_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI Hunyuan3D 2.0 â High-Resolution 3D Assets Generation
xgkickt wrote 2 hours 44 min ago:
Any user-generated content system suffers from what we call âthe
penis problemâ.
geuis wrote 4 hours 47 min ago:
Question related to 3D mesh models in general: has any significant work
been done on models oriented towards photogrammetry?
Case in point, I have a series of photos (48) that capture a small
statue. The photos are high quality, the object was on a rotating
platform. Lighting is consistent. The background is solid black.
These normally are ideal variables for photogrammetry but none of the
various common applications and websites do a very good job creating a
mesh out of it that isn't super low poly and/or full of holes.
I've been casually scanning huggingface for relevant models to try out
but haven't really found anything.
Joel_Mckay wrote 1 hour 9 min ago:
COLMAP + CloudCompare with a good CUDA GPU (more VRAM is better)
card will give reasonable results for large textured objects like
buildings. Glass/Water/Mirror/Gloss will need coated to scan, dry
spray on Dr.scholls foot deodorant seems to work fine for our object
scans.
There are now more advanced options than Gaussian splatting, and
these can achieve normal playback speeds rather than hours of
filtering. I'll drop a citation if I recall the recent paper and
example code. However, note this style of 3D scene recovery tends to
be heavily 3D location dependent.
Best of luck, =3
troymc wrote 4 hours 9 min ago:
Check out RealityCapture [1]. I think it's what's used to create the
Quixel Megascans [2]. (They're both under the Epic corporate umbrella
now.) [1]
URI [1]: https://www.capturingreality.com/realitycapture
URI [2]: https://quixel.com/megascans/
jocaal wrote 4 hours 30 min ago:
Recently, a lot of development in this area has been in gaussian
splatting and from what I have seen, the new methods are super
effective. [1]
URI [1]: https://en.wikipedia.org/wiki/Gaussian_splatting
URI [2]: https://www.youtube.com/watch?v=6dPBaV6M9u4
geuis wrote 3 hours 48 min ago:
Yeah some very impressive stuff with splats going on. But I haven't
seen much about going from splats to high quality 3D meshes. I've
tried one or two with pretty poor results.
tzumby wrote 4 hours 31 min ago:
Iâm not an expert, only dabbled in photogrammetry, but it seems to
me that the crux of that problem is identifying common pixels across
images in order to sort of triangulate a point in the 3D space. It
doesnât sound like something an LLM would be good at.
godelski wrote 6 hours 11 min ago:
As with any generative model, trust but verify. Try it yourself.
Frankly, as a generative researcher myself, there's a lot of reason to
not trust what you see in papers and pages.
They link a Huggingface page (great sign!): [1] I tried to replicate
the objects they show on their project page ( [2] ).
The full prompts exist but are truncated so you can just inspect the
element and grab the text.
Here's what I got
Leaf
PNG: [4] /8HDL.png
GLB: [4] /8HD9.glb
Guitar
PNG: [4] /8HDf.png other view: [4] /8HDO.png
GLB: [4] /8HDV.glb
Google Translate of Guitar:
Prompt: A brown guitar is centered against a white background,
creating a realistic photography style. This photo captures the culture
of the instrument and conveys a tranquil atmosphere.
PNG: [4] /8HDt.png and [4] /8HDv.png
Note: Weird thing on top of guitar. But at least this time the
strings aren't fusing into sound hole.
I haven't tested my own prompts or the google translation of the
Chinese prompts because I'm getting an over usage error (I'll edit
comment if I get them). That said, these look pretty good. The paper
and page images definitely look better, but these aren't like Stable
Diffusion 1 paper vs Stable Diffusion 1 reality.
But these are long and detailed prompts. Lots of prompt engineering.
That should raise some suspicion. Real world has higher variance and
let's get an idea how hard it is to use. So let's try some simpler
things :)
Prompt: A guitar
PNG: [4] /8HDg.png
Note: Not bad! Definitely overfit but does that matter here? A bit
too thick for a electric guitar but too thin for acoustic.
