I've been working with poser ever since version 4. I now use Poser 13 and I'm so utterly underwhelmed with Poser 14, that I have no intention of upgrading.

As long as I can remember I wanted to recreate pictures that are in my head. I can draw pretty well, but found it way too complicated/time consuming. So discovering Poser 4 in 2000 was something like a 'godsend'. 

25 years on we're in middle of the AI hype. I'm appalled to see the outpour of mindless AI images drowning out creations that are worthwhile. But at the same time I’m intrigued by its possibilities.

I’ve experimented a lot with AI over the last year. I want to be in control and be able to tinker with the setup, so I started using ComfyUI locally on my laptop. Using this node based open source system was a steep learning curve. And besides learning the technical ins and outs, the most frustrating part is the randomness of AI in going from prompt and latent image to end result.

So my train of thought was: why not try to combine both worlds: use the full control over the scene by creating in Poser and then render and enhance in AI.

After a lot of trail and error I managed to put a ComfyUI workflow together that transforms a very crude Poser render into the picture I have in my head.

This is what the result looks like: 

Being able to transform an original crude Poser render I made into an image that looks almost real and maintains every detail from the original up to the intricate pattern of the fabric, to me was a ‘eureka moment’.

There is still a lot of room for improvement. AI is best at rendering portraits and does a better job at female faces than at male faces (wonder why ;-)). Rendering full body poses or a crowded scene with a lot of props and details in AI, leads to hallucination and loss of detail. If the subject is not looking straight into the camera, eyes tend to go in all directions, except for that in the source image, even with detailed prompting. And often I need to combine 2 or 3 AI renders to create the final image. 

Also I notice that some of my fans on Patreon and other platforms I post on, express resistance to the use of AI.

But in my honest opinion: if Poser (or any other 3D rendering platform for that matter) wants to survive, they need to look into ways to incorporate the power of AI into their products, just like for instance Adobe does in Photoshop.

What do you think?

Cheers,

Richard

The Poser web version has some AI built into it, but the scale was off. But I think those problems can be fixed. So, there's already some AI and Poser out there. 

Some of the big AI issues are: too resource intensive, they all look the same, and none of the court cases on copyright infringement have been resolved yet (on the graphics side of thing) - so the future of AI is uncertain. Then there's talk of the AI bubble bursting like the dotcom bubble did.

In the meantime, I can create graphics for games in Poser much faster than using anything else and is mainly what I've been using Poser for. At least I know I can safely use the renders and not face copyright issues down the line.

Richard,

PoserPlay (https://play.posersoftware.com) has been our testing ground for precisely the type of integration you describe.
It has a feature called ClothFX that by default make clothing drape convincingly, but you can also do lighting correction, etc with a prompt.
It's reasonable to expect this type of integration into Poser desktop over time.  There's also a forum here for PoserPlay.

-Tim

The interesting question is, what's missing to create the second image?

Shaders, lighting, and time.

Personally, the lighting and shaders change so often, and the information given in the threads is complicated for me, as someone who doesn't speak English. hborre was talking about Blackbody today; I didn't understand how it worked, but I knew he'd mentioned it before. Even after searching, I know it will take me a long time to master all of this. Poser has become a specialist's domain, and I was hoping that Poser 14 would resolve the cycle issue.

La question intéressante, c'est, qu'est-ce qu'il manque à poser pour réaliser la deuxième image?

Shaders, lumière, et du temps

Personnellement la lumière et les shaders  changent tellement souvent et les informations données dans les fils moi qui ne parle pas anglais compliqués à suivre

hborre parlait aujourd'hui de Blackbody, je ne comprenait pas comment ça marchait mais je savais qu'il en avait parler avant, mais même après une recherche je sais qu'il me faudra beaucoup de temps pour maîtriser tout cela, Poser est de venu une affaire de spécialistes et j’espérai avec Poser 14 la question de cycle bouclée.

Congratulations on learning ComfyUI. It's worth it.

There are several ways to constrain the annoying randomness. It sounds like you need to learn (if your laptop can take it) about ComfyUI's Controlnets (Canny etc) and perhaps also Liveportrait (change eye gaze direction).  

Poser can output good line-art that can be used with a Controlnet to constrain the AI generation, so that it more closely matches what you have in Poser. Liveportrait in Comfy means you no longer have to fuss about eye gaze direction in Poser.

