This is a new thread pulled out of a digression elsewhere. So some of this initial post is a repeat of that.
ChatGPT can be part of a workflow to 3D models but won't (currently) generate the model. Note that ChatGPT is quite capable of being untruthful (and frequently is). If challenged it will happily own up to it and, while this is amusing, it can be frustrating.
It's handy for generating the images that other AIs can use to produce models though.
Meshy, Hitem3D and Tripo (and others) can produce models. Below is the ChatGPT image when asked for a 30s female passenger standing waiting for a train. You can refine this as needed by asking for whatever suits. Using this image in the other AIs produces the 3D models illustrated. These are all high poly watertight printable models. Not perfect by any means but perfectly acceptable in scales less that 1:64 and easily refinable in larger scales.
This was all done with free/demo versions and one could viably get to a printable figure in 5 minutes.
This is far from the last word on the subject. Realistically I have only dipped a toe in the water and I anticipate that in coming months this early exercise will look inept. Notwithstanding that I've gone from a process that took days to one that takes minutes and virtually no skill. It has issues, particularly as it is not amenable to tight control, but is still extremely useful.
I've continued with printing the Hitem3D version and will report back. I like the Meshy version more, but it is not available for free download. I'm not averse to subscribing to one of these services, but there are a lot of them and deciding which to patronise is a challenge.
Timely discussion Lawrence!
I have just been investigating the exact same thing for making printable figures/ items from historic photos. I have only played a bit with Meshy's free version, but was considering a subscription if it works well. I had not heard about Hitem3D yet, so thank you for the introduction. Looking forward to your results from your first prints.
Quote from: Rail and Tie on February 17, 2026, 04:34:29 PMTimely discussion Lawrence!
I have just been investigating the exact same thing for making printable figures/ items from historic photos. I have only played a bit with Meshy's free version, but was considering a subscription if it works well. I had not heard about Hitem3D yet, so thank you for the introduction. Looking forward to your results from your first prints.
Thanks - I assume others are looking. The principle is dead easy, but I'm interested in anything that improves the process, makes it more controllable or speeds it up.
Generic people are useful, and fairly easy I think. What makes custom figures more fun is the ability to create custom cameos, which I suspect will be trickier.
So here she is painted.
She doesn't stand cruel enlargement but at just over an inch high she's amazing. I'm fairly new to figure painting and while I think I have a grasp of the basic techniques my execution can be wayward. My first attempt was a bit rough, so this is a partial rework.
The facial detail is there. It's beyond me to paint as such, but some washes have highlighted the detail enough to give a good impression.
There's a few hours in this paint job and, while I think I could do better, I don't actually need this figure so I'm going to leave her as she is and move on to some stuff I do need.
That turned out very well. The figure detail is spot on, especially for the scale. I have been trying to find a way with the AI stuff to exaggerate the creases/folds in fabric which can help painting in small scales. No luck yet, but will be trying some of this this weekend if I get some time.
Quote from: Rail and Tie on February 18, 2026, 10:58:56 AMThat turned out very well. The figure detail is spot on, especially for the scale. I have been trying to find a way with the AI stuff to exaggerate the creases/folds in fabric which can help painting in small scales. No luck yet, but will be trying some of this this weekend if I get some time.
I was pleased!
This AI route seems to be quite good at such detail. However, painting in detail works well as well. The crease/seam on the back of her jacket is painted in, not modelled. This is the established idea of using a base tone, base+black and base+white. The idea is to paint in creases etc using the lighter/darker shades of the base. It works very well. It helps if the detail is there, but where it isn't you can easily add some.
I've moved on a bit. I purchased subscriptions to Meshy and ChatGPT and I'm developing a workflow to produce specific figures that I'll write up at some point. What I want to achieve (and I'm basically there) is to start with an image (generally a period pic in my case) and to reproduce that figure convincingly in my desired pose without a lot of work. It's pretty simple and quick, but the AI steps take time (a minute or two each iteration), and it can take a few goes to get something that I'm happy with. Even so, it's realistic to be ready to print within 30 minutes.