Prompt: A Monstera leaf
PNG: [4] /8HD6.png [4] /8HDl.png [4] /8HDU.png
Note: A bit wonkier. I picked this because it looked like the leaf
in the example but this one is doing some odd things.
It's definitely a leaf and monstera like but a bit of a
mutant.
Prompt: Mario from Super Mario Bros
PNG: [4] /8Hkq.png
Note: Now I'm VERY suspicious....
Prompt: Luigi from Super Mario Bros
PNG: [4] /8Hkc.png [4] /8HkT.png [4] /8HkA.png
Note: Highly overfit[0]. This is what I suspected. Luigi isn't just
tall Mario.
Where is the tie coming from? The suspender buttons are all
messed up.
Really went uncanny valley here. So this suggests we're
really brittle.
Prompt: Peach from Super Mario Bros
PNG: [4] /8Hku.png [4] /8HkM.png
Note: I'm fucking dying over here this is so funny. It's just a
peach with a cute face hahahahaha
Prompt: Toad from Super Mario Bros
PNG: [4] /8Hke.png [4] /8Hk_.png [4] /8HkL.png
Note: Lord have mercy on this toad, I think it is a mutated
Squirtle.
Paper can be found here (the arxiv badge on the page leads to a pdf in
the repo, which github is slow to render those): [3] (If you want to
share images like I did all I'm doing is `curl -F'file=@foobar.png' [4]
`)
[0] Overfit is a weird thing now. Maybe it doesn't generalize well, but
sometimes that's not a problem. I think this is one of the bigger
lessons we've learned with recent ML models. My viewpoint is "Sometimes
you want a database with a human language interface. Sometimes you want
to generalize". So we have to be more context driven here. But
certainly there are a lot of things we should be careful about when
we're talking about generation. These things are trained on A LOT of
data. If you're more "database-like" then certainly there's potential
legal ramifications...
Edit: For context, by "look pretty good" I mean in comparison to other
works I've seen. I think it is likely a ways from being useful in
production. I'm not sure how much human labor would be required to fix
the issues.
URI [1]: https://huggingface.co/spaces/tencent/Hunyuan3D-2
URI [2]: https://3d-models.hunyuan.tencent.com/
URI [3]: https://arxiv.org/abs/2411.02293
URI [4]: https://0x0.st
godelski wrote 3 hours 49 min ago:
Ops ran out of edit time when I was posting my last two
Prompt: A hawk flying in the sky
PNG: https://0x0.st/8Hkw.png
https://0x0.st/8Hkx.png
https://0x0.st/8Hk3.png
Note: This looks like it would need more work. I tried a few
birds and generic too. They all seem to have similar form.
Prompt: A hawk with the head of a dragon flying in the sky and
holding a snake
PNG: https://0x0.st/8HkE.png
https://0x0.st/8Hk6.png
https://0x0.st/8HkI.png
https://0x0.st/8Hkl.png
Note: This one really isn't great. Just a normal hawk head. Not
how a bird holds a snake either...
This last one is really key for judging where the tech is at btw.
Most of the generations are assets you could download freely from the
internet and you could probably get better ones by some artist on
fiver or something. But the last example is more our realistic use
case. Something that is relatively reasonable, probably not in the
set of easy to download assets, and might be something someone wants.
It isn't too crazy of an ask given Chimera and how similar a dragon
is to a bird in the first place, this should be on the "easier" end.
I'm sure you could prompt engineer your way into it but then we have
to have the discussion of what costs more a prompt engineer or an
artist? And do you need a prompt engineer who can repair models?
Because these look like they need repairs.
This can make it hard to really tell if there's progress or not. It
is really easy to make compelling images in a paper and beat
benchmarks while not actually creating a something that is __or will
become__ a usable product. All the little details matter. Little
errors quickly compound... That said, I do much more on generative
imagery than generative 3d objects so grain of salt here.
