where is that forum BTW? I found it through Google site search but I cannot find it here, this is why I rarely post on this forum

https://www.renderosity.com/forums/12484/mixed-medium

I cannot get to it from https://www.renderosity.com/mod/forumpro/ but yes did find another way since posting as long as I don't choose all general at the bottom, it and a few others are listed in the forum flyout

wendyvainity posted at 12:04 PM Wed, 19 October 2022 - #4447016

I cannot get to it from https://www.renderosity.com/mod/forumpro/ but yes did find another way since posting as long as I don't choose all general at the bottom, it and a few others are listed in the forum flyout

Hope that helps. 

yes, don't think I looked at that page in the last 10 years, I do recall it vaguely, had no idea I was missing out on so much forum! thankyou

You're welcome Wendy.  I haven't looked there in a long time, mostly because I chose the forums I always wanted to see, and then didn't have the need to add anymore.

I saw a warning someone posted on social media yesterday, telling people not to pay for commissioned art unless they show you sketches and works in progress. I guess people are selling AI created art as hand-drawn.

Not sure where that leaves us Poserers.

I saw a warning someone posted on social media yesterday, telling people not to pay for commissioned art unless they show you sketches and works in progress. I guess people are selling AI created art as hand-drawn.

Not sure where that leaves us Poserers.

I might be taking a bit of a break from AI Art by looks, update broke program I use, also got a rather ambiguous sitemail from one of the users of that forum about posting there. 

Genesis 9 has arrived and I have it working in Carrara and iClone 6,  Poser11 will be my next challenge (not buying 12, too many Python 2 scripts I use)

So much drama because of that AI !

you have to ask your self about : 

When making Poser art with purchased models is your creation intellectually yours ? Nor really as you are not the Intellectual owner of the 3d meshes used for your work ! You can't clame it as yours's, you sort of made fan art. Rules are the same for Poser, DS, AI etc. 

If you make a Outfit based on V4 Bones is that outfit yours ? Not really Intellectual rights still go to the V4 owner. This are actually your rules !  So what is really yours on the "derived Art" you make ? I Mean Derived as most you used in Poser, Daz, Ai is not Intellectually yours and never will be as you are not the real creator.

Making it simple, The signature is yours, weather a Dirivitive Artwork, a Fan Art, a Ai. The Print is yours if you sign it . But wat you used is Derivative Art nothing else. So Poser is in the same boat like Ai, not more rights, probably even less as AI that might have results that are more unique then the Derived stuff made in Poser DS in witch you have no Intellectual rights.

Moving this to the Mixed Medium forum since it is not Poser related.

Thank you Digitell

...............................................................................................................................................................................................

Sadly A.I. Art IS altering existing copyrighted artwork... sometimes you can see the artist's name and logo blurred out.

Done with Wombo Art, prompt "thomas kinkade", style "realistic"

Midjourney Ai

Giger meets Da Vinci

oh cool, I can share some of my stuff then too

this is a Deforum Stable Diffusion reinterpretation of my viral video from 12 years ago

originally rendered mostly in DAZ Studio painfully using 3Delight instead of Carrara or Poser 7 I otherwise used

I had only been doing 3D a year and was unprepared for the views it got

selfies are fun

Meow!

LastQuest posted at 5:36 AM Thu, 20 October 2022 - #4447093

So much drama because of that AI !

you have to ask your self about : 

When making Poser art with purchased models is your creation intellectually yours ? Nor really as you are not the Intellectual owner of the 3d meshes used for your work ! You can't clame it as yours's, you sort of made fan art. Rules are the same for Poser, DS, AI etc. 

I think if you legally acquired the meshes, then yes, it is yours.

There's precedent for this in the traditional art world. There have been court cases about it. If you're an artist, and create a painting or sculpture based on a photo, is it yours? It is if you paid the photographer for the rights to do so (or if it's in the public domain).

Andy Warhol got sued a lot for his use of other people's photographs. He (or his estate) just paid up if they were sued.

https://www.nvidia.com/en-us/studio/canvas/

(Free, but RTX required.)

No, of course it doesn't say "getty images" we did a very good job smudging that up Actually you could've clearly read "getty images" in the first steps as Wombo was "creating" this... but then Wombo "covered it up".

But is that because it threw up a training image by accident or is it imitating a watermark on something it only thinks ought to have one? And is there a way to check? 

Sorry, I'm not checking anything anymore... it's not stealing anything from me... yet! ... other than my time

besides my artwork is so terrible... no one wants to steal that LOL!

I don't think that's exactly the way it works. But a lot of people seem to think so. Clarification is needed.

I have to assume Google is involved somehow. I suppose different AI art programs have different methods.

