AI for model generation

[lab-dad]

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

[Lawrence@NZFinescale]

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.

[Hauk]

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.

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.

[Lawrence@NZFinescale]

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 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.

[Hauk]

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...

[Rail and Tie]

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.

[Lawrence@NZFinescale]

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.

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.

[lab-dad]

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

[Lawrence@NZFinescale]

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

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...

[Hauk]

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

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.

[lab-dad]

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

[Lawrence@NZFinescale]

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.

[Bill Gill]

Lawrence, Those are good looking figures even at 1:64.

[Lawrence@NZFinescale]

Lawrence, Those are good looking figures even at 1:64.

I'll go blind painting the seams on 1/64 stockings!

[finescalerr]

I have learned a lot from this thread. Thank you for the clinic and comments. -- Russ