Keep in mind: generative models (of any kind) are incredibly
difficult to evaluate. Always keep that in mind. You really only have
a good idea after you've generated hundreds or thousands of samples
yourself and are able to look at a lot with high scrutiny.
BigJono wrote 3 hours 26 min ago:
Yeah, this is absolutely light years off being useful in
production.
People just see fancy demos and start crapping on about the future,
but just look at stable diffusion. It's been around for how long,
and what serious professional game developers are using it as a
core part of their workflow? Maybe some concept artists? But
consistent style is such an important thing for any half decent
game and these generative tools shit the bed on consistency in a
way that's difficult to paper over.
I've spent a lot of time thinking about game design and
experimenting with SD/Flux, and the only thing I think I could even
get close to production that I couldn't before is maybe an MTG
style card game where gameplay is far more important than graphics,
and flashy nice looking static artwork is far more important than
consistency. That's a fucking small niche, and I don't see a lot of
paths to generalisation.
godelski wrote 2 hours 27 min ago:
Yeah the big problem I have with my field is that there seems to
be stronger incentives to be chasing benchmarks and making things
look good than there is to actually solve the hard problems.
There is a strong preference for "lazy evaluation" which is too
dependent on assuming high levels of ethical presentation and due
diligence. I find it so problematic because this focus actually
makes it hard for people to publish who are tackling these
problems. Because it makes the space even noisier (already
incredibly noisy by the very nature of the subject) and then it
becomes hard to talk about details if they're presumed solved.
I get that we gloss over details, but if there's anywhere you're
allowed to be nuanced and be arguing over details should it not
be in academia?
(fwiw, I'm also very supportive of having low bars to
publication. If it's void of serious error and plagiarism, it is
publishable imo. No one can predict what is important or
impactful, so we shouldn't even play that game. Trying to decide
if it is "novel" or "good enough for " is just idiotic and breeds
collusion rings and bad actors)
keyle wrote 5 hours 37 min ago:
Thanks for this. The results are quite impressive, after trying it
myself.
Kelvin506 wrote 5 hours 39 min ago:
The first guitar has one of the strings end at the sound hole, and
six tuning knobs for five strings.
The second has similar problems: it has tuning knobs with missing
winding posts, then five strings becoming four at the bridge. It also
has a pickup under the fretboard.
Are these considered good capability examples?
godelski wrote 4 hours 48 min ago:
I take back a fair amount of what I said.
It is pretty good with some easier assets that I suspect there's
lots of samples of (and we're comparing to other generative models,
not to what humans make. Humans probably still win by a good
margin). But when moving out of obvious assets that we could easily
find, I'm not seeing good performance at all. Probably a lot can be
done with heavy prompt engineering but that just makes things more
complicated to evaluate.
denkmoon wrote 6 hours 18 min ago:
For the AI un-initiated; is this something you could feasibly run at
home? eg on a 4090? (How can I tell how "big" the model is from the
github or huggingface page?)
swframe2 wrote 29 min ago:
I tried using Hunyuan3D-2 on a 4090 GPU. The Windows install
encountered build errors, but it worked better on WSL Ubuntu. I first
tried it with CUDA 11.3 but got a build error. Switching to CUDA 12.4
worked better. I ran it with their demo image but it reported that
the mesh was too big. I removed the mesh size check and it ran fine
on the 4090. It is a bit slow on my i9 14k with 128G of memory.
(I previously tried the stability 3d models: [1] and this seems
similar in quality and speed)
URI [1]: https://stability.ai/stable-3d
sorenjan wrote 6 hours 8 min ago:
The hunyuan3d-dit-v2-0 model is 4.93 GB. ComfyUI is on their roadmap,
might be best to wait for that, although it doesn't look complicated
to use in their example code.
URI [1]: https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan...
