Daz 3D is part of 
Connect
DAZ Productions, Inc.
7533 S Center View Ct #4664
West Jordan, UT 84084
Licensing Agreement | Terms of Service | Privacy Policy | EULA
© 2025 Daz Productions Inc. All Rights Reserved.
Comments
Nice (I suspect she's making a sultry expression under that helmet though*)
*J/K obviously, but I mention it in case it's not obvious.
LOL
(Now, just a quick note before I go on. I'm pretty sure you are joking due to the preponderance of the style of images in question, so the rest of my response is more at those who might not understand that AI really does do more than that.)
I can definitely see where you are coming from since that vast majority of the AI images you see would seem to support that idea. However, it's just like for someone who has never gotten into really using DS (or Poser) it would seem that it is only good for producing NVIATWAS, and in the early years it was really bad quality NVIATWAS!! (Note for those who haven't been around that long, this stands for Naked Vicky In A Tomb With A Sword, this seemed to be the most prominent art form in the galleries back in the Poser 3/4 days.)
Judging what a product can produce simply by the digital "art" most prominently posted on line runs the risk of thinking it is only capable of that art form, when it really isn't limited to only that. So, to counter your tongue in cheek argument that you need to put in extra effort to not get the AI equivalent to NVIATWAS, I will provide the following example.
Using this simple prompt "redhead female in a Victorian gown standing in the foyer of a Victorian mansion" resulted in the image posed below (it was the first image produced using the Krita AI plugin for Krita). I'm not a big proponent of AI image generation, but I am investigating it to better understand it potential uses and capabilities. I'm also interested in how it might be used in conjunction with DS.
Now, just because no discussion should be engaged without invoking kitties. this second image is from Krita AI using the prompt "cute siberian gray kitty in a field of flowers, sitting, close up".
I'm constantly amazed at what some of the people who use/incorporate AI image generation are able to produce. With that in mind, here are some links to some images that definitely "break the mold" (if anyone is interested).
https://civitai.green/images/50629679
https://civitai.green/images/50380475
https://civitai.green/images/50623217
https://www.deviantart.com/editpix2/art/Caitax-1144923026
https://www.daz3d.com/gallery#gallery=aipartial&sort=popular&page=1&image=1357193
https://www.daz3d.com/gallery#gallery=aipartial&sort=popular&page=1&image=1357040
I'm glad I wasn't drinking coffee when I read this!
The prompts of the first three are nice short-stories.. but somehow the pictures don't really manage to show fully what they describe. Looks a bit like a Hollywood movie version of a good book to me...
And about those scantily dressed ladies that show up, sometimes (often?) without being invited by the prompt: seems it depends what AI gets used and how it had been trained, right? A wild AI, feeding on all the interwebz does offer, without being restricted somehow, might be produce other content than one that got served a nice menu of Art.
YES!
That's a great analogy as often the image generated isn't quite the same (as one might interpret) as the text, and often a bit of an abridged version of the prompt. Though sometimes it can go the other way.
Yes, the AI model and checkpoint being used can significantly alter the output of the images (as I understand it, a checkpoint is sort of an extension of the base model with additional training data to influence the base ai model to generate images of a certain style/content better). AI image generation can also be influenced by a Lora. A Lora is sort of an external add on to the ai model that is generated using smaller more focused image sets to guide the ai generation to create more specific image elements. For example, if you wanted to consistently create a specific character in your images, you could create a Lora that would focus on that character and different angles/distances and environments, then the ai image generator will produce images using this character when it is referenced in the prompt.
I'm sure commercial sites will train their models to produce the images their customers want to see/create, and no doubt add a lot more training data than found in a base model like SDXL. There are also free checkpoints based on free models like the SDXL model (open source model) that extend it, and can be used to generate specific types of content easier (at least that is how I understand it).
Ah yes. Daz Studio-known its excessive usage of spicy imagery. As bad of a rap it gets for that, I think any platform that can create visual media has adult content as a huge part of its use. After all, it's the best money maker (unfortunately).
I actually find it hilarious that the scantily ladies can just appear in prompts even unrelated to it it's like..."So here's that castle you ordered and...oh how'd SHE get in there? Well, anyway, image is done!"