For 2026... Poser is Python, and so is ComfyUI, and they're both very mature ecosystems in what they can do. They can theoretically talk to each other in a stable way. Such as auto rendering a set of named files, that then get picked up and auto-slotted into a ComfyUI workflow and run. With the result returned back to a panel inside the Poser UI.

What AI can't yet do just from a prompt is complex ensemble action scenes, with the sort of precision that requires. But, as you've discovered, it can also do relatively subtle Img2Img makeovers for a single dressed figure. It can also act more like a Photoshop filter, using what are called 'Edit' models such as Flux Kontext. These are dedicated to image editing and filtering rather than to image generation. 

Congratulations on learning ComfyUI. It's worth it.

Thanks @HartyBart. I've experimented with controlnet and depthmaps, with mixed results. When 2 or more characters are involved that are interacting with each other, it often messes up limbs.

The workflow I’ve now put together uses Qwen-image-edit-2509 with 2 Lora’s added. This gives good results, even on more complicated scenes consisting of more characters (often in NSFW situations ;-)), but the next stage truly makes the difference: I added a ‘Resample banding fix’ node that refers back to the original input image and prompt. This irons out a lot of artifacts and small distortions that were generated in the first stage and gives a crisp image. After that I added a VAE-decoder that upscales 2x while decoding. This speeds up the upscale process considerably!!

I will try certainly try the LifePortrait in my workflow!

This is what I've put together so far borrowing from sereval seperate workflows and adding a bit of my own.

Yeah, the make "art button" has become reality.
Don't take credit for this eye candy result.
It hasn't been made by you. AI did it for you.

Trying out some Poser erotic logos but Ai still is messing up these hands !

Ai Enhanced Poser render, No text, mix of 3 poser renders

Yeah, the make "art button" has become reality.
Don't take credit for this eye candy result.
It hasn't been made by you. AI did it for you.

Yes I agree there is a lot of crap mindless AI stuff flooding the internet made with a ‘Make art’ button.

But I think that doesn't mean using AI to create something isn't art by definition. I also didn't write the code for the Cycles Render Engine used in Poser. I didn't create Victoria 4 I still use for most of my work. And I bought most props, textures and clothing I use on Renderosity, DAZ and other web shops. 

What I did do over the last 25 years is make an effort to learn and understand how Poser works and put all these things together to create something new and mine. 

With AI it's the same. It’s a tool. And I am trying to make an effort to actually understand how this stuff works, and use that knowledge to configure it in a way I have full control over the result, so I can put something together that is uniquely mine. And that’s why I’m looking for ways to integrate my knowledge of Poser and try to configure Comfy UI to use it as an advanced render engine.

So yes I intend to take credit for that effort and the result!

If you beg to differ, please point to the ‘Make art’ button in the workflow above.

Nevertrumper posted at 8:43 AM Mon, 22 December 2025 - #4502475

Yeah, the make "art button" has become reality.
Don't take credit for this eye candy result.
It hasn't been made by you. AI did it for you.

Yes I agree there is a lot of crap mindless AI stuff flooding the internet made with a ‘Make art’ button.

But I think that doesn't mean using AI to create something isn't art by definition. I also didn't write the code for the Cycles Render Engine used in Poser. I didn't create Victoria 4 I still use for most of my work. And I bought most props, textures and clothing I use on Renderosity, DAZ and other web shops. 

We could agree, that photgraphers are artists too.
They didn't create their motives. They find them, they arrange them they set the lights on them.Poser, DAZ or any other content based 3d environment just works like looking through a photographer's lense.
Generative AI is different.

But when you blend Poser and AI together there still is a 3D environment to start out with. In case of the image I posted: I posed the figure, constructed the dress from 6 different clothing props including a dynamic cape I draped in the cloth room (now missing in Poser 14) to form the flowing train of the dress, added the bows, gave the skirt texture, created her expression,  positioned her arms on the dress, choose a camera angle and frame. All that falls into your definition of art and something I can take credit for. True?

Then I made a rough render, build an AI workflow, wrote a prompt, fine-tuned that prompt over and over again to get the result I was looking for, and made the final image using elements of 2 AI renders and doing touch ups and last lighting corrections using a photo editor.

And that AI phase suddenly degrades all the earlier work to just hitting an 'art button'?

I do agree there are many shades of grey here. But creating the result I posted actually took me more time than setting up the lighting in Poser and render it in Superfly. 