MikeTheRocker wrote 6 hours 42 min ago:
Generative AI is going to drive the marginal cost of building 3D
interactive content to zero. Unironically this will unlock the
metaverse, cringe as that may sound. I'm more bullish than ever on
AR/VR.
PittleyDunkin wrote 5 hours 17 min ago:
Maybe eventually. Based on this quality I don't see this happening
any time in the near future.
taejavu wrote 6 hours 2 min ago:
Jeez I'd love to know what Apple's R&D debt on Vision Pro is, based
on current sales to date. I really really hope they continue to push
for a headset that's within reach of average people but the hole must
be so deep at this point I wouldn't be surprised if they cut their
losses.
EncomLab wrote 5 hours 38 min ago:
As Carmack pointed out the problem with AR/VR right now - it's not
the hardware, it's the software. Until the "visicalc" must have
killer app shows up to move the hardware, there is little incentive
for general users to make the investment.
PittleyDunkin wrote 5 hours 15 min ago:
> As Carmack pointed out the problem with AR/VR right now - it's
not the hardware, it's the software.
The third option is peoples' expectation for AR/VR itself: it
could be a highly niche and expensive industry and unlikely to
grow to the general population.
jsheard wrote 6 hours 30 min ago:
I can only speak for myself, but a Metaverse consisting of infinite
procedural slop sounds about as appealing as reading infinite LLM
generated books, that is, not at all. "Cost to zero" implies drinking
directly from the AI firehose with no human in the loop (those cost
money) and entertainment produced in that manner is still dire, even
in the relatively mature field of pure text generation.
bufferoverflow wrote 3 hours 39 min ago:
Minecraft is procedurally generated slop, yet it's insanely
popular.
chii wrote 1 hour 30 min ago:
Not all procedurally generated things are slop, and not all slop
are made via procedural generation.
And popularity has nothing to do with private, subjective quality
evaluations of the individual (aka, what someone calls slop might
be picasso to another), but with objective, public evaluations of
the product via purchases.
delian66 wrote 43 min ago:
What is your definition of slop?
jdietrich wrote 4 hours 5 min ago:
I can only speak for myself, but a large and growing proportion of
the text I read every day is LLM output. If Claude and Deepseek
produce slop, then it's a far higher calibre of slop than most
human writers could aspire to.
noch wrote 4 hours 23 min ago:
> a Metaverse consisting of infinite procedural slop sounds about
as appealing as reading infinite LLM generated books
Take a look at the ImgnAI gallery ( [1] ) and tell me: can you
paint better and more imaginatively than that? Do you know anyone
in your immediate vicinity who can?
Read this satirical speech by Claude, in French [2] ) and in
English ( [3] ) and tell me: can you write fiction more
entertaining or imaginative than that? Is there someone in your
vicinity who can?
Perhaps that's mundane, so is there someone in your vicinity who
can reason about a topic in mathematics/physics as well as this:
[4] ?
Probably your answer is "yes, obviously!" to all the above.
My point: deep learning works and the era of slop ended ages ago
except that some people are still living in the past or with some
cartoon image of the state of the art.
> "Cost to zero" implies drinking directly from the AI firehose
with no human in the loop
No. It means the marginal cost of production tends towards 0. If
you can think it, then you can make it instantly and iterate a
billion times to refine your idea with as much effort as it took to
generate a single concept.
Your fixation on "content without a human directing them" is
bizarre and counterproductive. Why is "no human in the loop" a
prerequisite for productivity? Your fixation on that is confounding
your reasoning.
URI [1]: https://app.imgnai.com/
URI [2]: https://x.com/pmarca/status/1881869448275177764
URI [3]: https://x.com/pmarca/status/1881869651329913047
URI [4]: https://x.com/hsu_steve/status/1881696226669916408
chii wrote 1 hour 27 min ago:
> fixation on that is confounding your reasoning.
it is a fixation based on the desire that they themselves
shouldn't be rendered economically useless in the future. Then
the reasoning come about post-facto from that desire, rather than
from any base principle of logic.
