Stance on AI generated material?

I keep seeing people (and I'm talking in general - not limited to this forum) claim they are pro-artist, yet use AI (which is trained on stolen material from artists) in their images or videos of their dolls...
So I'm curious what the rules, or stance, is here concerning AI generated material.

I think that’s a complicated question. If AI is sampling thousands of images or texts to create something original, I’m doubtful that would violate any copyrights. Thats basically what people do with their own brains when they create something; we’re pretty much monkeys after all.  If you use it to create a new Superman comic and sell it, I’m sure you’d lose the subsequent lawsuit. 

Fanart is a grey area. I mean if you make fanart of Sailor Moon, you are stealing someone’s IP, but mangaka seem to look the other way as long as you don’t inflict harm on their creations. Indirect Monetization of those images via social media is another can of worms the courts need to address.  

As far as the forum, we do have policies against theft of intellectual property, but we aren’t lawyers, and I don’t think there is a lot of case law on this yet. Determining the nuances of what is and isn’t stolen is going to be impossible for us with a lot of things. 

I also don’t know if Open AI’s language models are designed to prevent outright plagiarism. 

AI is here to stay though. Using AI cuts the time it takes to do a lot of work way down. Today, it wrote a working powershell script for me, and helped me quickly fix an issue in just a few seconds. It would have taken me an hour to do it on my own, and I didn’t have it to spare; you really can’t close Pandora’s box once it’s been opened. 

I asked ChatGPT the following question: 

Are you allowed to create a picture of the character Sailor Moon?

I got the following answer:

Yes — I can create a picture inspired by or depicting the character Sailor Moon, as long as it follows fair use and fan art guidelines (e.g. no explicit, violent, or commercial use).

This is what it created:

 

She lost a finger somewhere. 😅 

This is Usagi, she may have accidentally bitten it off while scarfing down her food. 

I don't know if this follows fair use, it probably does, but I am pretty sure it complies with fan art. 
 

I asked it this: 

Do your language models prevent you from inadvertently plagiarizing existing works? For example if I asked you to tell me an original story, could you tell a story that copied something from the works of Mark Twain?

I got the following answer: 

Excellent question — and yes, there are several layers of protection to prevent plagiarism or unintentional copying.

Here’s how it works:

1. Training Process

My model doesn’t have access to copyrighted books or their full texts (like Mark Twain’s novels). Instead, it was trained on a mix of:

• Licensed data
• Data created by human trainers
• Publicly available information

This means I don’t “remember” or store passages from those works — I generate language based on patterns I learned.

 

2. Generative Rather Than Reproductive

When you ask for an original story, I don’t retrieve or copy from memory; I create text from scratch, predicting what fits your prompt while staying consistent with context and tone. So even if the style resembles Twain’s — say, a 19th-century Mississippi voice — the words and story structure are new.

 

3. Similarity Checks and Style Modeling

OpenAI includes safeguards that reduce the likelihood of verbatim overlap with known sources. When I imitate a style (“in the voice of Mark Twain”), I use general stylistic features — rhythm, dialect, humor — not specific lines.

4. Public-Domain Exception

If you explicitly ask for material that is public domain (for instance, The Adventures of Tom Sawyer), I can quote or summarize it freely — but I’ll always note when I’m doing that rather than presenting it as original writing.

If you’d like, I can demonstrate this by writing a short original story in the style of Mark Twain, then show you how it differs from any actual Twain passages. Would you like me to do that?

It wrote the following: 

 

“The River Ain’t Got No Memory”

(An original story in the voice of Mark Twain)

When I was a boy down by the Mississippi, we used to think the river knew every secret we ever told it. If you lost your hat, or your marbles, or your patience, you could stand on the bank and holler, and somehow you felt the river was listening. But the older I got, the more I suspected the river didn’t remember a thing — it just kept rollin’ along, carrying off our foolishness like it was paid to mind its own business.

One hot July, my friend Billy Tull and I decided we’d make a raft and float clean down to New Orleans. Billy said we’d find treasure. I said we’d find trouble. Turned out we were both right — though the treasure was a catfish big enough to sink the raft, and the trouble was Billy’s mama, who hauled us home by our ears before we ever left sight of town.

That night I sat by the river again, my ear still burning, watching the moonlight stretch across the water. The current didn’t care about my schemes or my bruises. It whispered the same thing it always had — that boys will grow up, and rivers will move on, and neither will ever stop trying to outsmart the other.

 

Why this isn’t plagiarism

• It uses Twain’s stylistic traits — a nostalgic first-person narrator, Southern river setting, wry humor, and folksy voice.
• It does not copy or closely paraphrase any existing Twain text or character.
• The story’s events, dialogue, and phrasing are completely original.