There is indeed a grey zone here.
You have created the character, you have created the pose, but you did not create the light, not the color grading and not the eye popping- eye candy textures.
There is too much generative AI work in this to my taste.
I am not entierely against the use of AI as a tool, if AI just calculated light rays better, understood the layers of skin and produced better accurate realistc skin shader effect.
I am not against something like AI denoising or upscaling. Maybe you want to make an animation and AI could help you with collisions or preventing bodyparts intersecting with each other, by marking scene elements as solid.
Those are AI TOOLS.
As soon as AI makes "artistic decisions" for you, like this color grading, your art work is no longer YOUR artwork.
Only that image on the left is all yours.

AI is yet another tool in the box. The great thing about the AI tool is that it can remove differences in style of components in a scene. I posted this image in one of the forums before:   

It is the Poser 2  casual woman dancing next to LaFemme2. You see that the obvious difference in detail etc. is gone. This means that old content has new use. 

> "old content has new use". 

An excellent point. 

And before anyone points out the wonky thumbs/hands, I'll note that with Ken's Openpose script for Poser (available on Renderosity) and an Openpose Controlnet node, you might also get the hands looking good on the above AI image generation. His script does Openpose with hands included.

When using AI, you decide what to keep and what to discard—it’s entirely the artist’s choice. I mainly use it to generate reference materials, which is also my primary use for tools like Poser.

In the past, I used to collect images from Google or reference books to inspire my drawings and paintings, manually creating something new from a variety of sources. With AI, I can now generate the references I need. Whether this is “art” is a big philosophical question, but for me, it’s simply another tool. I’m not a professional, and I don’t claim to be , but even my painting teacher was amazed when I brought in AI-generated images that perfectly matched my artistic previous works.

When using AI, you decide what to keep and what to discard—it’s entirely the artist’s choice. I mainly use it to generate reference materials, which is also my primary use for tools like Poser.

In the past, I used to collect images from Google or reference books to inspire my drawings and paintings, manually creating something new from a variety of sources. With AI, I can now generate the references I need. Whether this is “art” is a big philosophical question, but for me, it’s simply another tool. I’m not a professional, and I don’t claim to be , but even my painting teacher was amazed when I brought in AI-generated images that perfectly matched my artistic previous works.

AI is yet another tool in the box. The great thing about the AI tool is that it can remove differences in style of components in a scene. I posted this image in one of the forums before:   

It is the Poser 2  casual woman dancing next to LaFemme2. You see that the obvious difference in detail etc. is gone. This means that old content has new use. 

Still working a little on a erotic Poser logo enhancing Images with AI, not using Prompt or text.

Slowly teaching a model .... It is getting better but still some things to be fixed, the character is quiet stable. It takes day's to teach a model to the results you wish having. 

VirtualBite posted at 7:46 AM Sun, 21 December 2025 - #2997111

If you wanna do AI stuff, then do AI stuff. What's that to do with Poser?... or Blender, or DaVinci Resolve or a hundreds of other creation tools that dont do AI image generation?
Completely different tools with different purposes.  But like any tools, you make your own workflow for your desired results (as you already are).  That's nothing to do with Poser being "obsolete" or not.

I heard the term "slop" for AI produced content.
Can we call producers of AI content "sloppers" then?

I sure do understand the request and need for AI as most people are not artists, sculptors, or 3d modelers. We could also interpretate the situation like one who is just using prefabricated models to pose, but never in a lifetime would be able to get one done. That is what poser per se is, a Pose program for prefabricated models. It can be compared like using a generative AI as the user will not really build up he's own designs and not own the prefabricated model, just using what is being offered. A sort of evolution with Generative Ai in a similar direction for the ones who do not have the sills to sculpt or rig for Poser/Ds.

I can't list the amount of tools and programs on one hand used to make a model poser/ds ready, just for the ones who like to use them, but in poser they are just prefabricated and set together into a scene. So I do not see a big difference between using Poser/Ds or generative Ai as both types are setting up given products into a scene. 

We could see it like this, the creative part are the ones who have the skills making the tools, or the models to be used in a posing program, others list there wish for what they want to be done. In Poser they say I want this outfit, this character, this Environment, this features, making it a commission, In AI they will ask for it in a same way to get the art they wish for, no big differences as someone else or something else made it for them after a request.  if it was not a request then we could interprete it " I had no Idea that I wanted it, but I take it because I like it " This in both Poser/Ds and AI. Either way the original artwork has been prior premade for the user that just likes to Pose the scene and does not have the skill building it from scratch. 

