Image-blaster: Creates 3D environments, SFX, and meshes from a single image

178

MMattRogish 1 day ago 37 commentsRead Article on github.com

HI version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

84% Positive

Analyzed from 1191 words in the discussion.

Discussion (37 Comments)Read Original on HackerNews

avaer•1 day ago

If you haven't tried AI modeling pipelines in the last year you'll be surprised.

The star of the show here is https://platform.worldlabs.ai/ (author works there, I don't) which is really good. There's also Meshy.ai (which this repo doesn't seem to use?) for non-scene stuff that's right up there in quality. There's texturing, auto-rigging, etc.

The latest VLLM models have true pixel image grounding which means you can totally ask your AI about pixel coordinates of things, so you get 3d perception for edits and anything else you need.

I'm actually surprised I don't see this stuff being used more; I think it's because most pipelines are hard-baked with assumption that your 3D assets are files you get from an artist, not something you can imagine up in minutes in a script. The technology is moving faster than the industry can keep up with.

NitpickLawyer•1 day ago

> I'm actually surprised I don't see this stuff being used more;

There's very little incentive to publicly admit you're using this tech. In fact there are a lot of reasons not to.

spookie•about 13 hours ago

Outside trained images or objects, Hunyuan falls apart pretty hard.

Out of 30 objects I tried, only 4 had relative success. And even then, the topo ain't great.

pawelduda•1 day ago

What's the best option for converting house blueprints or 3D rendered images back to models?

totalview•about 21 hours ago

There are not good workflows for doing this for a whole scene, especially where accuracy needs to be preserved. One shot models seem to be very good at providing 3D from a single angle, but multishot is very shoddy at this point, and without seeing behind things you have no clue about what is actually there.

Also, try meshy and look at how many polygons or triangles you get from any of the model objects. Hundreds of thousands, when you retopologize still goes to the high tens of thousands.

tombert•1 day ago

This is cool as hell.

I remember like seventeen years years ago, Microsoft had "PhotoSynth", which would make 3D environments based on a bunch of images, and seventeen-year-old-tombert thought it was one of the most amazing things to ever be done on a computer.

Doing this with just one image makes this at least an order of magnitude cooler. I will be playing with this over the weekend.

agentifysh•about 23 hours ago

yeah I remember that was pretty neat each generation 3d stuff gets wilder and wilder

I used to spend all day on Bryce3D creating 3d landscapes, leaving computer on fall night to render like 10 seconds of video of a flyover sunset

bit of a rant here but we are definitely speedrunning 3d and its just going to get wilder once we get glass free bounded AR...projecting 3d video streams and objects in front of our phones (this one I know Samsung is already working on) and rooms

taffydavid•1 day ago

Photosynth was awesome, I really miss it, but it was more of a panorama tool than a 3d environment.

My pixel6 has a photo sphere mode on the camera which is the same thing

tombert•1 day ago

You could actually make it have a rough 3D environment as well. Their demo had a model of Piazza San Marco with dots to estimate the actual buildings and the like.

taffydavid•1 day ago

Oh yes, I remember that now!

toisanji•1 day ago

I see it used worldlabs, i’ve tested it quite a bit and no results were not really that usable, it hallucinated so many parts outside of the wall that made no sense. He will be fine if hallucinated and it made sense but if it doesn’t make sense, I’m not sure what the point of inputting a single image is. I’ve actually found better luck using gpt image 2 instead.

vunderba•about 22 hours ago

Yeah, even the latest version, Marble 1.1 which this repo uses can make a royal mess of things, especially outdoor environments.

agentifysh•about 23 hours ago

I wonder if there is something similar but for creating isometric sprites? I burned through $30 yesterday realizing that I can't just get image gen to give me isometric static/animated sprites with consistency....even the best image gen cannot do this and im just baffled how difficult isometric sprite is compared to 3d mesh gen

I'm at a crossroad , do I opt for 3d mesh isometrics with more hardware requirements for mobile phones or stick to isometric sprite which nobody seems to be generating via AI reliably (happy to be corrected here if anybody does find a way)

keerthiko•about 6 hours ago

You're better off creating a 3D model and then taking image-grabs of it facing different directions/doing different poses from an isometric perspective to get your isometric sprites, with the genAI tools of today without a skilled 2D artist at hand.