Would you like me to analyze how this story’s tone and language technically emulate Twain’s writing style (for example, dialect use, sentence rhythm, and narrative structure)?

It's been so long since I read Twain, I'm not sure how well it did copying his style.

Ask copyright related questions to an expert on copyright, not ChatGPT. LLMs are incapable of thought, they are nothing more than machines that generate a natural-sounding answer based on advanced statistical token processing.

On top of that, they have artificially induced limits in place that force them to answer certain questions in certain ways, imposed on them by their makers, because without those limits they would go totally off rails in ways that are clearly unacceptable.

Furthermore, makers of LLMs wouldn't be involved in all kinds of legal procedures over whether or not it is copyright-theft to process large bodies of data without asking for permission first if their process was 100% legal - something doesn't become automatically legal if you do it without asking. Basically, what makers of LLMs did was to perform the dubiously legal process of assuming no answer means "yes" (in certain other circumstances doing so is very clearly a crime in many legislations, e.g. sleeping with someone without their permission, or selling copyrighted material you don't own for a profit).

The normal procedure for using large amounts of data that you don't own in research or otherwise is to ask permission first, unless the material in question comes with a very clear license that puts it in the public domain (with or without additional guardrails). Disclosure here: I've worked in a field where I helped release a large amount of previously privately published scientific material under a Creative Commons license, and determining the kind of CC license used was a very important step in the process because a bad choice might either jeopardise future use of the data or our own legal position.

TL;DR: Using the technology on your own material is probably safe, as is using it on stuff you've asked permission for or that is licensed to be available to you. Note that e.g. a Bluray video disc or book is not something you truly own, you've just got a license to watch the contents, and it comes with a lot of strings attached that may or may not be legal in your country depending on local copyright law. Oh, and don't use ChatGPT and similar as replacement for expertise.

Edited October 31, 2025 by Kemonomimicry

@BeyondTime Are you serious..? Or did you intend to mock?

I would like to see AI generated doll images be discouraged. I think allowing images to be posted like that degrades the quality of the galleries on this site (‘AI slop’ is the popular term for it for a reason). Although I don’t know how realistic it is to moderate for that. 

I think the biggest issues concerning this hobby and AI would be as already mentioned totally synthetic pictures, and probably animation.

We've already had a bit of a since deleted outburst on the latter some time ago. I have to admit the clips i've seen are genuinely impressive on occasion, but... the base movement capture had to come from somewhere, for Grok does it source from every other Twitter/X user? Sora2 has already been reported as being a hoover of data where even IP holders have to opt out of their stuff being used.

But if someone goes through the motions of actually making stop-motion animation from start to finish, people who know, will appreciate it. Actually I dont see too much of a problem using AI as an aid in this if you yourself make the Key frames of something and let the AI fill in the blanks. Just let people know what you did to fill those blanks.

As far as image manipulation goes... at what point do you draw the line since manipulation was already a bit of an equipment sport in the hobby, with people removing stands and whatnots and doing composites of putting dolls into scenery they originally werent in ever since since the early days of photoshop. Now you have photoshop advertising just text prompt editing for even larger parts of the image and you have to wonder how much the image poster actually had to do with the image in question, especially since adobe's stance on this was "All your cloud stuff is ours for machine learning" a year ago.

AI has its uses, in coding its a nothingburger. except if you actually want to know how the code works, since that may not always be the case. so depending on how mission critical it is, you may or may not want to utilize it.

its just the artsy side of stuff where it gets iffish.

 

2 hours ago, finnleo said:

AI has its uses, in coding its a nothingburger. except if you actually want to know how the code works, since that may not always be the case. so depending on how mission critical it is, you may or may not want to utilize it.

*cough* like microsoft having laid off a lot of people in favor of AI doing the work, and with the mess of recent updates - it shows *cough*

But yes, AI does have its uses. Editing and slightly manipulating images to remove people/items, as an example, at least can be done/programmed without stealing data from people (not that anyone would when they can just steal...)
But to stay on point, the majority of artists and creators does not want their work to train AI, or be used/exploited. Even if it is just to generate a background for your doll photo to show people online, it is a tool that is currently unregulated and is causing damage. Much like with the situation with recasts.
So I think it is important to take a proper stance, either for or against.
 

2 hours ago, finnleo said:

We've already had a bit of a since deleted outburst on the latter some time ago.

Ah, must have missed that!

14 hours ago, Yumeiro said:

@BeyondTime Are you serious..? Or did you intend to mock?