Most, if not all, that are somewhat against the advent of AI are
like the above in some way or another.
nice_byte wrote 2 hours 31 min ago:
> can you paint better and more imaginatively than that?
the fact that you are seriously asking this question says a lot
about your taste.
Philpax wrote 3 hours 0 min ago:
> Take a look at the ImgnAI gallery ( [1] ) and tell me: can you
paint better and more imaginatively than that?
So while I generally agree with you, I think this was a bad
example to use: a lot of these are slop, with the kind of AI
sheen we've come to glaze over. I'd say less than 20% are
actually artistically impressive / engaging / thought-provoking.
URI [1]: https://app.imgnai.com/
esperent wrote 2 hours 32 min ago:
This is a better AI gallery (I sorted all images on the site by
top from this year). [1] There's still plenty of slop in there,
and it would be a better gallery of if there was a way to
filter out anime girls. But it's definitely higher than 20%
interesting to me.
The closest similar community of human made art is this: [2]
Although unfortunately they've decided to allow AI art there
too so it makes comparison harder. Also, I couldn't figure out
how to get the equivalent list (top/year). But I'd say I find
around the same amount interesting. Most human made art is slop
too.
URI [1]: https://civitai.com/images
URI [2]: https://www.deviantart.com/
deadbabe wrote 5 hours 31 min ago:
I think youâre being short sighted. Imagine feeding in your
favorite TV shows to a generative AI and being able to walk around
in the world and talk to characters or explore it with other
people.
xgkickt wrote 2 hours 45 min ago:
The trademark/copyright issues of making that both a reality and
an income stream are as yet unsolved.
slt2021 wrote 4 hours 30 min ago:
do you find it interesting talking to NPCs in games?
deadbabe wrote 2 hours 58 min ago:
Talking to NPCs in games is really just reading dialog written
by humans.
If you could actually talk to NPCs as in get their thoughts
about the world and ask open ended questions, thatâd be very
interesting.
bschwindHN wrote 4 hours 40 min ago:
That's still AI slop, in my opinion.
deadbabe wrote 2 hours 57 min ago:
Everything will be AI slop to you.
There will never be a point where AI creates something
incredible and you are like wow I prefer this AI stuff over
human made slop.
bschwindHN wrote 2 hours 51 min ago:
Yes, because if someone has a tool that creates "something
incredible", then everyone will be able to generate
"something incredible" and then it all becomes not
incredible.
It's like having god-mode in a game, it all becomes boring
very quickly when you can have whatever you want.
chii wrote 1 hour 21 min ago:
> everyone will be able to generate "something incredible"
and then it all becomes not incredible.
no, that's just your standard moving up.
There is an absolute scale for which you can measure, and
ai is approaching a point where it is an acceptable level.
Imagine if you applied your argument to quality of life -
it used to be that nobody had access to easy, cheap clean
drinking water. Now everybody has access to it. Is it not
an incredible achievement, rather than it not being
incredible just because it is common?
That quote from the movie "the incredibles", where the
villain claims that if everybody is super, then nobody is,
was your gist of the argument. And it is a childish one
imho.
bschwindHN wrote 47 min ago:
It is equally childish to compare the engineering of our
modern water and plumbing systems with the automated
generation of virtual textured polygons.
People don't get tired of good clean water because we
NEED it to survive.
But oh, another virtual world entirely thought up by a
machine? Throw it on the pile. We're going to get bored
of it, and it will quickly become not incredible.
chii wrote 28 min ago:
> we NEED it to survive.
plenty of people in the world still drink crappy water,
and they survive.
You don't _need_ it, you want it, because it's much
more comfortable.
But when something becomes a "need" as you described
it, you think of it differently. Just like how you
don't _need_ electricity to survive, but it's so
ingrained that you now think of it as a need.