People have taken to posting images on social media of AI-generated posters for movies. And the text is often similar, but not the same. For example, "The Handmaid's Tale" from Dall-e came out "The Mandal" or "The Thandal."  "The Two Towers" came out "Trill Rows."

The images were a decent match. Women in hoods, or veils for the former, two medieval towers for the later.

These AI programs are pretty tied into pop culture. They will produce celebrities, fictional characters, etc., pretty accurately. In a toon or hand-drawn looking style if you want. Putting in "Star Trek" can generate reasonable likenesses of Kirk and Spock.

glad online options are increasing 

I just got my electricity bill

DOUBLE since last quarter 

no more locally rendered Stable Diffusion animations for me (maybe a few images )

these are from DeepDream Generator

randym77 posted at 3:35 PM Thu, 20 October 2022 - #4447150

I have to assume Google is involved somehow. I suppose different AI art programs have different methods.

People have taken to posting images on social media of AI-generated posters for movies. And the text is often similar, but not the same. For example, "The Handmaid's Tale" from Dall-e came out "The Mandal" or "The Thandal."  "The Two Towers" came out "Trill Rows."

The images were a decent match. Women in hoods, or veils for the former, two medieval towers for the later.

These AI programs are pretty tied into pop culture. They will produce celebrities, fictional characters, etc., pretty accurately. In a toon or hand-drawn looking style if you want. Putting in "Star Trek" can generate reasonable likenesses of Kirk and Spock.

Traditional computer vision and image recognition models work the same way. They are taught truth and lie using 100% truth or 100% lie. This picture is an apple. So is this one and this one as well. Three pictures of an apple and all are labelled apple. 100% true. Then you give a picture of an orange labelled as an apple and tell the ai you are training that this is a lie. You have no confidence that your picture of an orange is actually an apple. 

Diffusion models are trained differently. You start with a picture of an apple and add a set amount of noise to your apple image and tell the ai that the apple image and the noisy apple image are the same thing. An apple. Then you add even more noise to the already noisy image and say this is an apple. Rinse and repeat a specific number of times and you are left with an image of just noise that the ai knows as apple.

Still with me? The ai just knows items as noise at this point in the process. Apple, banana, grape, orange. We teach these items to the ai along with a containers such as cups and bowls. To the ai it is just a pile of noise like the static you used to see on an old tv getting a signal with a pair of rabbit ears. Now the fun starts.

You type a text prompt that says you want to see a still life painting of a bowl of fruit. The ai then parses the prompt with CLIP (language training) and attempts to denoise images of apples, bowls, grapes, and the rest of your prompt items from a patch of noise the size of the image. Usually square as all the first step to training any type of ai is consistency of input and most current diffusion models are trained on 512x512 images. Now the ai just denoises whatever it has been trained upon so as to fit into the space. The result is as many different bowls of fruit as want.

The noise in the square is a random pattern based upon the seed value used to generate the image. That is why you get different bowls with different fruit. The ai is looking through the noise pattern to see if it has a bowl, banana, apple, or whatever; that it can denoise to fit the noise in the space. It has learned many different versions of bowl, apple, or whatever in the training so it has many noise patterns to choose from. The "steps" used in the generation of the image are how much denoising happens and thus the juxtaposition of the final elements of your image.

There are other rules involved in the placing of the objects in the scene. There is an aesthetics as part of the learning. That is a big part of the training image classification system and has led to some training bias in the diffusion models. Some things are also specifically sketchy in outputs such as text. Most diffusion setups are not designed to render legible text on purpose.Thus fictional movie posters that almost seem readable.

The image scrapes done for training are not specific to Google. Not by a long shot. The Laion 5B data set has been released to the public. This is the training set for "Stable Diffusion". Thats almost 6 billion pairs of image and text and a search base of 1.6 trillion data sets. Google's is considerably smaller.

The training is not tied to pop culture but to popularity (sure are a lot of apple images here to train on) and aesthetics biases (I like green apples better than red apples.)

Apparently, a lot of artists are upset because their art has been scraped by these programs. I guess if you're prominent enough, the programs can produce art "in your style."

There's a lot of talk among artists about what to do about this. There's some who are suggesting you post your work with misleading tags, to screw up the algorithms. Post body horror or graphic porn with tags like "beautiful forest" or "autumn sunset." Or tag your landscape painting with "big boobs" or "sexy babe."

I imagine human viewers would find that pretty annoying.

Mis-tagging would also bite them in the backside by making it harder for their own fans to find their work. And what school or library or workplace would allow access to Big Name Artist Joe Whomever's website once it gets known for having "big boobs" or "sexy babe" or other NSWF tagged images? I do agree that anyone who does not want their work used in AI training should be able to say no and have it removed, or compensated/licensed if they agree, but poisoning the well does no one any good, not even themselves.