I was not trying to mock you. Edit: You asked a serious question, and I know better than to mock someone for that. 

 

16 hours ago, Kemonomimicry said:

 

Ask copyright related questions to an expert on copyright, not ChatGPT.

 

I was asking chatGPT to identify its own programmed limits, and not asking it for expertise on copyright law. I asked it questions that I had that were born from my own statement:

On 10/30/2025 at 5:01 PM, BeyondTime said:

I also don’t know if Open AI’s language models are designed to prevent outright plagiarism. 

 

I posted its responses so people could draw their own conclusions.

The use of generative AI is theft. Plain and simple. 

 

There shouldn't be any place for it here IMO, and it can't ever be likened to art made by a real, human artist.

It's unethical, and that's not even delving into how destructive it is environmentally. 

I tend to agree that we should have some rules about AI generated doll images, and I think letting members discuss this need is a good idea, but there need to be some ground rules to keep the passion people feel about this subject from derailing the thread. 

1) All the normal guidelines about conduct on the forum apply. 

2) This forum is about dolls, so while discussion about relevant general information about AI is fine, this isn't the place for any kind of AI activism, pro or con.

3) Any sort of rage, or abuse of other forum members will be removed and repeat offenders can get a ban. That's from the basic guidelines, but I am restating it because we had to remove a thread a few weeks ago. It's like some people never read these.

As of right now:

I think presenting AI generated images of dolls themselves shouldn't be allowed to be presented in any of the image galleries in our forum regardless of the gallery format i.e the ABC thread is considered a "gallery" under this. Keep in mind that moderator decisions are subjective in nature, and @baldylox & I may differ in our responses at times. He will have his own opinions on this very topic, and I'm only 1/3 of the staff here. 

Using AI generated images to illustrate a point in a discussion like this should be fine as long as it is identified as AI, is on-topic to the discussion, doesn't break forum rules. 

I don't think using AI to remove doll stands, or fix imaging flaws like dust and other distractions is an issue nor does it require calling out. Image editors exist for that purpose and are meant to save a photographer or editor's time; AI is an evolutionary step in that task. 

If AI is used to generate some significant element of an image it should be called out. 

AI is a tool, and as such, it is subject to use and misuse. Much of the distinction between those two ends of the spectrum will need to be decided by government and the courts. The most we can do here is decide how it applies to doll related posts. 

AI is here to stay, like it or not; it can be weaponized so every developed nation is going to try and evolve it for their own needs. Civilian / commercial purposes will inevitably follow any advance created for a military purpose.

14 hours ago, finnleo said:

and probably animation

AI animation is still very uncanny valley at the moment, and given that dolls trigger uncanny valley responses in people, AI animation might hurt the hobby's reputation.

 

14 hours ago, finnleo said:

AI has its uses, in coding its a nothingburger. except if you actually want to know how the code works, since that may not always be the case. so depending on how mission critical it is, you may or may not want to utilize it.

This is a general statement and not aimed specifically at you. Your comment just raised a very valid point.

I would strongly suggest that no one should blindly follow guidance from AI on a topic they know nothing about. I used AI to generate a Powershell script that I could have written myself with time. I read the script and understood it well enough to determine that it did what I intended it to. I ran it in a non-production area to confirm my own assessment, and only after doing so did I run it in production; this is especially important if you are running under any sort of root level user context.

There have been examples of lawyers asking ChatGPT to interpret case law, and then getting schooled in court by angry judges. 

In the doll context, I wouldn't blindly trust AI to tell you how to do something irreversible to a doll, but it can be a starting point for additional research.

 

14 hours ago, finnleo said:

Just let people know what you did to fill those blanks.

I'm going to give a few examples of my own use of AI, and again not aimed at you, you just raise a point that is worth discussing.

 

I want people to see different ways it it can be used as a basic tool in Photoshop, and to comment on whether or not AI use should be called out. My own comments in red, and people don't need to agree, just be polite and contribute in a productive way. You can just call out the image numbers, no need to quote the entire post.

1) Before using Generative Fill:

Kaede Takagaki V2 - Bottoms Up-13009-2.jpg by Cult-Of-Athena - Info Photos & Photo Stories, on Flickr

A) Could have been done with clone stamp / content aware fill.

B) Would have taken 40+ minutes with traditional tools, and probably wouldn't look quite right when I was done and that would have resulted in the use of the Bokeh filter to blur the entire background. I spent 3 days cleaning up distracting backdrop wrinkles on a series of images once, and AI could have smoothed the lot in a few minutes. Using AI to give me back that kind of time is a no brainer.