> We're going to get bored of it, and it will quickly
become not incredible.
exactly, but i have already said this in my original
post - your standards just moved up.
hex4def6 wrote 5 hours 32 min ago:
I think it has its place.
For 'background filler' I think it makes a lot of sense; stuff
which you don't need to care about, but whose absence can make
something feel less real.
To me, this takes the place / augments procedural generation stuff.
NPC crowds in which none of the participants are needed for the
plot, but in which you can have unique clothing / appearance /
lines is not "needed" for a game, but can flesh it out when done
thoughtfully.
Recall the lambasting Cyberpunk 2077 got for its NPCs that cycled
through a seemingly very limited number of appearances, to the
point that you'd see clones right next to each other. This would
solve that sort of problem, for example.
MikeTheRocker wrote 5 hours 43 min ago:
IMO current generation models are capable of creating significantly
better than "slop" quality content. You need only look at
NotebookLM output. As models continue to improve, this will only
get better. Look at the rate of improvement of video generation
models in the last 12-24 months. It's obvious to me we're rapidly
approaching acceptable or even excellent quality on-demand
generated content.
modeless wrote 1 hour 35 min ago:
NotebookLM is still slop. I recommend feeding it your resume and
any other online information about you. It's kind of fun to hear
the hosts butter you up, but since you know the subject well you
will quickly notice that it is not faithful to the source
material. It's just plausibly misleading.
deeznuttynutz wrote 5 hours 29 min ago:
This is exactly while I'm building my app now with the
expectation that these assets will be exponentially better in the
short term.
jsheard wrote 5 hours 38 min ago:
I feel like you're conflating quality with fidelity. Video
generation models have better fidelity than they did a year ago,
but they are no closer to producing any kind of compelling
content without a human directing them, and the latter is what
you would actually need to make the "infinite entertainment
machine" happen.
The fidelity of a video generation model is comparable to an LLMs
ability to nail spelling and grammar - it's a start, but there's
more to being an author than that.
MikeTheRocker wrote 5 hours 30 min ago:
I already feel like text models are already at sufficiently
entertaining and useful quality as you define it. It's
definitely possible we never get there for video or 3D
modalities, but I think there are strong enough economic
incentives such that big tech will dump tens of billions of
dollars into achieving it.
jchw wrote 1 hour 36 min ago:
I don't know why you think that's the case regarding text
models. If that was the case, there would be articles on here
that are just created by only generative AI and nobody would
know the difference. It's pretty obvious that's not happening
yet, not the least of which because I know what kinds of slop
state-of-the-art generative models still produce when you
give them open-ended prompts.
echelon wrote 6 hours 23 min ago:
You're too old and jaded [1]. It's for kids inventing infinite
worlds to role play and adventure. They're going to have a blast.
[1] Not meant as an insult. Working professionals don't have time
for this stuff.
wizzwizz4 wrote 5 hours 48 min ago:
Object permanence and a communications channel is enough for
this. Give children (who get along with each other) a pile of
sticks and leave them alone for half an hour, and there's half a
chance their game will ignore the sticks. Most children wouldn't
want to have their play mediated by the computer in the way you
describe, because the ergonomics are so poor.
jdietrich wrote 4 hours 23 min ago:
The majority of American children have an active Roblox
account. Those who don't are likely to play Minecraft or
Fortnite. Play mediated by the computer in this way is already
one of the most popular forms of play. Kids are going to go
absolutely nuts for this and if you think otherwise, you really
need to talk to some children.
jsheard wrote 5 hours 43 min ago:
I'm reminded of that guy who bought an AI enabled toy for his
daughter and got increasingly exasperated as she kept turning
it off and treating it as a normal toy.
URI [1]: https://xcancel.com/altryne/status/1872090523420229780
wizzwizz4 wrote 5 hours 32 min ago:
That thread has a lot of good observations in it. I was
probably wrong in framing the problem as "ergonomics".
