Combination MidJourney with Houdini

[Librarian]

Imagine /
"Its offer really fast bowling for Ideas" I think nothing more ...
homework for today to Build in Houdini..
 

[flcc]

ai generated images become very interested these days. I've also apply for an invite some day's ago, but nothin fot now.

[animatrix]

You can use this invite:

https://discord.com/invite/7TJ5vx2GA3

[Librarian]

More Invites 24 Hours /exp
https://discord.gg/C6AWXQwQ

[animatrix]

I also did some experiments with MJ, it's a crazy powerful tool:

[Librarian]

crazy powerful tool I'm Addicted..

 

[DecoyOctopus]

I tried to make something ugly, but still ended up with something kinda beautiful to look at:

Edited June 26, 2022 by DecoyOctopus

[flcc]

@Librarian Thank for the invite but I have already get mine. Can be usefull for someone else

And by the way yes it's totally addidictive,

And effectively can be very cool for some inspirations

 

 

 

 

 

And a mix of two "render"

 

 

 

 

 

Edited June 26, 2022 by flcc

[flcc]

@Librarian Especially for you

Starting prompt : Art_Forms_in_Nature_drawing_by_Ernst_Haeckel

 

[Librarian]

@flcc In the near future, if we experience it, how things started in the world and the plunder of ordinary people, I hope!. There will be no need for two people to work on the project, only an IDEA will be enough, nothing more, at least I think so. Idea its everything  Always . Fantasy

[flcc]

Is this your Library (first two images) ?

[Librarian]

Yes @flcc My imagine/ promt

 

[flcc]

Houdini sidefx seen by the AI

 

 

 

Edited June 29, 2022 by flcc

[Atom]

I'm trying out the GitHub version of CLIP Guided Diffusion.  I seemed to be "capped" at 256x256 output. I run out of GPU memory when I try 512.

Does anyone have any tips on making larger output?

 

"A fractured sky by Odilon Redo"

 

"A melted clock, by Salvador Dali"

 

"Beautiful lemon people enjoy a dessert, by Richard Dean"

 

"A massive starship battle inside a beautiful nebula, artstation, dof"

 

Edited July 2, 2022 by Atom

[jordibares]

No doubt MidJourney is mindblowing, that said, I am worried about the Terms of Service, in the end, I am not sure what I do there is really mine at all. Check this out, moreover, let's imagine someone sees one of my images and decides to 'be inspired by them' and produce art that is derived from those, is it really a minefield so I am not that keen on using MJ precisely because of that.

Furthermore, everything has a bit of a look, that I don't like either so I am not sure this is for me... not sure.

What do you guys think? I am very interested in your opinion on the subject.

 

Rights you give to Midjourney

By using the Services, you grant to Midjourney, its successors, and assigns a perpetual, worldwide, non-exclusive, sublicensable no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute text, and image prompts you input into the Services, or Assets produced by the service at your direction. This license survives termination of this Agreement by any party, for any reason.

 

Your Rights

Subject to the above license, you own all Assets you create with the Services. This does not apply if you fall under the exceptions below.

Please note: Midjourney is an open community which allows others to use and remix your images and prompts whenever they are posted in a public setting. By default, your images are publically viewable and remixable. As described above, you grant Midjourney a license to allow this. If you purchase a private plan, you may bypass some of these public sharing defaults.

[Atom]

I agree, I don't like the terms of service or paying for it. There are the open source versions you can run locally which have a different look, because they are trained on a different image set. I think there is no doubt, that this is the future of concept art. Another job replaced by the machine.

 

"a wizard casts a magic spell in a serene slight fog, brighten shadow"

[Librarian]

Yes absolutely right @jordibares regarding that some strange look(it has that strange feeling when you look on any produced picture from MidJ...not Fake, more like to Complicated and Fine at the some Time( but maybe that its the Feeling that I have when you know that its not A persona Making that, i don't know   , @Atom not only for concept I'm afraid ...and for there's Terms of Service Rights and other Baloni ..they change every  week terms ..because its not holding anywhere,  if we gonna go know really deep on what they first use to make those pictures ...its a bunch already made names of something that exist or not(some Famous artist/fine Art/Octane ,Arnold Fine art   ), they don't own rights on words they can't absolutely forbid any one to make art of those Prompts on any software( just change color on place of Stone)...Just think About Music Right's and Tones ....they changing every week Terms... and they just HAPAJu paricke "taking money for just short period" it gonna be free soon for everyone .. I think so ..