If you aren't ready to rig and adjust model poses in a 3D tool, you might be better off generating each movable model part as a separate mesh and just arranging them in space before doing the above.

agentifysh•about 3 hours ago

yeah 3D comes up often but the economics don't work for the large scale I am trying to do.

taylorfinley•about 16 hours ago

I had a similar experience recently while helping my 5 year old daughter vibe code a sandcastle-themed tower defense game (https://sandcastles.finley.lol).

I ended up thinking it might be easier to generate rigged models, animate them, and capture from an iso perspective, then do some kind of pixel art style transfer on the masked sprite sheet. Eventually I realized my kid didn't really care too much about the visuals so I didn't get too far with it.

ShinyLeftPad•about 14 hours ago

> I'm at a crossroad , do I opt for 3d mesh isometrics with more hardware requirements for mobile phones or stick to isometric sprite which nobody seems to be generating via AI

Just find an artist or learn to draw

xrd•about 23 hours ago

Is this in the same vein as TRELLIS?

https://github.com/Microsoft/TRELLIS

I've been trying to use this to generate 3d character models from images. I am enjoying 3d printing these models to mess with my kids.

Not much of what I've found runs on local models but I'm always on the lookout. Meshy.ai (mentioned here) offers really nice generation but the cost adds up quickly.

washadjeffmad•about 22 hours ago

There are quite a few, now, and more coming out regularly to surprisingly little fanfare.

Tencent's Hunyuan3D (https://github.com/Tencent-Hunyuan) is a single/multi view photogrammetry replacement, which image-blaster is based on.

Facebook Research has extended SAM to 3D (https://github.com/facebookresearch/sam-3d-objects), separating as 'Objects' and 'Body'.

The workflows to make meshes watertight for 3D printing are all pretty effective.

vunderba•about 22 hours ago

This is more like a Claude-based skill set that orchestrates a bunch of different, separate systems. The closest equivalent to Trellis would probably be its usage of Huyuan-3D, which it uses to create some of the 3D object models.

From what I can tell, it takes an image and first segments it into objects versus environment then sends the environment to Marble 1.1 to generate a Gaussian splat,sends all the isolated individual objects to Hunyuan to generate GLB model files.

mattbillenstein•about 24 hours ago

My team is working in the character animation space which might complement this: https://uthana.com/

Example: https://uthana.com/app/preview/cXi2eAP19XwQ/mH7opbcqZE4P

ZiiS•1 day ago

So Blade Runner's Esper photo analysis went from ruining the suspension of disbelief to reality quicker then most magic.

taffydavid•1 day ago

Well, in blade runner he looks around a corner and zooms in microscopic detail on something not visible from the photo.

But the esper interface is all voice activated, and doesn't talk back - which I think is very prescient, and more likely the way things will go. I'd much rather voice assistants just did the thing that I want them to do rather than talk back to me

janfoeh•1 day ago

I've never forgotten this SIGGRAPH demo from almost twenty years ago, in which the authors effectively switch camera and light source computationally (... in a static scene) [1]

Ever since then, I have viewed scenes such as the "lingerie store scene" from Enemy of the State [2] with a little bit less eye rolling...

[1] - https://www.youtube.com/watch?v=p5_tpq5ejFQ

[2] - https://youtu.be/3EwZQddc3kY?t=6

ChoGGi•about 18 hours ago

Thanks for posting that demo, kinda sad I've never seen it till now.

MattCruikshank•1 day ago

I went to high school with the sales clerk, Ivana Miličević.

It's always weird to see her in stuff.

nomadar•about 24 hours ago

Curious about the actual architecture. From the outside it looks like Gaussian splatting anchored to roughly one viewpoint, since the moment you wander outside the original frame or behind an object, it becomes messy. But Ben Mildenhall is one of the co-founders and a NeRF co-author (https://arxiv.org/abs/2003.08934), so I'm betting that whatever they're doing is more interesting than naive splatting. Curious if OP can share anything about the pipeline.

p0w3n3d•about 24 hours ago

What about creating 3d meshes from multiple photos of the same object?

PacificSpecific•about 19 hours ago

I've had some success with that. It's pretty neat!

Haven't used it professionally mainly because the titles I've worked on lately aren't realistic so you can't really procure the materials to scan.

andrew_kwak•about 13 hours ago

That's pretty wild. How does it handle different lighting conditions in the source image? Curious if the results look natural or if they need a lot of tweaking.

SilentM68•about 21 hours ago

Very cool.

May I ask if Claude is the only option to use the tool?

Sol Roth

par•1 day ago

I’m ready to make a game with this, or something similar. Open to suggestions on tooling and asset pipelines that utilize AI, if anyone has any suggestions or guides.