What a time to be alive.
^This.
I imagine Krita AI is geared more towards the artistic kind of images that Krita is more famous for (at least the images I see advertised as 'made with Krita', which is an ace programme by itself).
Certain free online ai models may have a propensity to throw out the NVIATWAS style. The more control you have over the checkpoints / Lora, the more you'll get the style of thing you're looking for.
I've been unable to get any of the ones I've tried to follow a prompt closely enough to meet what's in my head, but I'm sure there are people who can.
There's someone on DeviantArt (damnmad660) who displays quite impressive results from enhancing the photorealism of his renders with AI. So I thought I'd give it a shot as well. Photorealism always was and is the aim of my renders. I think it depends on many variables. What are you trying to achieve, what the quality of the source file is, what model checkpoints and prompts you are using and so on.
So I took an admittedly older render of mine and dabbled around with different settings in ComfyUI. After about two hours I had a kind of acceptable result which I put into Photoshop and added it as a layer with 50% opacity on my original file. Results below.
Truth to be told I still prefer the original render. Still I wouldn't bet that I'll come to the same conclusion by mid 2026 or so.
One of my favorite dumb AI tricks is still just converting a render and then going back through and in painting section by section to up the detail and quality. I imagine it scratches the same itch as those people with coloring book apps on their phones where they're just tapping predefined colors into predefined spaces.
So I decided to try the AI on clip art. In these images, the original is on the left and AI version is on the right. They exhibit the typical issues with hands and feet, which seem to be more prevalent if the original image doesn't have very realistic hands and feet. And it doesn't allow a character to keep a surprised look on her face. However, some of the other details seemed surprisingly good to me.
I love how AI does that. I recently have been experimenting on NightCafe.Studio with that technique to copy poses easily.
...and this is what concerns me about moving to Win 11. I don't need an AI running around in my system trying change and modify operations "it" thinks need to be changed. Anything that I feel "interferes" with how I set up and use my system is an immediate candidate to be disabled or better yet, uninstalled (if the latter is possible even if it requires editing the registry
Lately I've pretty much moved to using my old copy of Word to compose commentaries and news items for posting online as I have full control over the spell/grammar checking parameters and dictionaries (I have actually built up a fairly extensive custom dictionaries over time).. I have noticed that Google's spell check is apparently using AI as lately it it has been giving some of the most ridiculous, if not outlandish suggestions for what are often simple typos like transposing two letters. In some cases the suggestions have absolutely no relation to the word I intended to use. A short while back this wasn't the case.
Yeah, AI has a very long way to go in my book even for such routine tasks as described above.
@ Laurita, I'm only getting the "broken image" icons. Refreshed the page but they still show up.
Finally got a build of Hunyuan 3D running on my PC with Pinokio
taks about 5mins to generate a mesh
Not bad time for the generation.
I have used the online one and it takes usually around 100 seconds to complete.
Who is running out of Data??
I see this claim often but never any link to
a legit generative AI company publicly stating they are “running out of Data”
It is as if people seem to think that
generative AI depends soley on individual Artists providing it with new unique works to train from
and nothing else.
Somehow ignoring the millions of hours of
of new news footage put online 24 hours a day.
old cartoons ,movies ,TV shows,Book illustrations
youtube videos in every style & genre
animated real life, streamed video game footage, Netflix movie review footage etc etc
There is no finite amount of visual data to
“run out of “
The evolution of this thread has been fascinated to read.
When I first posed the question of the effect of AI on Daz, when one took into account that the majority of people using DAZ weren't necessarily using it for "art", or commercial purposes, but to realize images the individual wanted to see and that AI could in time scratch that itch much faster ( and cheaply ) than the amount of time it took to learn how to adequately use a program that the sellers never even bothered to make an all comprehensive manual for, I was basically told that it was a silly question and DAZ was fine as it was.