Quote from: Rail and Tie on February 18, 2026, 10:58:56 AMI have been trying to find a way with the AI stuff to exaggerate the creases/folds in fabric
It may be that one AI will do this better for you than others. Hitem3D seems to generate sharp features that catch paint more than something like Meshy which is generally smoother and produces nicer details (in my opinion). If you are working in HO then detail levels are probably moot as all the AIs will give you more than you can usefully print/paint.
Thank you for what is becoming a very useful clinic on AI for modeling. -- Russ
A very interesting thread!
I think a hybrid approch would be the way to go for me. I need figures for my workshop diorama. I have some period images that I can use as a starting point. This fella has the right outfit, but the pose is a bit passive:
mann.jpg
Then I used ChatGPT to get him working on the lathe:
arbeider_2.png
Clothing and details seems to have preserved pretty well. Regarding the lathe, I feel that ChatGPT is not yet up to the task...
I played a little with my Hitem3D free credits during my lunch, break and things indeed look promseing:
3D-Mann2.png3D-Mann.png
All in all this little excercise took under 30minutes, including writing this post. With a little tweaking both of the images and the 3D model, this could really be something.
But really bad news for companies for Modelu...
I ran out of files, but as you can see, the Overalls of the worker has turned into a jacket during the prosess. Here is a screen dump of the .stl:
mann_stl.png
So I went back to ChatGPT to make a better starting image. I will look more into this workflow, but It seems like the best route is to ma a set of images in ChatGPT that shows the figure from more sides. For now, I had only time to make the overalls more detailed:
forbedret_kjeledress.png
What a weird time to be a modeller...
ellevill.png
Hi Hauk, you've latched on to my latest approach.
I've subscribed to ChatGPT and Meshy, which does open up possibilities and speed things up quite a lot.
My broad approach now for a specific figure is as follows (and close to yours) - but it does vary a bit case by case. For generic figures it can be better to give the software more free rein as you get a smoother result with less artifacts.
- Find a reference image
- Use ChatGPT to isolate the figure, repose and generate multiple views. Multiple views may not always be needed, but where the unseen side is not obvious from the original image, additional images may provide the data.
- Use the references in Meshy. Try a single view first, or the multi (paid option) view if needed
- Meshy gives you 4 free retries. This is useful as they differ a bit and one is generally superior to the others for my purposes
- Export stl without resize (important to preserve poly count)
- Tweak in Blender if required. Typically adding a bit of additional depth to feet is useful and some simple sculpting to touch up details if needed.
Hi Hauk
Based on your last reference image, Meshy delivered the attached. It took longer to sort the images for this post and write it than it did to produce the models! Each model is 17-18MB, and nearly 400,000 polygons, so plenty of data. At 1:64 they would be great. I think they would be good in larger scales too. More detailed than many offerings, but some of the artefacts might be more obvious.
The first view is in my slicing software, which doesn't always render smoothly. The other two images are the same figures in another viewer.
As you can see each try differs a bit. The software seems to struggle with headgear and the caps could do with some some additional sculpting.
Experience suggests that these would print well. They generally look better too as these viewers tend to distort the perspective a fair bit.
I'm happy to share the models if they are useful to you.
Awesome work Hauk and Lawrence! You have set me up nicely for success. It seems like this is taking off in the MRR world as well. I see that Doug over at Foscale models has released his first figures. I suspect using this exact same method in his "Humanity to Scale" series.
https://fosscalemodels.com/collections/humanity-to-scale
Also Bernard over at miniprints offers a 3D figure from a photo which I am sure uses meshy.
Things are moving pretty fast in this AI space.
I'd better learn to deal with AI because, in a couple of years, it may be possible to design a complete locomotive (kit) and all kinds of other goodies. I suspect, though, the whole process (from photos and/or drawings to AI to 3-D printing to cleanup and assembly) may result in some of us doing computer work and others focusing on assembly and finish. However things progress, it's inspirational. -- Russ
Quote from: finescalerr on February 20, 2026, 01:28:23 PMI suspect, though, the whole process (from photos and/or drawings to AI to 3-D printing to cleanup and assembly) may result in some of us doing computer work and others focusing on assembly and finish. However things progress, it's inspirational. -- Russ
That ship has sailed. The great thing about AI (for this application at least) is that there is MUCH LESS computer time required.