> Dr. Michelle (@MichelleSaidel): I think because it takes
away control from the child. Play is how children work
through emotions, impulses and conflicts and well as try out
new behaviors. I would think if would be super irritating to
have the toy shape and control your play- like a totally
dominating playmate!
> Alex Volkov (Thursd/AI) (@altryne): It did feel dominating!
she wanted to make it clothes, and it was like, "meanwhile,
here's another thing we can do" lacking context of what she's
already doing
> The Short Straw (@short_straw): The real question you
should ask yourself is why you felt compelled to turn it back
on each time she turned it off.
> Angelo Angelli JD (@AngelliAngelo): Kids are pretty decent
bullshit detectors and a lot of AI is bullshit.
> Foxhercules (@Foxena): [â¦] I would like to point out
again that the only things I sent this child were articulated
3d prints. beyond being able to move their arms, legs and
tails, these things were made out of extruded plastic and are
not exactly marvels of engineering. [â¦] My takeaway from
this is that, this is what children need. they don't need
fancy with tons of bells and whistles with play on any sort
of rails. And there's not a thing that AI can do to replace
a Child's imagination NOR SHOULD IT.
sebzim4500 wrote 6 hours 42 min ago:
Interesting. One of the diagrams suggests that the mesh is generated
from the marching cubes algorithm but the geometry of the meshes shown
above are clearly not generated in this way.
wumeow wrote 6 hours 11 min ago:
The meshes generated by the huggingface demo definitely look like the
product of marching cubes.
GrantMoyer wrote 6 hours 14 min ago:
To me, the bird mesh actually does look like marching cubes output.
Note the abundance of almost square triangle pairs on the front and
sides. Also note that marching cubes doesn't nescessarily create
stairstep-like artifacts; it can generate a smooth looking mesh given
signed distance field input by slightly adjusting the locations of
vertices based on the relative magnitude of the field at the
surrounding lattice points.
pella wrote 6 hours 47 min ago:
Ouch; License: EUROPEAN UNION, UNITED KINGDOM AND SOUTH KOREA
TENCENT HUNYUAN 3D 2.0 COMMUNITY LICENSE AGREEMENT
Tencent Hunyuan 3D 2.0 Release Date: January 21, 2025
THIS LICENSE AGREEMENT DOES NOT APPLY IN THE EUROPEAN UNION, UNITED
KINGDOM AND SOUTH KOREA AND IS EXPRESSLY LIMITED TO THE TERRITORY, AS
DEFINED BELOW.
URI [1]: https://github.com/Tencent/Hunyuan3D-2?tab=License-1-ov-file
EMIRELADERO wrote 6 hours 39 min ago:
I assume it's safe to ignore as model weights aren't copyrightable,
probably.
slt2021 wrote 4 hours 29 min ago:
you dont know what kind of backdoors are hidden in the model
weights
LiamPowell wrote 40 min ago:
Can you elaborate on how any sort of backdoor could be hidden in
the model weights?
It's a technical possibility to hide something in the code, but
that would be a bit silly since there's not that much of it here.
It's not technically possible to hide a backdoor in a set of
numbers that are solely used as the operands to trivial
mathematical operations, so I'm very curious about what sort of
hidden backdoor you think is here.
swframe2 wrote 15 min ago:
When you run their demo locally, there are two places that
trigger a warning that the code loads the weights unsafely. To
learn more about this issue, search "pytorch model load safety
issues" on Google.
EMIRELADERO wrote 2 hours 56 min ago:
I mean... you can just firewall it?
slt2021 wrote 2 hours 48 min ago:
you dont know which prompt activates the backdoor, how can you
firewall it if you run the model in production?
foolfoolz wrote 2 hours 28 min ago:
3d asset generation is a use case that for most doesnât
need to run in production
gruez wrote 6 hours 44 min ago:
Is this tied to EU regulations around AI models?
DIR <- back to front page