C) Same as B.

As to why I didn't just fix the rug? I was way too worried about my new Kaede falling over and face planting in a glass full of water mixed with grenadine, and as long as she was balanced I just wanted the photos done as fast as I could. Normally you do want to fix before you push the shutter.

2) After Generative Fill.

Kaede Takagaki V2 - Bottoms Up-13009.jpg by Cult of Athena, on Flickr

To my recollection this tool uses the local computer's CPU and only uses elements from your own image to generate the fill; it is generative though. 

I don't think this sort of thing needs calling out. 

 

Two images that I made to hang as background images in doll diorama shoots. For both I used ChatGPT for research like listing movie titles from the 70s for the second one, and listing appropriate fonts for movie posters from that era. The idea to use the word Dolls as a play on existing movie titles was mine. The posters are from Adobe Stock Templates. Could I have done research the long way, yes, but at the cost of the most valuable thing any of us have — Time.

3) The zombies in the backdrop on this one were made with Generative AI, Adobe Firefly 3, and I did look for stock photos in Adobe Stock first but nothing I found was suited to the requirements. 

Movie Poster 2.jpg by Cult of Athena, on Flickr

4) This one didn't use AI for anything except research. 

Movie Poster.jpg by Cult of Athena, on Flickr

On #3 AI was used to generate an important element that helps identify the poster as horror, but it's a small element that was darkened to keep it from distracting from the foreground. That part prints a lot darker than the exported jpg. It's subjective as to whether or not this should be called out. 

On #4 I don't think using AI for research needs calling out. I picked the title and font from AI provided lists that helped narrow down the options and save time. 

5) This used AI to write much of the filler text with a lot of prompting from me, and I called that out. I don't want credit for writing that isn't mine. The entire news layout was an InDesign template downloaded from Adobe stock.

Spoilered for image size.

Spoiler

Vinyl News - War.jpg by Cult of Athena, on Flickr

I called it out because no one should take credit for something they didn't do. My prompts were probably 5%, and my post AI text edits were another 5%.

 

6) This used AI for the bedroom / doorway image in the background, again my stock search didn't produce what I needed; especially since Kaede was lit from behind. The Russian text is AI generated. I didn't call AI out, but only because I didn't think to at the time.

Kaede Takagaki V2 - Bottoms Up-13043.jpg by Cult of Athena, on Flickr

Probably should be since AI generated text and image covers a majority of the photo. The entire image is a recreation of a real cover from long ago, but mine stars Kaede, so not a wholely original work at all, but it should fall under fair use.

7) The men in this one are AI generated, and again my stock search gave me nothing that fit exactly what I needed. The AI image was heavily darkened with an exposure filter because I wanted more vague silhouettes than detailed people, and I used a blur filter to further obscure detail. The blur filter was an Adobe 'Neural Filter,' and I am pretty sure those rely on cloud based AI processing. The stage is generative fill because using the AI fill tool to re-texture your existing floor is the best way to get a floor that the doll feet actually look like they are standing on. (Just realized I need to add a shadow to Kaede.)

Kaede Takagaki V2 - Bottoms Up-12984.jpg by Cult of Athena, on Flickr

Again, I think it's subjective, the men are barely visible, but they are important. The stage is backdrop imo.

16 hours ago, BeyondTime said:

AI is here to stay

AI has been around for a long time, so this statement is a bit odd. As this topic is on generative AI, so if I where to assume that is what you are referring to, I'd call it utter bullshit!
IF they where to regulate it and force the companies to provide compensation or respect copyright, it would die out. Same with if people would just stop using it. Which brings me to:

13 hours ago, BeyondTime said:

I did look for stock photos in Adobe Stock first but nothing I found was suited to the requirements. 

Respectfully, then don't?
(Are there not other (free, and fair) resources to utilize?)

"I wanted Goku in my graduation photo, but didn't like any existing pictures so instead of commissioning someone to draw, or learning to draw myself, I had AI make it!"
Time is limited, yes, but if people would rather not spend it on the art of creating, then where will the entitlement end?
"I couldn't find a song by Elvis that sounded like I wanted it to, so I had AI make one!"?

It doesn't make it ok, to me.
 

13 hours ago, BeyondTime said:

Before using Generative Fill

A) Could have been done with clone stamp / content aware fill.

B) Would have taken 40+ minutes with traditional tools, and probably wouldn't look quite right when I was done--

This is what gen. AI as a tool should be used for, if anything. I could argue that the more time one would spend with the clone stamp the more you'd learn and the better you'll be at it in the long run. But also, where AI falls short, you'd probably have to correct it manually anyway... bla bla bla.
Point is, it isn't taking something from someone else. A tool and not a replacement. So generally no, no need to call it out.