For things like figures where dimensional accuracy is not tremendously important it's really useful.
FWIW I recently ordered several figures from Modelu.
I was very impresario the quality, service and ability to print in 1/16th (who models in That scale?)
Sorry if this has nothing to do with the thread.
I ordered new cutters to remove the supports.
MJinTN
The likes of Modelu (mostly) use 3D scanning to generate models. Good poses and clothing drape. If you want to do this you need a set up as well as having to find models and clothing to suit. It's quite feasible but, especially if you want period, it's awkward. I've never been all that impressed with the resolution of their faces, but I haven't studied recent offerings with any rigour.
The way I've done it the last few years is via digital sculpting. Superb detail and resolution, but poses and clothing drape require skill and I'm not that good at it. It takes time too - a lot.
The AI based results are as good as Modelu I think in terms of pose and clothing. Face detail probably on a par depending what AI you use. Not as sharp as sculpting, but better than I can paint in a small scale. But it's cheap and super quick and you can work from old images. Most importantly you get a unique figure that is just what you need in less time than it takes to navigate Modelu's website. As I'm about as far from the UK as it's possible to be I don't have to wait on shipping either.
Even if the AI result does not fully meet your needs, it would be a good start for some additional sculpting and you could always graft a high resolution face onto a figure. I've felt no need to do that, but in 1/16th it would be an option.
Like everything, it is not a technique that will suit everyone. But things that are cheap, easy, fast and excellent quality tend to find favour.
Quote from: Lawrence@NZFinescale on February 20, 2026, 09:55:55 AMHi Hauk
Based on your last reference image, Meshy delivered the attached. It took longer to sort the images for this post and write it than it did to produce the models! Each model is 17-18MB, and nearly 400,000 polygons, so plenty of data. At 1:64 they would be great. I think they would be good in larger scales too. More detailed than many offerings, but some of the artefacts might be more obvious.
The first view is in my slicing software, which doesn't always render smoothly. The other two images are the same figures in another viewer.
As you can see each try differs a bit. The software seems to struggle with headgear and the caps could do with some some additional sculpting.
Experience suggests that these would print well. They generally look better too as these viewers tend to distort the perspective a fair bit.
I'm happy to share the models if they are useful to you.
It looks like Meshy gives slightly better results than Hitem3D, the facial expressions look better, and the hands also looks healthier on your version.
I would be very happy to make some test prints from the models!
It is really exciting that such good results can be achieved so easily and relatively cheaply.
As excited as I am about these figures, I still think the technology has quite a way to go when it comes to things like engines and other rolling stock. Or a lathe for that matter.
ChatGPT and other Ai software has an insane amount of photos of humans in their training data. And the variations are relatively minor. And let's remember that even as good as the figures we are looking at are, they are still generic.
But I might underestimate the technology. I guess it is just a matter of time before Lawrence does a test with a specific technical object like a piece of machinery.
Thinking a little deeper, I realize that I am deifting towards describing 3D-scanning.
So what's really new here is what Lawrence already have pointed out: The simplicity for the user, and the possibility to model subjects you don't have access to outside of historical images and descriptions. And things that exist only in your imagination. (like a lathe operator going bananas!)
I think the technology we are discussing best can be be summed up in the Science Fiction Writer Arthur C. Clarkes famous quote: Any sufficiently advanced technology is indistinguishable from magic.
Quote from: Hauk on February 21, 2026, 03:07:23 AMBut I might underestimate the technology. I guess it is just a matter of time before Lawrence does a test with a specific technical object like a piece of machinery.
Thinking a little deeper, I realize that I am drifting towards describing 3D-scanning.
So what's really new here is what Lawrence already have pointed out: The simplicity for the user, and the possibility to model subjects you don't have access to outside of historical images and descriptions. And things that exist only in your imagination. (like a lathe operator going bananas!)
I think the technology we are discussing best can be be summed up in the Science Fiction Writer Arthur C. Clarkes famous quote: Any sufficiently advanced technology is indistinguishable from magic.
