Загрузка видео...
Не удалось загрузить видео
🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build connected parts for robot learning... show more
150,324 просмотров • 1 месяц назад •via X (Twitter)
Комментарии: 57

Code:

15 cents per 3D asset is a massive drop in cost.

Yeap : ) Feel free to try it out and raise any issue!

Definitely will, open sourcing this could push the whole space forward.

Thanks for sharing !!!

This is WONDERFUL!!!

Thanks!

Interesting! Following along 🔖

Thanks!

Exactly what I need at the moment. Starred

Thanks!

thank you how its different from @

We are using multi-agent, it is cheaper with better success rate. The code is very different if you do a comparison. We also politely cite and compare with them at the very beginning of the github paper. If you see my twitter, I just share their code base yesterday.

好的 谢谢

nice job!

I am curious to compare the notes on this for text to print directly…

Thank you!

Wow! Will try it out! gave you a follow as well✅

Thanks!

Awesome to see. Can this be integrated with kicad?

Sorry, not so familiar with kicad, the output is stl file, raise an issue in the github to ask my student 🥲

Got it. It is amazing though. Thanks for the work.

@J0hn_bee check this out!

@J0hn_bee Thanks!

Incredible, that's a beautiful piece of art. Added to my bucket list. So peaceful.

Thanks!

add actuator planetary and cycloidal parts along with the exact motors that can be used to create actuators with pancake drone motors and nema, etc. then please give me 5% of sales for the idea.

Thanks!

This is beyond cool.

Thanks!

👀

👀

Nice!!

@Do_owne

This looks very cool, Professor. Would love to try it.

Thanks!

good to see guys,I’ll test it out and give feedback

Give me a feedback if you happens to play with it.

Nice! These are the kind of projects that will lead to computers building useful things 🚀

Thanks!

the $0.15 ball-in-cage is going to ruin a lot of afternoons.

hhahah!

Awesome stuff

THANK YOU! been looking for a good text to cad repo

Thanks!

The $0.15 figure makes sense if the output is clean geometry, but genuinely asking, how are you measuring 'higher accuracy' here? Prompt adherence and structural validity feel like very different bars.

Awesome work, congratulations on the release! That aside, I personally know of a few founders in the text -> CAD space and they'd be stoke to see releases like this. Perhaps a super impactful continuation would be to create a set of useful "harness" on top of this. Cheers!

Thanks a lot!

So cool, look forward to testing it!

Thanks! Give us a feedback!

Amazing work. The results in the video look great, but could this be used to manufacture mechanical parts for something like a robotic arm?

Yes, we are extending on that direction.

Cutting CAD generation to $0.15 shows the power of tightly coupled agents. The Qwen backbone explains the speed boost you demoed. Keep the budget tight, let the agents handle error correction

$0.15 per 3D asset is impressive. The real breakthrough is making CAD generation faster, cheaper, and accessible through multi-agent workflows.

does the $0.15 include geometry validation retries, where these pipelines usually lose margin

Text-to-CAD agents are finally moving past demos. The real test isn't the pipeline, it's whether a designer can iterate on the output without fighting the harness.

these are such basic shapes, a novice CAD user could do these in a short amount of time