Now that we might understand that both AI and Poser/Ds are working in a similar way by using premade models, what would be wrong about using AI to make the Posed Prefabricated models look a little better after posing them in Poser/Ds. As there is actually no big differences between both posing applications.

Except Poser isn't trawling other artists' works to copy them without permission.

lsauvage posted at 6:57 AM Sun, 28 December 2025 - #4502603

When using AI, you decide what to keep and what to discard—it’s entirely the artist’s choice. I mainly use it to generate reference materials, which is also my primary use for tools like Poser.

Your friend A. I. makes a imagages for you, that you ordered, and you pick and choose, which one to keep?
And then you claim, this is YOUR art work?
Hell NO!

Again, I think it's not as black and white as this. In Poser most works take at least 50 renders (often many more!) to get near the end result I want. I go back endlessly, tweaking poses, lighting and render setting, figuring out why the hell Poser messed up details, I thought I got right. In the end my final image is almost always a mesh up of several renders and some post production. With AI, thought the technique is different, the prosess is the same. I work endlessly changing settings and prompts to get a result that is clossest to what's in my head. When I'm close I fix the seed and vary around that, tweak the prompt some more, sometimes change details in the input image and finaly ending up with two or three renders I put together for the final image. The lighting, textures, etc. are not totaly random: There is an input image, a prompt that gets finetuned over and over again and there is skill and patience involved to get the result I have in my head, not what AI presented me in the first go, just like with Rendering in Poser. 

I found this article interesting in this respect: https://shotkit.com/are-ai-generated-images-art/

---

AI and the Click Delusion

Some would argue that because AI generations can be created from a basic text prompt and a few clicks, it cannot be considered art. And I would agree: after all, not every photograph clicked is art. 

Anyone who has used AI to create images knows it is no mean feat to coax it into creating a replica of the image you envision. [my emphasis]

When you click the generate button, AI might generate an interesting visual, but it usually won’t look anything like the visual you had in mind. 

AI has its limitations. To create the picture you wish takes a lot more than entering one line of text and the click of a generate button.

The majority of artists using AI to generate work don’t use the one-click fix to create their art.

They have a practice that is time-consuming and complex, which allows them to create the specific style and visuals they envision.

(...) 

What divides an artist from a painter? The artist has a vision, a message, while the painter is satisfied with the process of painting and has no vision.

In a similar way, anyone can prompt AI to create appealing images, but are they like the painter… splashing colors on a canvas with no clear intent?

Interestingly, if we look back on history, photography was once considered a one-click wonder, incapable of producing art.

Considering the mechanical nature of the photography process, how did photography come to be considered art?

The quick answer is that society began to realise the depth of expertise required to take a good photo.

Art institutions began to appreciate the intention behind the click, realising it wasn’t just a random shot, but required skill and creativity.

There are parallels between how AI is viewed and how photography was first viewed. After all, like AI, photography was first considered a purely mechanical contraption.

----

And for the record: I do appreciate your opinion and the discussion we're having here.

Quote:
"

Anyone who has used AI to create images knows it is no mean feat to coax it into creating a replica of the image you envision. [my emphasis]

When you click the generate button, AI might generate an interesting visual, but it usually won’t look anything like the visual you had in mind. 

AI has its limitations. To create the picture you wish takes a lot more than entering one line of text and the click of a generate button.

The majority of artists using AI to generate work don’t use the one-click fix to create their art.

They have a practice that is time-consuming and complex, which allows them to create the specific style and visuals they envision."

Given, what you say was absolutely correct, this would be nowhere represented in the final result.
there is nowhere to know, if you tweak every detail by pick and choose or take the first result.
The damage that AI has already done, is severe. It has destroyed trust into art.
The process of creating those AI images is undesputable. A software does it for you.
Even if you tell your AI-friend a thousand times how to create an image for you.
There is that disconnection between the result and the intend with generative AI.
Because it is NOT you, who is directly involved in the artistic process, you are "only" the idea provider.
Quiz question:
Who created the sistine chappell ceiling fresco?
Michelangelo
or 
Pope Julius II. (because he has been the one ordering it)?
And yes, I do see that very black and white.

Quiz question:

Who created the sistine chappell ceiling fresco?
Michelangelo
or 
Pope Julius II. (because he has been the one ordering it)?
And yes, I do see that very black and white.