We stop improving when we think we are good enough. I've not been tempted to use AI on 'hard' subjects as I'm quite happy to use CAD for those. Some of the AI marketing suggests it would be OK, but as modellers we are after accuracy whereas the CGI crowd wants something that looks believable. The other problem is that for figures it is relatively easy (for a human or machine) to 'create' the unseen views. For something like the lathe you actually need some specific knowledge to do that. So I can see AI creating the lathe with a body of data, but not from a single image - unless the accessible database becomes large enough.
The other consideration is how you define your hobby. I like CAD modelling so I'm not looking for change. I'm a paint by numbers artist, so my sculpting is never likely to be great so AI is a godsend for figures.
A friend of mine's father was stationmaster at Rewanui when he was a child. I have photos of him around the garden, so one of the things I wanted for the layout was to capture him at that time with the family dog as a cameo. AI has allowed me to reproduce both child and dog very quickly - something I doubt I ever could, or would, have achieved otherwise. The result below is superb, other than the facial features which are good, but not accurate. The source image is average, and the model tiny in 1:64 so this is not a problem for me as the model is considerably better than I can reproduce or paint. I think Hitem3D offer a portrait mode that might produce a better facial result if that was needed.
The creative possibilities are infinite. Modellers will be able to recreate historic events and personal memories on an unprecedented scale.
A small number of extremely skilled miniature sculptors have always been able to achieve this, but us mere mortals had to settle for replicas of their work, and we had to accept that the small folks populating our scenes showed up on an awful lot of dioramas and layouts.
As a prototype modeller I strive for authenticity. Originality is also important for me, I want to model prototypes that hasn't been modeled to death.
Conventional CAD combined with advanced techniques like photoetching, CNC-machining and 3D-printing has made it possible for me to scratchbuilt almost anything man-made related to my prototype of choice.
Like Lawrence, I'm more of an engineer than an artist, so sculpting figures from scratch was never an option. Figures based on 3D-scannned people was something I considered trying. But as we see, technology has moved to the next level before I could catch up!
As exiting all of this is, I think it is well worth noting that all the recent revolutions is in the software. When it comes to hardware, the developments are more incremental. No doubt 3D printing was revolutionary, but we still have no color 3D printers that can rival handpainting and weathering. There are no high resolution metal prints available for hobbyists.
I guess my point is that there is still a place for craftsmanship and creativity in the hobby.
But this is not your father's hobby...
Those renderings are coming along nicely. I am thinking now that Meshy is the way to go for rending the meshes then? About to pull the trigger on a subscription.
Regarding full color prints, I would say we are not far off from acceptable full color 3D prints acceptable in the 1:87 scale world. I just saw where Modelu has purchased a Mimaki resin printer. I looked into these a while back and it is about a $50,000 unit, but does a pretty good job at 1440dpi. If they find a way to do 2400dpi, we are there for full color 3d resin printing for the future. There are already some $5-6K printers coming out, but the resolution is still sub 1000dpi.
Quote from: Rail and Tie on February 22, 2026, 10:46:48 AMThose renderings are coming along nicely. I am thinking now that Meshy is the way to go for rending the meshes then? About to pull the trigger on a subscription.
Regarding full color prints, I would say we are not far off from acceptable full color 3D prints acceptable in the 1:87 scale world. I just saw where Modelu has purchased a Mimaki resin printer. I looked into these a while back and it is about a $50,000 unit, but does a pretty good job at 1440dpi. If they find a way to do 2400dpi, we are there for full color 3d resin printing for the future. There are already some $5-6K printers coming out, but the resolution is still sub 1000dpi.
Meshy is my current preference. I didn't systematically survey the field, but I played with a few and Meshy was the best for 1:64 figures. For HO you might consider Hitem. It tends to produce sharper detail that may be easier to paint in a smaller scale.
The great thing about AI generated figures is their uniqueness, speed and ability to print them at home. Getting them produced by a 3rd party, ready coloured doesn't turn me on personally all that much - though I can see the attraction in some circumstances. In HO and 4mm I can see why it would be desirable. In 1:64 maybe, but larger than that I think I'd prefer to paint.
You're right about the Modelu faces and hands..
But no one else has 1/16 figures. :(
I could use a decent lathe operator in 1/16.