Edited November 1, 2025 by Yumeiro

Personally I'm not a fan of gen AI content (for many of the common reasons, unethical data etc)- even if it's just people using it to make their dolls move etc.

Though, as a tool, I get it: using it's implementation in Photoshop to remove doll joints, using it to explain certain topics (in tandem with other sources).

...it seems most people don't particularly care. So I'm just gonna accept I'll be one of the few people who want to actually write my own content and "source" images ethically. I'm not going to get upset when other people use it.

 

The other day someone I follow,  who wants to run a manga Cafe in my city,  posted a bunch of AI gen logos and asked for opinions. They seemed really surprised some people were calling them out on the irony.

Edited November 1, 2025 by luna_Lillie

6 hours ago, Yumeiro said:

 

Some of this seems more focused on the optics of generative AI's existence in general, and while it's a valid point of debate, it really is beyond the scope of this forum and should be discussed in an appropriate venue. I'm not trying to ignore your points, they just aren't for here. The question of use of copyrighted material here is valid, and we don't allow theft of IP. However, what IP is and isn't is defined by law, and it's not just anything that individual artists want it to be. I do see objections by artists that AI copies their style, and they say it's copyright infringement, only it's not, style in most cases can't be copyrighted.

We do allow fair-use, and if we didn't many people's custom profile images wouldn't be allowed. 

Yes I do mean Generative AI, the "Generative" part is just a pain to type out every time. 

 

6 hours ago, Yumeiro said:

"I wanted Goku in my graduation photo, but didn't like any existing pictures so instead of commissioning someone to draw, or learning to draw myself, I had AI make it!"
Time is limited, yes, but if people would rather not spend it on the art of creating, then where will the entitlement end?

So it's ok to make fanart of Goku for personal purposes, as long as you use traditional artistic tools & methods and not this newfangled tool called generative AI? I know people who went to art school for 4 years and who still can't do art, so that's not really a realistic option for most people. I can take fairly decent photographs, but I'm hopeless and painting and drawing, and a big part of that is physiological tension caused by stress and anxiety. That kind of art is out of reach for me, and speaking of photography, painters reacted to it's invention with hostility for the same pecuniary reasons that modern artists are rejecting AI as a tool; At this point in time, I'm not sure this is any different.

Saying that I can't take an image in my head and bring it out in a visual form unless I pay someone to do so for me seems to me like an unfair limitation on my own free expression. Do we now limit free expression only to people who have enough disposable income? I realize that to some extent that's a US-centric argument, because of the US Constitution's 1st amendment, things fly here that don't fly in other parts of the world. The courts will weigh limitations on individual expression differently here.

For my own images, I did not ask it to recreate specific works of art, or the styles of specific artists. I asked for generic images that fit a theme. Adobe compensates artists whose images it uses for training, and they spell out the terms in their policies. Artists might not like that, but they don't have to publish and market their images on Adobe Stock. Based on the information I have, as long as Adobe complies with all applicable laws, I don't think their tool, or my specific use of it, is wronging anyone. I don't believe using something like that as a part of an image should be forbidden here, but we shouldn't allow Generative AI images that do infringe on copyrights. Here in our rules, we may need to say that Generative AI can't have been used on more than a certain percent of an image, in order to protect the forum itself.

I used their lower powered AI model because there wasn't any point in using the more powerful model for background images I intended to darken and blur. That means reduced power consumption and carbon emissions. 

 

6 hours ago, Yumeiro said:

I could argue that the more time one would spend with the clone stamp the more you'd learn and the better you'll be at it in the long run.

I have done a lot of clone stamping over the years. Clone stamp is good for small scale repairs, you can stretch it's use a bit for larger jobs, but it has serious structural weaknesses as things get larger and more complex. Content Aware Fill covers part of that gap, but starts to fall apart as the complexity of the area being filled increases. Generative Fill picks up where Content Aware Fill leaves off. 

I tested generative fill on removing doll joints, and it did an amazing job on everything in that image except shoulders. It had Kaede looking like she was on a silicone body. I didn't keep the image or I would have posted it above to show the result as an example. You can't do that with clone stamp, I've tried and the tool just doesn't work that way. 

 

6 hours ago, Yumeiro said:

I'd call it utter bullshit!

Please be careful with strong language. I know this was aimed at the idea and not me, so it's fine under the guidelines, but not everyone picks up on that kind of context. Based on what happened a few weeks ago, this thread is going to be hard to keep from being derailed by vitriol as is. 

