: post #4

Earlier quoted context omitted.

The consensus seems to be that the lack of open source SDXL anime fine tunes is simply due to laziness and lack of resources from the interested parties in the community. Datasets like from the boorus are already floating around online to train on. Always funny to see that furries are ahead of weeaboos in the war for the best open source nsfw generator

Last I heard, everyone was struggling to fine tune SDXL on furry art too. The only community fine tunes that seem to have succeeded are ones aimed at taking things it was already designed to generate and trained on and making it actually good at those, or improving the aesthetics of its output.

That's mildly surprising, given how large and well tagged e621 in particular is. Though I assume most of the major furry art hosts are blocking scraping by this point, given how divisive GenAI is?
Post reply on HN