Well, I guess Pope Julius II didn't put a scetch on the plaster of the sistine cheppell and gave Michelangelo precise instructions on how to fill in the colours. Also I guess the Pope wasn't  present at all times to instruct Michelangelo what to do. 

Il ne faut pas ignorer l'histoire de l'art, chaque changement a donné un nouveau courant, un pixel reste un pixel d'où qu'il vienne, et au début de Poser beaucoup d'artistes faisait une mise en place sous Poser qu'il texturait sous photoshop.

Les artistes se revendiquant 100% Poser sont récents 

Compelling arguments, but take a moment to consider where the information for the final AI render is coming from and how it was gathered.  The internet has become a vast source of data for AI.  Every artistic image uploaded and every photograph posted has become data-mined to composite a final AI render on verbal command, which means your final image is a repository of stolen data bits.  You may argue that the input might be infinitesimal and no one will recognize their data, but in an age where internet users are very anal about security, there should be guardrails on how AI data is farmed.  There is no compensation for how your data is used.  In Poser, you pay vendors for license use of materials, morphs, and content.  You are allowed to create whatever scene you want, but you are restricted in how you share the components of your creation.  There are no guarantees with AI; you compose your image, create a final render, upload it to the internet, and refeed the AI monster with fresh data with no compensation.  

I am seeing many content makers restricting the use of their models for AI data mining.  Are you telling me that you would totally disregard the licensing terms of a vendor just to improve an image through AI?  Until regulations clearly specifiy when and how AI implementation can be permitted, I would tread carefully how you use that AI knowledge.

By that same argument, all human art is also stolen.  Look at a painting of a building.  Notice the roof tiles have a pattern.  Who made that pattern? the artist or the builder of the building? Did the painter get permission to copy that pattern when they made the painting?  Since a human is basically a data-mining machine (i.e. a very slow one) then where does that place the output they produce?   Or look at stories, there are only 7 basic themes, and everything is just a rehash of one of those themes.  So you change the name and location it will still come down to a simple underlaying theme.  And who owns the rights to those themes?

The only true art that is not stolen ideas from other people is from 1 year old kid with their crayons and even then, that is suspect as they have seen other people and things so even they have stolen ideas as to what something should look like.  i will amend that in that a person born blind and deaf will have no change to be influenced by other art so maybe what they produce could be original art.

Michelangelo paintings look an awful like the art that was around at the time he did the chapel panting, so did he get permission to copy those art styles?  And if he did does that make the chapel his or someone else's?

hborre, the problem is even more true for software, and even more so for free software, since AI takes without knowing where and free software does not accept that, an author knows his references, his masters, even if he copies, he knows that he must be better or bring something new (even the art of collage can be creation).

Has it ever come into your mind that if you place fear, just like politicians do, restricting people to evolve, the same is happening with new things. Might it be that Poser can not compete with AI so AI must be bad, drop a little fear and say It is stolen with the hope that People will not use and just use the poser features. 

That is exactly the wrong step. If you would say Poser can be used to control a little AI giving you closer results for the final Image you want, then you will make it good and make something more Popular. A way to Integrate an old with new to make it better. Same like that you need another program to create models for poser, 

So what is wrong about using AI to make the your render look better. Believe me if I make a model and show that in combination with AI it will look awesome more will jump onto it, People that only use AI might get interested to use the combination instead of only texting AI .

If I make a AI render, place the description that the Base was made using Poser/DS Models, what do you think will happen ? If I say I controlled the Image and it was not a coincidence! This is the point where interest will grow. But by saying it is stolen, do not use it , Is an IQ  of a chimpanzee that does not understand simple math! 

Make it something Positive, show what it can do in combination with the new. I do understand that some in here are visually stuck and probably not capable to evolve but it does not mean that all need to go this way. But even these if they try they might get positive results and could show what could be achieved using Poser in combination with AI.  

Aside from the issue of whether or not AI is ethical, I don't enjoy using it.  I experiment with it from time to time and I guess the results are OK.  The problem is that it doesn't feel to me like I'm the artist when I tell a generative AI application to improve my pictures.  I feel like I am commissioning someone (something?) else to improve my picture for me.  It's a personal thing, I guess, but I don't find that very satisfying. =\

Molly

Using generative AI as a workflow tool can be a wonderful process once the ethical legalities are resolved.  I don't mind using it to refine a certain look or style, to embellish a render, or to add to it.  Ken1171_Designs has done a tremendous job publishing software that exports posed figures for AI use.