I took some photographs in and around my house and fed them to the AI

I have to assume Google is involved somehow. I suppose different AI art programs have different methods.

No, they don't! Google is their bread. If someone is going to end the AI art, it's going to be Google. Then the other search engines will follow.

People are posting comments on art, along the lines of "What do you call this style?"

They're looking for prompts to feed into AI generators to mimic the artist's style.

the AI gave me a sexy Succubus using an old photo of me

So there's an AI-generated art forum now.

FWIW...at DeviantArt, they are automatically opting works into "third party AI datasets."

You can opt out, but as I understand it, it must be done individually for each artwork.

Does Rosity have a policy on this? Just curious...

Thanks for letting us know about Deviant art. I don't know if there is a policy here.

I was on Deviant art, opting out my images and the site crashed with some overloaded error. I can't help but wonder if there are too many who want to opt-out there.

I posted this in my gallery earlier this summer. I like using Midjourney to explore how the AI might interpret certain ideas. I asked the AI to illustrate the story of Eleanor Rigby and Father MacKenzie, from the classic Beatles song, by feeding it bits of the relevant lyrics. I thought I should share a collage of some of the better interpretations illustrating the story. Hope you like it.

"Eleanor Rigby" (lyrics by Paul McCartney and John Lennon, released in 1966)

--------------------------------------------------------------------------------------------------------------

Ah, look at all the lonely people

Eleanor Rigby

Picks up the rice in the church where a wedding has been

Lives in a dream

Waits at the window

Wearing the face that she keeps in a jar by the door

Who is it for?

All the lonely people

Where do they all come from?

All the lonely people

Where do they all belong?

Father McKenzie

Writing the words of a sermon that no one will hear

No one comes near

Look at him working

Darning his socks in the night when there's nobody there

What does he care?

All the lonely people

Where do they all come from?

All the lonely people

Where do they all belong?

Ah, look at all the lonely people

Ah, look at all the lonely people

Eleanor Rigby

Died in the church and was buried along with her name

Nobody came

Father McKenzie

Wiping the dirt from his hands as he walks from the grave

No one was saved

All the lonely people (ah, look at all the lonely people)

Where do they all come from?

All the lonely people (ah, look at all the lonely people)

Where do they all belong?

Well done! You can often get really good results with song lyrics or poetry. I've run some of my own original work thru SD, not posted any of it yet because not finished the project  but very encouraging so far. Would never have thought of using Daz or Poser for it because too time consuming and complicated and sometimes doesn't translate well into 3D but I've found it well suited to AI art.

my cards for this year taken care of

f

feel free to download and use as you wish

is ai art, IMO public domain CC0

the Santa images are both weird and awesome!

Here's a cat for wendy

https://www.youtube.com/watch?v=R0Duxv2WFnI

cute

And someone found medical photos she thought were private, taken by her doctor, in an AI dataset.

https://arstechnica.com/information-technology/2022/09/artist-finds-private-medical-record-photos-in-popular-ai-training-data-set/

DAZ Filament animation driven VOC Deforum Stable Diffusion  ai video

postwork in Capcut video maker

various post productions applied

My Heritage has ai too
those were generated from photos of me

latest selfie, submitted 25 of them

i need some info.. i'm pretty new at this, and i only use FREE/NO SUBSCRIPTION + NO LOGIN sites, like night café. i'm happy with 5 credits a day...

now, nightcafé made for me (with me?? lol) this awesome portrait, from head to upper torso or kinda waist. so far, so perfect. BUT it's at an angle, maybe 17°, and i think it's too much. i tried to rotate it in gimp, but then i lose the top of the head. i found no rotating or anything in night café, only enhancing, and i'm not sure about evolving, i don't want any other image, just this one with enough deco around the portrait so i can rotate i.e. crop it with the whole head intact.

but i know about outpainting. this is imo pretty much the only solution. but i can't find a free no login site to do this - or i haven't noticed the right places to click or sth..

anyone?

wendyvainity posted at 2:49 PM Fri, 2 December 2022 - #4450799

DAZ Filament animation driven VOC Deforum Stable Diffusion  ai video

postwork in Capcut video maker

i'm not smart or up-to-date or maybe interested in tech enough to get how you did it (DAZ Filament animation driven VOC Deforum Stable Diffusion  ai video postwork in Capcut video maker...whaaaaat? lol) - but keep at it! this deserves to be published as a meditation animation, or a game...

Midjourney Ai

Giger meets Da Vinci

OpenAI Dall-E2 does out painting 

so does Stable Diffusion but I haven't had much success using it with the NMKD GUI version on my PC, Dall-E2 worked well, I only use free apps too now