[flcc]

If you want to use the midjourney images as is, the terms of service are indeed rather prohibitive.
But in a professional context midjourney is more of a source of ideas, and in this case it is not a problem.
I already use it for a professional project, and the images allow me to either :
to add proposals to mine to know where the client wants to go. It's just "concepts" that will end up in the trash.
Or to get some textures, or elements such as skies or meadows but that I will recompose completely, and will be jsut some parts of the final work.

That's why I'm not too worried about the professional concept artists. It will be an extra tool in their kit. But when it comes to fulfilling a director's specific request, there is still time before midjourney is able to do the job.

Just try to get a green ball in a red bowl in front of a blue wall, you will see that there is still a long way to go before midjourney would be able to answer a precise and complex request, with framing, perspective orientations and character positioning.

 

Edited August 9, 2022 by flcc

[animatrix]

There is also a new open source one called stable diffusion, so it will be great to use this. I heard it's not censoring stuff also. So the price of running on cloud and locally could actually be much cheaper than MJ.

[flcc]

Here is an interesting excerpt from an interview with David Holz (founder of Midjourney), in which he discusses issues related to terms of service, copyright and authorship.

The link to the full interview
https://www.theregister.com/2022/08/01/david_holz_midjourney/
and a link to the decision against Steven Thaler and his AI
https://news.artnet.com/art-world/us-copyright-office-rejects-artificial-intelligence-art-2076830

"
America, land of the lawsuit

In terms of Midjourney output, current US jurisprudence denies the possibility of granting copyright to AI-generated images. In February, the US Copyright Office Review Board rejected [PDF] a second request to grant copyright to a computer-generated landscape titled "A Recent Entrance to Paradise" because it was created without human authorship.

In a phone interview, Tyler Ochoa, a professor in the Law department at Santa Clara University, told The Register, "The US Copyright Office has said it's [acceptable] if an artist uses AI to assist them in creating a work as long as there's some human creativity involved. If it's simply you typing text, and the AI generates a work, that pretty clearly is not subject to copyright protection under current law."

Midjourney's Terms of Service state "you own all Assets you create with the Services," but the company requires a copyright license from users to reproduce content created with the service – a necessary precaution to host users' images, even if it looks doubtful that those making Midjourney images simply through text input have any copyrights to convey or enforce.

That may not always be the case. Ochoa said that he believes Steven Thaler, who created "A Recent Entrance to Paradise," may want to challenge the Copyright Office's rejection of AI-based authorship in court, though that hasn't happened yet.

There are also potential copyright concerns arising from AI models trained on copyrighted material. "The question is whether or not it would be a fair use to use those images for training and AI," said Ochoa. "And I think the case for fair use in that context is fairly strong."

Additionally, there's potential liability for those who generate images that are substantially similar to existing copyrighted material. "If your training set isn't large enough, what the AI spits out might look an awful lot like what it ingested," Ochoa explained, noting that the issue then is whether that's a copyright violation. "Indirectly, I think it very likely could be."

As for potential legal risk to clients using Midjourney-generated assets, Ochoa said he thinks it's fairly low. If the training of an AI model infringed copyright, that was done before the client was involved, he explained. "So unless the client sponsored the creation of the AI in some way, I don't think [the client] would be liable for any infringement of the training set," he said. "And that's the strongest claim here. So I think clients are on pretty solid ground in using these images, assuming it was well done."

Holz acknowledges that the legal situation lacks clarity.

"At the moment, the law doesn't really have anything about this kind of thing," he said. "To my knowledge, every single large AI model is basically trained on stuff that's on the internet. And that's okay, right now. There are no laws specifically about that. Maybe in the future, there will be. But it's sort of a novel area, like the GPL was sort of a novel legal thing around programming code. And it took like 20 or 30 years for it to really become something that the legal system is starting to figure out."

Holz said he believes it's more important at the moment to understand how concerned parties feel about this technology. "We have a lot of artists who use our stuff, and we're constantly checking with them like, 'do you feel okay about this?'" he said.

Holz said if there's enough dissatisfaction with the status quo, it may be worth thinking about some sort of payment structure in the future for artists whose work goes into training models. But he observed that assessing the extent of contributions is difficult presently. "The challenge for anything like that right now is that it's not actually clear what is making the AI models work well," he said. "If I put a picture of a dog in there, how much does it actually help [the AI model] make dog pictures. It's not actually clear what parts of the data are actually giving [the model] what abilities."

 

 

Edited August 10, 2022 by flcc