AI usage will become a personal decision and depend on how comfortable you feel tapping into it as part of a workflow.  ATM, there is no easy recipe; either users devote enough time and effort to learn how to be textually creative or abandon the technology altogether for something simpler.

Aside from the issue of whether or not AI is ethical, I don't enjoy using it.  I experiment with it from time to time and I guess the results are OK.  The problem is that it doesn't feel to me like I'm the artist when I tell a generative AI application to improve my pictures.  I feel like I am commissioning someone (something?) else to improve my picture for me.  It's a personal thing, I guess, but I don't find that very satisfying. =\

Molly

I can relate to that, but to me that was also a motivation to get back to it over and over again and explore ways to make it work for me.

A bit of a personal story: I think I was 6 or 7 years old when I saw a movie on TV with a woman in a beautiful baroque dress that somehow struck a chord. I remember I wanted to replicate that image on paper and was utterly frustrated my hands weren’t able to do that. In my teens I saw Hammer Horror’s  ‘Dracula has risen from the grave’, with Veronica Carlson and Christopher Lee. Since then I've been hooked on this genre, but secretly always wanted Dracula to win and go just a little further than sensors would allow.

Over the years I learned how to draw, but found it too frustrating/time consuming. So discovering Poser 4 in 2000 was something like a ‘Godsend’. Setting up a scene and choose every angle and detail possible before committing to the final render was a revelation. Over the last 25 years I thoroughly learned how to use all successive versions of Poser (and Photoshop) improving my art and gaining an audience for my ‘art niche’.

But I feel the leaps Poser made with new versions going from Poser 4 to 13 became an agonizing slow crawl and with poser 14 a step back. So looking for ways forward I explored DAZ and several other software, but they all felt like throwing all I’ve created and learned in the bin, for only a minor improvement in capabilities.

When AI arrived and I saw what it can do, the 7 year old me woke up again. This technology finally can truly help me bring the pictures I have in my head to life. And almost 50 years later I now have gained some knowledge to actually make it work. Still it takes a lot of effort to work around all AI’s limitations and quirks to make something that’s in my head. But with the help of Poser a fair amount of creativity and work arounds I’m on my way to getting there in ways the 7 year old me couldn’t have imagined in all the world possible!

I love what Poser has brought me over the last 25 years. I’m rooting for the makers of this software to create something worth buying. But to be honest: if Poser 14 is all they can bring to the table, Poser 13 will be the last version I’ve bought.

Whether you like it or not, the genie is out of the bottle and AI is here to stay. Yes there need to be guardrails, and it floods the world with trash I hate.  But it also a powerful, scary, hopeful, intriguing, … tool, capable of things we couldn’t have fathomed a few years ago. And it won’t go away.

So this is also a heart felt call to everybody at Poser reading this. I don’t care if it’s AI or something else, but add capabilities to your product that truly help artists advance in recreating the pictures in their heads. Start with the users and why they truly use your software and go from there.

Cheers!

Richard

--

Unprocessed Poser render for AI workflow:

Closing in on the image that's in my head ...

Nevertrumper posted at 9:47 AM Sun, 28 December 2025 - #4502605

lsauvage posted at 6:57 AM Sun, 28 December 2025 - #4502603

When using AI, you decide what to keep and what to discard—it’s entirely the artist’s choice. I mainly use it to generate reference materials, which is also my primary use for tools like Poser.

In the past, I used to collect images from Google or reference books to inspire my drawings and paintings, manually creating something new from a variety of sources. With AI, I can now generate the references I need. Whether this is “art” is a big philosophical question, but for me, it’s simply another tool. I’m not a professional, and I don’t claim to be , but even my painting teacher was amazed when I brought in AI-generated images that perfectly matched my artistic previous works.

Your friend A. I. makes a imagages for you, that you ordered, and you pick and choose, which one to keep?
And then you claim, this is YOUR art work?
Hell NO!

What I mean is that I draw from various sources to fuel my art, and once you learn how to make AI do what you want, it becomes more useful to me than stock photos. Just as Francis Bacon used Velázquez’s pope as a starting point for his own paintings, I ask AI to generate images, which I then modify and transform.

The idea that you have a clear vision in your mind and simply print it out is not how the artistic process works. When you paint, there are mistakes, experiments, and many failures—until suddenly, you decide to keep an “erroneous” stroke and repaint the rest. There’s an unconscious force guiding you, and you’re not just a perfect inkjet printer reproducing the ideal image from your brain.