 

2 hours ago, luna_Lillie said:

So I'm just gonna accept I'll be one of the few people who want to actually write my own content and "source" images ethically.

I can write well enough, it's just that when I feel attached to something I write I will spend months polishing it before I am happy with it. If I am trying to write something creative I wouldn't use AI, but with more generic text it's an option. I use it for internet searches because it does a better job getting the results I need than I do, and that's kind of the point of tools in the first place.

 

Edit: I think my own use of Generative AI at the beginning of this thread is fundamentally different than how I used it in my own images. The AI picture of Sailor Moon contained nothing that I did myself except ask for a picture of Sailor Moon. My own images reflect my own image concept, the dolls in the images are taken from my own photos of my own dolls, and AI was used as a tool to support parts of the creative process, but those tools were not the creative process. I can look at my photos and composite images and feel like they are mine, but the Sailor Moon image is not mine in any way. 

I am personally, not as a moderator, against forbidding people from using a lawfully available (at this time) tool, but I believe that tool has to be used in compliance with the law. The hard part is finding the line between acceptable and unacceptable content here. 

This is a forum for doll owners, and not AI pictures of dolls, so for certain I feel that should be out. Theft of IP should be out. 

56 minutes ago, BeyondTime said:

So it's ok to make fanart of Goku for personal purposes, as long as you use traditional artistic tools & methods and not this newfangled tool called generative AI?

The underlaying problem here is that if you are using an ethically trained AI model, it should not directly spit out an image of Goku, it would ask "Describe goku for me". If just by prompts the AI is able to make something like goku happen, all's good, if you directly show it an image of what to do we go back to training with IP rights reserved stuff.

Its the test Midjourney "failed" some time ago, where people were asking it to make superman, or batman. It should have spit out a half man half beast chimera, not the actual superhero characters, and most definately not be using the logos associated with those characters, so at some point someone showed the model copyrighted characters to define those meanings.

21 minutes ago, finnleo said:

If just by prompts the AI is able to make something like goku happen, all's good, if you directly show it an image of what to do we go back to training with IP rights reserved stuff.

I haven't asked Adobe Firefly if it can make an image of Sailor Moon, but I know GPT and Midjourney can. The other big one, the name escapes me, can do Sailor Moon, but does Sailor Moon when I ask it for Sailor Mercury.

If I search Adobe Stock for images of Sailor Moon I get images of Sailors and Moons and Sailors with Moons, but no Mooning Sailors, and the only Sailor Moon image returned was an "editorial use only" photo of a real world item with a picture of Sailor Moon and other anime characters on it. I did get a picture of a girl with pink hair, Princess Leia style buns, and a bow on her chest. If that image came from Firefly, then it sort of knows what Sailor Moon is, but that image viewed out of context wouldn't be seen as a copy of Naoko's work. 

For sake of the discussion here is that image. (I went ahead and used a credit to license it.)

Spoiler

 

If stock really is the basis for Firefly's knowledge, it shouldn't be able to make an image of Sailor Moon.

Based on experience with other things, Firefly might well reject the prompt entirely rather than give me sailors in the moonlight, but I don't want to risk trying it because I do know that Adobe forbids that as a matter of policy.

 

7 minutes ago, BeyondTime said:

but no Mooning Sailors

Bruh 😂 

2 hours ago, finnleo said:

The underlaying problem here is that if you are using an ethically trained AI model, it should not directly spit out an image of Goku, it would ask "Describe goku for me". If just by prompts the AI is able to make something like goku happen, all's good, if you directly show it an image of what to do we go back to training with IP rights reserved stuff.

It's the test Midjourney "failed" some time ago, where people were asking it to make superman, or batman. It should have spit out a half man half beast chimera, not the actual superhero characters, and most definately not be using the logos associated with those characters, so at some point someone showed the model copyrighted characters to define those meanings.

Sorry, I sort of missed the larger point about Goku; my brain tends to chase after squirrels in text due to some level of ADD.

Is it legally ok to make a picture of Goku at all? At this point in time, I believe the answer is yes, but under very specific fair-use guidelines. Is it legally ok to make Goku with generative AI, if that AI follows those same guidelines? I believe that second question is unanswered at this time. General recommendations seem to be to be careful and make sure that work which uses AI complies with fair use rules. For example: Make sure that AI images are below a certain percent of the total image.

I'm looking at Generative AI as a tool that can be used or misused. I've never been someone who blames tools when people misuse them. Misuse here can apply to training just as well as use of the final product. 