Seems that that opinion has shifted as has the original attitudes on AI in general. While you still hear the knee-jerk response on "how AI isn't 'art", or how AI looks terrible, the people out there willing to still die on that hill are looking rather lonely and silly. AI at this stage looks so good, artists that are actually masters of their craft are constantly having their work accused of being AI generated because people can't believe that there are actually artists out there that are that good anymore. This was always going to be the end result. The average person who wants a nice looking picture to frame on his wall doesn't really care who ( or what ) made it. The average guy who wants to peruse beautiful women on instagram doesn't care if the woman is real or not -- he's never going to actually interact with her one way or the other plus a virtual model never gets old, and will never say something stupid or insulting. Plus who cares if you're objectifying a pixel; win win.
AI is a tool, it's not a threat to any artist that uses art for self expression, anymore than a digital tablet is a threat to an artist that prefers canvas and brush. That is if you're an independent artist, or hobbyist, but as for commericial artists, than I direct you to the tagline for the film The Fly. As for does this spell the end for Daz; I no longer think so as they've belatedly made the software compatible with other software like Blender, and incorporating AI of their own. As long as no one is forced to use tools they'd rather not, or like Microsoft Windows, making the program uncoompatible with user current hardware with updates they should be fine.
The "art" in the case of AI is finding the right command line to achieve the wanted result.
Based on that, each and every person doing programming on a computer is an artist.
I've spent about a week putzing around with this one. I wanted something to print on a tshirt for myself, spurred on by anxiety around the current political climate. It's inspired by Mitch Gerads cover for Mr. Miracle #9, but with the second kid added in. Not sure if I want to keep fiddling with it to try to get the kids to have more heavy linework or to have him have less. Honestly, I kind of think the disparity works given the nature of the material.
"Based on that, each and every person doing..."
A judgment about a work decides (subjectively) whether or not something is a piece of art- or if someone is an artist. It is not determined by their tools or method.
Can we please avoid the who, or who's not considered an "artist" comments?
Might be interesting to get an AI's opinion about the definition of it, wouldn't it?
You can talk about AI all you want and the issue(s) it presents, which I believe was the opening topic of the thread. I'm not 100% on that, but there is no need to dictate who is or isn't an artist. Most of the participants in this thread have been here long enough to know the direction those conversations go and the inevitable closing of the thread, because it gets out of control and our warnings are ignored. Declaring who or what is or isn't an artist can bring about various violations of the TOS, depending on the context. We would like to avoid that, if humanly possible, so the thread could go on with a constructive conversation where we don't have to intercede.
A few weeks back, someone shared this "AI or Human art Turing test" on one of the Discords I'm on, challenging people to tell what was or wasn't AI.
And while I will concede that the test is difficult, reading their methodology afterwards made it clear the whole thing was fundamentally flawed. If you read their methodology, all the entries were deliberately curated, removing anything that was obviously flawed or in a rather AI-ish style, and disallowing human created art doing things that AI finds difficult (like wrestling poses). This is now not a test of human vs AI, but of the test creator's curation. The test results are useless in the end as an AI vs human test, but the fact the test even needed that methodology is pretty damning.
That's the thing. AI can do some things well, such as pretty portraits, but when you start asking it to do things outside of its dataset, it just starts to fail completely.
I've mucked with AI a fair bit myself, but it's limited and frequently frustrating if you want to achieve anything specific. Most times I try for anything other than the most generic and boring pin-up portraits, I get fed up and go back to DS to just do it there.
If AI were genuinely able to do whatever, then I should, without using these images as an input in any way (e.g. img2img, Controlnet, training a new model off my work, etc), be able to remake them from scratch using AI tools and an image editor.
Stylistic differences would be fine and I'm not worried about the exact details of what's in the background (although it should retain the same feel), but other than that, if I wanted something close? Basically no chance.
AI might, if you generate many copies and cherry pick the best, be able to create something of the same quality as a human artist, but it cannot explore new ideas, only rehash old ones.
This is now not a test of human vs AI, but of the test creator's curation.
but it cannot explore new ideas, only rehash old ones.
So you pick a thing AI is not good at to decide how good it is.
If AI were genuinely able to do whatever, then I should, without using these images ... training a new model off my work
There is an incredible irony here as you've demonstrated exactly how AI works with the example of your image and *most likely* how you made it.