By the way, I also use AI to correct my English in this forum, but I always write my thoughts first, read them over, and then refine them. Does that mean the ideas become the AI’s?

Whish you all the best.

lsauvage posted at 5:50 AM Wed, 31 December 2025 - #4502706

Nevertrumper posted at 9:47 AM Sun, 28 December 2025 - #4502605

lsauvage posted at 6:57 AM Sun, 28 December 2025 - #4502603

When using AI, you decide what to keep and what to discard—it’s entirely the artist’s choice. I mainly use it to generate reference materials, which is also my primary use for tools like Poser.

In the past, I used to collect images from Google or reference books to inspire my drawings and paintings, manually creating something new from a variety of sources. With AI, I can now generate the references I need. Whether this is “art” is a big philosophical question, but for me, it’s simply another tool. I’m not a professional, and I don’t claim to be , but even my painting teacher was amazed when I brought in AI-generated images that perfectly matched my artistic previous works.

Your friend A. I. makes a imagages for you, that you ordered, and you pick and choose, which one to keep?
And then you claim, this is YOUR art work?
Hell NO!

What I mean is that I draw from various sources to fuel my art, and once you learn how to make AI do what you want, it becomes more useful to me than stock photos. Just as Francis Bacon used Velázquez’s pope as a starting point for his own paintings, I ask AI to generate images, which I then modify and transform.

The idea that you have a clear vision in your mind and simply print it out is not how the artistic process works. When you paint, there are mistakes, experiments, and many failures—until suddenly, you decide to keep an “erroneous” stroke and repaint the rest. There’s an unconscious force guiding you, and you’re not just a perfect inkjet printer reproducing the ideal image from your brain.

By the way, I also use AI to correct my English in this forum, but I always write my thoughts first, read them over, and then refine them. Does that mean the ideas become the AI’s?

Whish you all the best.

IIRC, it has been reported that AI will achieve its maximum external input within 5 years before is begins feeding on itself.

On va finir par faire de la philosophie et parler du degré de liberté, qui n'empêche pas la vérification et le choix.

We'll end up doing philosophy and talking about the degree of freedom, which does not preclude verification and choice.

MollyFootman posted at 4:31 PM Tue, 30 December 2025 - #4502692

Aside from the issue of whether or not AI is ethical, I don't enjoy using it.  I experiment with it from time to time and I guess the results are OK.  The problem is that it doesn't feel to me like I'm the artist when I tell a generative AI application to improve my pictures.  I feel like I am commissioning someone (something?) else to improve my picture for me.  It's a personal thing, I guess, but I don't find that very satisfying. =\

Molly

I can relate to that, but to me that was also a motivation to get back to it over and over again and explore ways to make it work for me.

A bit of a personal story: I think I was 6 or 7 years old when I saw a movie on TV with a woman in a beautiful baroque dress that somehow struck a chord. I remember I wanted to replicate that image on paper and was utterly frustrated my hands weren’t able to do that. In my teens I saw Hammer Horror’s  ‘Dracula has risen from the grave’, with Veronica Carlson and Christopher Lee. Since then I've been hooked on this genre, but secretly always wanted Dracula to win and go just a little further than sensors would allow.

Over the years I learned how to draw, but found it too frustrating/time consuming. So discovering Poser 4 in 2000 was something like a ‘Godsend’. Setting up a scene and choose every angle and detail possible before committing to the final render was a revelation. Over the last 25 years I thoroughly learned how to use all successive versions of Poser (and Photoshop) improving my art and gaining an audience for my ‘art niche’.

But I feel the leaps Poser made with new versions going from Poser 4 to 13 became an agonizing slow crawl and with poser 14 a step back. So looking for ways forward I explored DAZ and several other software, but they all felt like throwing all I’ve created and learned in the bin, for only a minor improvement in capabilities.

When AI arrived and I saw what it can do, the 7 year old me woke up again. This technology finally can truly help me bring the pictures I have in my head to life. And almost 50 years later I now have gained some knowledge to actually make it work. Still it takes a lot of effort to work around all AI’s limitations and quirks to make something that’s in my head. But with the help of Poser a fair amount of creativity and work arounds I’m on my way to getting there in ways the 7 year old me couldn’t have imagined in all the world possible!