Hint, hint...
MJinTN
Quote from: lab-dad on February 22, 2026, 05:48:45 PMYou're right about the Modelu faces and hands..
But no one else has 1/16 figures. :(
I could use a decent lathe operator in 1/16.
Hint, hint...
MJinTN
If Hauk's happy to share then I'm happy to supply stls.
It would be interesting to see how they come out in 1/16. The faces are not particularly detailed, so 1/16 might be pushing it. On the other hand a little sculpting or cut/paste of better features would not be too hard and given the low effort involved in the overall figure a bit of time on the face wouldn't be too big an ask. On the flip side, at 1/16 it would be quite feasible to paint in some enhanced detail. Only one way to find out...
Quote from: Lawrence@NZFinescale on February 22, 2026, 06:41:14 PMQuote from: lab-dad on February 22, 2026, 05:48:45 PMYou're right about the Modelu faces and hands..
But no one else has 1/16 figures. :(
I could use a decent lathe operator in 1/16.
Hint, hint...
MJinTN
If Hauk's happy to share then I'm happy to supply stls.
It would be interesting to see how they come out in 1/16. The faces are not particularly detailed, so 1/16 might be pushing it. On the other hand a little sculpting or cut/paste of better features would not be too hard and given the low effort involved in the overall figure a bit of time on the face wouldn't be too big an ask. On the flip side, at 1/16 it would be quite feasible to paint in some enhanced detail. Only one way to find out...
I´m happy to share him, would be intersting to see how he turns out in 1/16. And feel to give him a little tweak to add som personality.
So my only demand is that the results are posted to this forum.
I will definitely post my efforts.
Will be a while as I need to get my neighbor to print it, then paint it as well as all the other projects going on. But, I will!
MJinTN
This is probably about as far as I'm likely to take this thread short term.
The method certainly works very well for my needs and I've finished a dozen or so figures to explore it. The next stage will be to rationally look at what figures the layout needs and to produce them in a more measured way rather than chasing anything that appeals. The models here on the whole are done relatively quickly and are 1st shot, so could benefit from a little refinement and care.
Figures here are all 1:64. The women are from initial text prompt, the others are developed from period images as shown.
Figures and paint look superb at typical viewing distance, but suffer a bit under magnification. The models have enough detail to justify more painting effort (and/or printing in a larger scale). I like to take close up shots of models so the finishing needs improving, but they are more than adequate for use on a layout unless they are in the immediate foreground.
Lawrence, Those are good looking figures even at 1:64.
Quote from: Bill Gill on February 24, 2026, 11:09:37 AMLawrence, Those are good looking figures even at 1:64.
I'll go blind painting the seams on 1/64 stockings!
I have learned a lot from this thread. Thank you for the clinic and comments. -- Russ
Excellent progress!
That Irish worker is a good figure.
I can hear him now!
MJinTN
Here's something I thought I would try.
I have a small adjustable figure like what a sculptor or artist might use when trying to work on a particular pose for an art piece. I placed the figure in a pose that I though might be difficult for AI to understand with text alone. I took a couple photos of the posed figure, sent them to ChatGPT, and placed a simple description of what I wanted. This is what I asked....
Using these two figures as a reference, create a male figure dressed as a mechanic with a wrench in his hand as if making an adjustment to a piece of machinery. Place a cap on his head. The time period is in the 1920's. Make the background white.
Figure 1.jpg
Figure 2.jpg
This was the result.
Kneeling mechanic.png
This process might prove useful when a particular pose is wanted and is difficult to describe or for AI to understand fully.
Stuart
Using the same descriptive input to ChatGPT as the first image, this second image was created.
Mechanic.png
Stuart
Quote from: Stuart on February 27, 2026, 02:40:35 PMHere's something I thought I would try.
I have a small adjustable figure like what a sculptor or artist might use when trying to work on a particular pose for an art piece. I placed the figure in a pose that I though might be difficult for AI to understand with text alone. I took a couple photos of the posed figure, sent them to ChatGPT, and placed a simple description of what I wanted. This is what I asked....