You opened Daz Studio and typed Centaur in you search window (There's your prompt)
Your library sorted Everything Centaur-related (Your library is like the AI data set, you know, the stuff it can use to satisfy your query)
You picked the most right thing you're looking for and added it to your scene. (1st generation of AI output)
You then adjusted all the details, once again, looking at all the possible choices in your *limited* library/dataset. (you can't render stuff you don't have in Daz Studio).
And then the artsy-judge part kicks in and you decide what works and what doesn't and what could be better, swap out the mansion for a better one. Change the sky...move this left and move this right....
angle of the camera...color...(basically re-rolling or inpainting).
-------------------------
The kicker is, no HUMAN could satisfy your "test" either. If you told someone (a competent artist with THE SAME LIBRARY as you) what you wanted, it would take endless pages of description to get close to that picture.
Which is how AI works right now. More precision requires more instruction (with the correct syntax). In other words, your vision needs to be communicated more clearly.
And worse, those pictures would't pass for human-done under scrutiny.
Someone would point out the shadow of the cat on the wall and say it's an AI error.
The two instances of text you can't read (car grill and blue banner)- a human artist would NEVER put text in an image you can't read. Only AI scrambles lettering.
There's a character holding a white thing in the background- and just like judging AI, once I don't know what it is- immediately I assume it's AI slop.
Same with the 'black arrow' coming out the trunk. Only because I know the assets and know Daz, I know it's a tail from the character. But! If I did not know your dataset, I'd assume you typed "pointing down" somewhere and the AI got confused.
-----------------------
If Terminators marched down my street, wiping out humanity- I would quickly realize, AI doesn't need to pass a test designed to keep me at the top of the cognitive food chain to end it all.
@Griffin Avid
Well stated
Uh... yeah?
I mean, it would be one thing if I were saying something like "AI art is terrible, it can't drive my car for me", but when I'm saying "it can't depict the novel and unique"... that's something at the very essence of what art is - that is a fair thing to evaluate a field of art by.
Your entire narrative here is predicated on the false assumption that people "can't render stuff [they] don't have in Daz Studio".
Which content store do you think I got horse leggings from? Which store sells the tools to put short shorts on a centaur?
Nowhere, because I did that myself.
If I want to get involved in a silly social media trend based around some cheap AliExpress bodysuit?
I can and will make that happen.
How about a different field? I sculpt wargaming miniatures from scratch.
Another? Well, while I'll absolutely admit I'm less good at it and haven't much done it in a while, I can also draw to an extent - here are two old concepts I was playing around with for a mech pilot character for an RP:
(Had two different ideas, one revolving around a character with a rougher look and the data plugs all over her body, and another where the data cables in the style of dreadlocks).
Do I always create from scratch? No. Is my ability to do so the best? No, absolutely not.
But that absolutely does not mean that I don't or can't.
I strongly disagree they're alike. Re-rolling and inpainting are a one armed bandit, hoping that this time it does what you want.
Whereas the editing process in DS is extremely direct. If I think "I want that character a bit further to the left"... I move them a bit further to the left. I do it, it happens.
Even the somewhat unpredictable process of a complicated dForce timeline simulation is still robustly refineable. The changes I make are iteratively driving me forwards.
Comparing AI generation to that is like saying bogosort is a good sorting algorithm.
(Bogosort - 1: Check if list is in order. 2: If not, shuffle entire list. 3: Go to step one.)
Both are legible and logical text. One reads "nitro" in a graffiti font, and the other reads "Eternal Storm LARP in a gothic font. You might not be able to read them (they *do* link to the full size versions), but they are not gibberish.
... you have got to be kidding.
A character with red skin, horns and hooves, and you're painting a reasonable interpretation as of the "arrow" connected to the base of their spine as the AI getting confused?? Spade tailed devils are a long established element of mythology/folklore.
(Also, you're mistaken - the assets/character do not look like that. The black tip is my own edit.)
~~~~~
If your entire argument for "some people will mistake your work for AI" is that people can be wrong about what they think they see, then you need a better argument.
@Matt_Castle
Well stated!