I love what Poser has brought me over the last 25 years. I’m rooting for the makers of this software to create something worth buying. But to be honest: if Poser 14 is all they can bring to the table, Poser 13 will be the last version I’ve bought.

Whether you like it or not, the genie is out of the bottle and AI is here to stay. Yes there need to be guardrails, and it floods the world with trash I hate.  But it also a powerful, scary, hopeful, intriguing, … tool, capable of things we couldn’t have fathomed a few years ago. And it won’t go away.

So this is also a heart felt call to everybody at Poser reading this. I don’t care if it’s AI or something else, but add capabilities to your product that truly help artists advance in recreating the pictures in their heads. Start with the users and why they truly use your software and go from there.

Cheers!

Richard

--

Unprocessed Poser render for AI workflow:

Closing in on the image that's in my head ...

Again, those renders here, should be possible to create in Poser WITHOUT AI.
Learn Lights, learn render settings and learn color grading in a photo editor, like Affinity or Gimp.

Nevertrumper posted at 6:56 AM Sat, 3 January 2026 - #4502771

Again, those renders here, should be possible to create in Poser WITHOUT AI.
Learn Lights, learn render settings and learn color grading in a photo editor, like Affinity or Gimp.

In terms of copyright, it’s even more complicated—we’re moving out of the realm of art and into the world of law. A well-directed AI can easily plagiarize famous artists. But in painting, plagiarism has been practiced for hundreds of years. Sometimes it’s hard to tell who actually painted a given work, especially since many were created with assistants, and we often just attribute it to the “school of…”

I don’t do mass reproductions; I paint for my own enjoyment, by hand. That alone would make it pretty hard—at least in France—for anyone to convince a judge to force me to give money to an open-source model that you’d have a tough time proving I even used!

The real copyright issue arises with the mass printing of plagiarized designs on mugs or similar items. In that case, you’d likely have more trouble with the artist whose work was used to train the AI than with the AI’s provider or programmer.

We can go over all the details endlessly, but instead of thinking in limitations, it's also possible to think in possibilities. I've been working with Poser for 25 years. I know what it can and can't do. I know how to put a scene together, light it and enhance it in a photo editor. I even made several animations and movies of several minutes using Poser.

The point I'm trying to make is that I'm frustrated with the lack of progress in Poser. From Poser 12 to 13 the major upgrade for me was render speed. But other than that I've seen hardly any real new features since I bought Poser 12 in February 2021. Only very small incremental improvements.

Poser is a wonderful tool to put a scene together in minute detail. It does a reasonably good job at texturing and lighting. It's mediocre at draping fabric and to my horror that feature has now been deleted from Poser 14 completely. It’s very very hard to replicate soft materials, like flesh. And poser is absolutely horrible at doing hair. Overall the unprocessed output often looks ‘plastic’ and needs major post production to bring it to life.

AI is absolutely amazing at doing textures, skin, hair, lighting, flames, etc. But the randomness is making it hard to work with it if you’re looking for a specific result. Also AI doesn’t know what’s outside the frame. It even has trouble interpreting things that are only partially within the frame. If AI can’t make sense of something it makes thing up (often badly), while in Poser I can create shadows from things that are completely outside the frame, because it knows there’s an object there.

In my view putting the best of these worlds together would be amazing and ground breaking.

And on the legality of things: If I can train (lora) models using my own material on my own PC, so can the developers of the Poser team. I think there should be plenty of material available that is legal to use. You can even create the material yourself.

Meanwhile I’m trying to learn and adopt this new AI technology, to learn something new and improve what I make. Because if I just do what I did, I get what I got, and that’s not satisfying my desire for progress.

And once again: I hope the Poser team will come up with a product that shows real progress and excites customers.

---

And yes, I do know how to use Poser and light a scene ;-)

Yeah, the make "art button" has become reality.
Don't take credit for this eye candy result.
It hasn't been made by you. AI did it for you.

I hesitate to weigh in here because my knowledge is limited to US copyright law and I recognize we very fortunately have a global community. That said, this discussion appears to miss the distinction (in the US) between original works and derivative works. Someone who adds to an original work creates a derivative work; and they "own" the derivative portion. The derivative portion is, in fact, their own creation. That raises the question of what AI actually contributes.

Did the AI platform find an idea/concept and apply it to the user's image/? If so, US copyright law does not recognize concepts, only tangible manifestations of published works. Or did the AI platform merely copy an original image?