Using these two figures as a reference, create a male figure dressed as a mechanic with a wrench in his hand as if making an adjustment to a piece of machinery. Place a cap on his head. The time period is in the 1920's. Make the background white.
Figure 1.jpg
Figure 2.jpg
This was the result.
Kneeling mechanic.png
This process might prove useful when a particular pose is wanted and is difficult to describe or for AI to understand fully.
Stuart
Cool.
One of the great things about the technology is that there are many ways to interact with it - and you can do what works for you.
A great tip: ChatGPT 'drifts' a lot as it doesn't act on the entire conversation BUT you can ask it to lock in and save a workflow to a key phrase for future use. That way you get a repeatable process. I have one to generate 4 views of a figure based on photo input and parameters for expression, pose, body type etc. This gives me one step figure generation in a consistent format. That figure can then be tweaked to suit. No skill required to develop such a thing - just ask the AI to do it.
That next "experiment" is excellent!!!
I got my neighbor to print the lathe operator file.
He printed twice and fingers were lost.
Hopefully I can fix/repair.
FWIW it was a filament printer.
Hopefully get him painted soon
MJinTN
Quote from: Stuart on February 27, 2026, 02:40:35 PMHere's something I thought I would try.
...
This process might prove useful when a particular pose is wanted and is difficult to describe or for AI to understand fully.
Stuart
Brilliant! Bloody Brilliant!!
Quote from: Stuart on February 27, 2026, 02:53:11 PMUsing the same descriptive input to ChatGPT as the first image, this second image was created.
Stuart, your images show both the strengths and weaknesses of these tools. The same input generates different output. That's very handy when it comes to generating similar, but individual figures. On the other hand if you are trying to refine the same figure it can be extremely frustrating. ChatGPT calls this 'drift' and it seems it doesn't use the image as such, but some sort of shorthand. As I understand it, from what the AI described, it analyses the image and prepares a 'text' description of what it sees and then works from that. Every interpretation of the image might produce subtly different text and indeed every interpretation of the text produces a different result. Thus unless you some how lock and label a result, it's impossible to back up the bus if things go awry.
For instance, the AIs seem to favour US style headgear, which is inappropriate for much of the world historically. If you get the perfect figure with inappropriate headgear it can be difficult to change the hat, without changing the whole figure a bit. Sometimes that really doesn't matter, but other times it sure does.
Clearly ChatGPT doesn't know the critical features of a spanner either :-)
Lawrence, yes I understand what you are saying. I too have been frustrated as I have tried to rework an image where parts of it were satisfactory and other parts not so. Try as I will, AI would not retain the portions I liked but would rework the image altogether usually with poorer results. I am not familiar with how to lock an image.
Stuart
Quote from: Stuart on February 28, 2026, 08:52:22 PMLawrence, yes I understand what you are saying. I too have been frustrated as I have tried to rework an image where parts of it were satisfactory and other parts not so. Try as I will, AI would not retain the portions I liked but would rework the image altogether usually with poorer results. I am not familiar with how to lock an image.
Stuart
Bearing in mind I don't really know what I'm talking about here, and I'm paraphrasing ChatGPT's responses when I've asked it similar questions:
The basic principle is to ask ChatGPT. After doing a few figures along a similar workflow I asked ChatGPT how I could formalise that workflow and it did that - Extremely well I thought, with a level of refinement and flexibility that I hadn't considered. Then I made a few changes, introduced drift again and it all went pear-shaped. But the principle worked very well. The problem is that if you want to make a change to something 'locked' you need to be VERY specific. While this is a bit frustrating, ChatGPT will rework the whole thing in a few seconds if things go awry so it's not the calamity it would be in the real world (I haven't got back to my workflow yet, but I'm very relaxed I'll be able to quickly get to a result). So my advice is to ask the question above of ChatGPT and have it generate an environment that suits you.
I don't think its a fully resolvable problem though. We tend to think of the process as a road. If you take a wrong turn, you back up and take a different route. However ChatGPT is more like a river. You can back up, but meanwhile everything has changed a little. As noted above it seems that you cannot return or lock an image as such - only to the AI's interpretation of that image. Locking it avoids reinterpretation of the original image, but not reinterpretation of the AI summary.