A question I might ask about general tech use and how you view its impact on the worth of your own skills. You have a lot of skill in woodworking, do you feel 3D printing devalues your woodworking skills? The concept here isn't about copyright, and on quality of product a 3D printed Megumin staff will never be as good as your handmade wood one. What I am interested in is about an earlier point of using an easy button to make something it probably took you years of hard work to learn how to do.

The Volks Fern staff isn't as plastiky as the photos made it look, but the doll is so beautiful it kind of cheapens her look. 🫤

Idk, generative AI is a fun novelty for now but it's likely not going to last forever. If you like using it that's fine and I think it's ultimately up to the moderators' decision of whether or not it's allowed on this forum. I don't really think ethical generative AI exists though, unfortunately :// it's too derivative of its source material. 

4 hours ago, BeyondTime said:

So it's ok to make fanart of Goku for personal purposes, as long as you use traditional artistic tools & methods and not this newfangled tool called generative AI?

Refer to finnleos previous comment
I know fanart is a iffy situation overall. Many dislike it too - like Anne Rice, and well as many really like it - like Larian Studios. As examples.
But non-AI fanart at least shows people make an effort of their own.

I turned my DDH-06 (or sculpted my own doll head) into Hatsune Miku vs. I recasted/purchased a Hatsune Miku recast, kinda.

4 hours ago, BeyondTime said:

speaking of photography, painters reacted to it's invention with hostility for the same pecuniary reasons that modern artists are rejecting AI as a tool; At this point in time, I'm not sure this is any different.

And traditional artists have (and some still are) cursing digital painting. You can erase and alter without having to redo your whole piece! You can have chain-brushes so you do not need to draw every link in the chain individually! Cheater!
Money and time can sure be saved there..!

But I do not find it comparable in the least to letting AI "create" for you. AI steals someone else's work/efforts, mixes it together, and puts a bow on it. Not exactly what portrait photography did to portrait paintings. (unless the comparison is that people lost their jobs)

4 hours ago, BeyondTime said:

I know people who went to art school for 4 years and who still can't do art, so that's not really a realistic option for most people. I can take fairly decent photographs, but I'm hopeless and painting and drawing, and a big part of that is physiological tension caused by stress and anxiety. That kind of art is out of reach for me

This might go more into the philosophical... "Still can't do art"? What does that mean? Did they skip class, or does it not live up to their expectation?
If the pursuit of art/creating isn't fulfilling, then maybe they are in it for the "wrong reasons". A lot of people seem to only see value in art if it can be monetized, exploited, or "look good enough for 1000+ likes".

I'm not good at photography. I've barely dedicated enough time to it either, but there is joy to be had in getting a really good picture. Even if it is one in a hundred. 
Same with drawing. I've been drawing since I could hold a pencil, but am I amazing? Hardly! There's people who've drawn for just 2 years that has done some incredible art - a million times better than my stuff! It takes dedication, effort, and hard work. Not a toddler tantrum by not being great on the first try - a hard lesson to learn as well.

What I am getting at is that it is inspiring to see good works of art. I see good photos and want to take photos that good, and if I keep at it, hopefully little by little I'd be able to find my style and probably become better and better.
Using AI to skip all that, I'll learn noting... Reliance on AI will kill so many inspiring artists/creators. I do not get the whole spiel about how AI makes art accessible for everyone argument either. It already is...

Before this off topic rant is over, could I ask a hypothetical? - Just for my own curiosity, so feel free to ignore! - When you say it is out of reach for you, do you want to draw and paint? If suddenly internet died forever today, so you cannot show your works to the masses, but you could still use generative AI, would you?

  

1 hour ago, BeyondTime said:

Is it legally ok to make a picture of Goku at all? At this point in time, I believe the answer is yes, but under very specific fair-use guidelines. Is it legally ok to make Goku with generative AI, if that AI follows those same guidelines?

If the AI software is using ethically sourced data, Goku should be treated as if he was from a new novel. No art exists of him yet, only descriptions. The image that it spat out, THAT, I would argue is "legal fanart".

  

1 hour ago, BeyondTime said:

You have a lot of skill in woodworking, do you feel 3D printing devalues your woodworking skills? The concept here isn't about copyright, and on quality of product a 3D printed Megumin staff will never be as good as your handmade wood one. What I am interested in is about an earlier point of using an easy button to make something it probably took you years of hard work to learn how to do.

I cannot really put them on an equal level.

3D printing still takes effort as you have to create a 3D model (unless you scan it....). And you do still pay people for their work, even if you yourself just push a button to print on your end.
Someone has to design the car, even if a machine builds it.