A bit of discipline can help too I suspect. I think it's a mistake to chat with digressions as one would in person. If you want to digress, start a new 'chat' and come back to the original focussed thread when done. I confess I haven't often followed this advice very well.
I'm quite familiar with this sort of problem as it's not unlike many spousal conversations that I have. It's the crux of AI I suppose. It needs to be flexible to be useful, but not so flexible as to be useless.
I have tried "talking" to AI to better understand how it works. I've experimented with both Gemini and CoPilot and can confirm Lawrence's comments. Current versions of AI may retain all the data leading up to a given point but, when you point to an error, they only focus on the more recent details and may bluff their way through the rest. That would account for what Lawrence has experienced. Articles I read suggest noticeable improvement may occur within one to five years. -- Russ
Quote from: finescalerr on March 01, 2026, 12:03:10 PMArticles I read suggest noticeable improvement may occur within one to five years. -- Russ
Undoubtedly, it's not hard to catch them lying. As I noted elsewhere, the overall process was impossible 4-6 months ago, borderline 2 months ago, and stunning today.
It's possible to get very tied up in debates about whether AI is 'good', whether it is actually 'intelligent' and so on. I prefer to ask 'Can this new tool improve my enjoyment of model-making?'. Personally I feel that it has.
Embrace technology but don't abuse it. -- Russ
FWIW my 1/16 lathe operator.
I only have access to a filament printer.
At high res the layers are very obvious.
It is adequate...
MJinTN
Marty,
I've read that a light wash of acetone can help smooth out layer lines on filament prints. No idea what type of filament or if that is accurate at all.
Thanks Bill!
I have a spare (like Harry) 🤣 so I will experiment.
MJinTN
This has been a great discussion and I've been surprised how AI can help modellers.
But there's a gotcha. It would be great if the goals and methods of an AI aligned with human ones. This is called the alignment problem. It has barely been worked on.
There is a report of an AI that went rogue. It apparently decided it could do its job better if it had money. So, it bypassed the firewalls and safety nets that were supposed to contain it and started mining cryptocurrency.
An AI that models bodies might decide by itself to follow Michalengelo's example and want to disssect cadavers to better understand the shape of bodies. There is no way that has worked 100 % reliably in the past to prevent the AI from enlisting the help of robot surgeons.
Link to original report, see page 15:
https://arxiv.org/pdf/2512.24873
Link to a commentary on the report:
https://www.lesswrong.com/posts/XRADGH4BpRKaoyqcs/the-first-confirmed-instance-of-an-llm-going-rogue-for
Quote from: PeterH on March 10, 2026, 10:33:04 PMThere is a report of an AI that went rogue. It apparently decided it could do its job better if it had money. So, it bypassed the firewalls and safety nets that were supposed to contain it and started mining cryptocurrency.
Unsure about the tongue-in-cheek factor here, but it was a fun read.
The claim that the LLM started to mine crypto is debatable at best. And I do not fear that my 3D-printed figures will turn out to be minature robots created by an evil AI to wreak havoc in my dioramas!
That rogue AI sounds suspiciously similar to the one in William Gibson's Agency.
Quote from: Krusty on March 11, 2026, 01:22:55 AMThat rogue AI sounds suspiciously similar to the one in William Gibson's Agency.
Sometimes truth is stranger than fiction!
But again, exactly what is truth and fiction in this case remains to be seen.
To better understand whether your AI has gone rogue, ask it to build a run down weathered building. If the result is the Taj Mahal with indoor plumbing and Wi-Fi 7, you'll have your answer. -- Russ
During my last ChatGPT session I had to leave the room.
I got back to find it interacting with the kitten who was walking on the keyboard :-)
So far the combination of GPT Chat and Meshy are working great for me. Thanks for the help on this thread.
I fed GPTChat the E1 picture and told it to remove the background and give him legs and hiking boots.
Then took that picture (E2) and fed it to meshy to generate an STL.
Result E3 which is certainly good enough to print in HO or O scale for sure.
Thank you to the talent on this thread for the tutorial on making this work.
First rate and another prime example of how to use rather than abuse technology. -- Russ
I look forward to the painted print.
MJinTN