Edited November 1, 2025 by Yumeiro
addition

13 hours ago, BeyondTime said:

do you feel 3D printing devalues your woodworking skills?

No, 3D printing is another tool in the toolbox for item creation, I do 3D printing myself (or did, my machine properly broke and looking for replacement at the moment), The megumin staff could be 3D printed, yes. but you'd need to still spend time and effort to make it equally presentable.

3D model procurement is a can of worms one might have a time with, but thats its own thing and you still need to paint things even ripping stuff from other places.

13 hours ago, BeyondTime said:

What I am interested in is about an earlier point of using an easy button to make something it probably took you years of hard work to learn how to do.

I think I have enough negative sentiment on the forum already, but... you asked for it.

No supports, almost straight out of the camera with just some highlights knocked off.

How do you think I feel about easy buttons, especially now since editing is so simple people wont understand thats almost unedited, unsupported posing, and because its not a edited breakdance pose feels bland even to myself?

EDIT: But to clarify, my feelings are not black and white with this. I can appreciate effort where I see it, but once I realize that something isnt fully organic, the bar is set much higher.

Edited November 2, 2025 by finnleo

10 minutes ago, finnleo said:

I think I have enough negative sentiment on the forum already, but... you asked for it.

 

Unless I have really missed something, I do avoid the AP thread for example, I don't think I have seen negative sentiment for you. I think you've always been pretty polite except maybe one time that you got annoyed and that happens to everyone. 

 

10 minutes ago, finnleo said:

How do you think I feel about easy buttons, especially now since editing is so simple people wont understand thats almost unedited, unsupported posing, and because its not a edited breakdance pose feels bland even to myself?

I know how hard that is. 
 

I'm going to go photograph my dolls for a bit, so I'll respond to the other posts and points later. Not trying to blow anyone off, it's just I want to make use of the big studio spot in the sky.

I am only going to pop in here to point out that there is a distinction to be made here that I'm not sure has been made. (Unless I glossed over it, there's a lot here already and it's possible I missed it)

The use of of AI to edit your own image in the way of removing objects or filling space is technically generative AI but not in the same way as using something like midjourney to create a whole image. It uses only what is in your own image to do so. And is actually the same thing as a clone or stamp tool which has been around for ages. It simply tries to do it in a way that may be better (but isn't always) than you would have by hand. This kind of AI is not unethical and it's up to you if you want to disclose you edited something this way. It's only because we're suddenly calling it AI that people don't like this tool.

My one and only beef with this is that because of the boom, pretty much every editing app (especially for phones) are putting this feature, as well as manual clone/stamp tools, behind a paywall when they used to be free. But that's not really what we're talking about here. Corporate greed is a whole other can of worms.

Honestly, my take on this is that AI software in the form of digital assistants, LLMs, Midjourney AI, etc are basically the current tech bubble and are more or less on track to pop and fall back into obscurity a la NFTs. Between the ethical concerns, pending copyright legal battles, and generally poor reception from the public, they're mostly being bolstered by various tech investment companies passing money back and forth, not by consumer interest.

As far as applications that edit pictures using automated versions of Photoshop tools, I don't have any particularly strong feelings. People have been complaining that digital artists take the "easy" way out by having digital tools since we first figured out we could use computers to make art. Ultimately, it makes the same Photoshop editing abilities accessible to people who can't afford to shell out for a license/learn the skills. It's ultimately not any bigger of a deal than, say, Instagram or Snapchat filters, imo.

All of that said, I do not use any "AI" programs and have no intentions to do so. I also actively avoid interacting with content, individuals, and businesses that utilize LLMs/complete image generation software. People drawing inspiration from media and using available tools to create art in the likeness of a character, such as making their own custom Hatsune Miku doll (thanks, Yumeiro), is inherently transformative. Even the best image generation software is only ever going to be able to spit out images that are sufficiently similar to what it was trained on, which may not be directly analogous to recasting but is, in fact, very close to it. In a way, it's like the controversy surrounding "artists" who trace other people's art and post it as their own. Can it be useful for your own personal fun/learning? Sure, but it's going to be poorly received if you start claiming that clearly traced art pieces are your original creations.

If you want to feed an editing tool your images and have it edit out the joints or fix the light balance for you, no one is going to stop you and very few people are going to be upset that you had the program do it for you instead of doing it yourself. I do still feel individuals should disclose when AI tools are utilized as part of the creative process, regardless of the degree to which it was used. Images generated primarily or solely by AI should be discouraged for the same reason that we discourage sharing recasts on this forum.