Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Generative AI is cool and all, but SDF modeling just hits different. Non-destructive shaping, blending and boolean modeling on an iPad using Uniform 1.4

bilawalsidhu's profile picture

Bilawal Sidhu

107,725 subscribers

83,493 Aufrufe • vor 1 Jahr •via X (Twitter)

KunstWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von E
Evor 1 Jahr

God, it makes everything so much simpler and more intuitive. The way 3D modeling works today is not very intuitive.

Profilbild von Bilawal Sidhu
Bilawal Sidhuvor 1 Jahr

Yeah meshes are a funky abstraction — they’re super useful but definitely not fun to manipulate manually

Profilbild von Yang
Yangvor 1 Jahr

Want to learn how practical AI skills and automations for your business and work? Check out our 50+ step-by-step video tutorials 100% FREE 20+ hours of Ai and Automation goodness absolutely free 🥳

Profilbild von rishi pandey
rishi pandeyvor 1 Jahr

i think it will be commonplace to see diffusion models running locally on apple silicon in the next 2-3 years which will have huge creative workflow implications

Profilbild von Bilawal Sidhu
Bilawal Sidhuvor 1 Jahr

I would like to see video generation movie locally at scale asap

Profilbild von アメド オシナイケ
アメド オシナイケvor 1 Jahr

What’s ‘SDF’ stand for?

Profilbild von Bilawal Sidhu
Bilawal Sidhuvor 1 Jahr

@grok explain SDF modeling and compare it to traditional mesh based modeling

Profilbild von chris
chrisvor 1 Jahr

whys it always look so easy and then when i try it i just get a flat plane or something grotesque

Profilbild von Bilawal Sidhu
Bilawal Sidhuvor 1 Jahr

Think legos — get comfortable with primitive based modelling

Profilbild von Dylan Bishop
Dylan Bishopvor 1 Jahr

Nice! Can’t wait to play with this. Just starting to get back into 3D it’s been a while.. here’s me from like 25 years ago with my Pokemon models/renders

Profilbild von Time is Light
Time is Lightvor 1 Jahr

Time is Light !

Ähnliche Videos

I'm continuing to play with sdf nodes in blender 3.6. I created a group to better manage this new workflow. Currently I can handle two separate addition and two different boolean . The modeling at the moment is quite slow but it still fun. #b3d #geometrynodes #sdf
1:43

I'm continuing to play with sdf nodes in blender 3.6. I created a group to better manage this new workflow. Currently I can handle two separate addition and two different boolean . The modeling at the moment is quite slow but it still fun. #b3d #geometrynodes #sdf

Emiliano Colantoni

13,251 Aufrufe • vor 3 Jahren

Generative ai is cool but procedural 3d generation just hits different. iCity basically feels like sim city for adults who know blender.
0:24

Generative ai is cool but procedural 3d generation just hits different. iCity basically feels like sim city for adults who know blender.

Bilawal Sidhu

533,794 Aufrufe • vor 11 Monaten

Generative AI is cool and all, but I continue to be blown away by the strides in real-time visual effects. Case in point — ripping through immaculate fluid simulations on an RTX 4090 using EmberGen:
0:23

Generative AI is cool and all, but I continue to be blown away by the strides in real-time visual effects. Case in point — ripping through immaculate fluid simulations on an RTX 4090 using EmberGen:

Bilawal Sidhu

552,683 Aufrufe • vor 3 Jahren

We just brought flow maps to language modeling for one-step sequence generation 💥 Discrete diffusion is not necessary -- continuous flows over one-hot encodings achieve SoTA performance and ≥8.3× faster generation 🔥 We believe this is a major step forward for discrete generative modeling and language modeling alike. 🚀 Full thread from first author Chanhyuk Lee:
0:23

We just brought flow maps to language modeling for one-step sequence generation 💥 Discrete diffusion is not necessary -- continuous flows over one-hot encodings achieve SoTA performance and ≥8.3× faster generation 🔥 We believe this is a major step forward for discrete generative modeling and language modeling alike. 🚀 Full thread from first author Chanhyuk Lee:

Nicholas Boffi

44,442 Aufrufe • vor 6 Monaten

🤔 What if you could skip painful subdiv modeling and paint your knurls instead? 3D artist Jordan Cain demonstrates a fast, non-destructive workflow using Toolbag’s vector layers and symmetry mode to create and refine knurling patterns in no time.
0:57

🤔 What if you could skip painful subdiv modeling and paint your knurls instead? 3D artist Jordan Cain demonstrates a fast, non-destructive workflow using Toolbag’s vector layers and symmetry mode to create and refine knurling patterns in no time.

Marmoset

211,090 Aufrufe • vor 8 Monaten

Generative AI is cool and all, but procedural 3D modeling just hits different. Check out this Houdini setup by Pepe Buendia. Why this is cool: Instead of manually placing every building and car, this system generates an NYC-style city that builds itself -- automatically spawning buildings with unique variations, plus a traffic system where cars actually obey traffic lights and avoid crashing into each other (all orchestrated through houdini VEX code). Each car knows exactly which road it's on and makes real-time decisions about navigation. The whole thing runs on custom algorithms that handle everything from road directions to building placement. If you did this with generative AI, even approaches to conditioning and taming the chaos -- you'd still get a ton of variance which might be an issue for visual and spatial consistency. To me this is procedural modeling at its finest - precise control meets infinite scalability. Immensely useful for media & entertainment, but also synthetic training data for robotics and augmented reality. I of course can't wait until multimodal LLMs to have the spatial understanding to write these kind of controllable 3D worlds for us. Claude counting 2D pixels on a screen is a step in this direction. Soon they'll be able to manipulate 2D ortho viewports, and eventually spawn procedural 3D worlds.
0:24

Generative AI is cool and all, but procedural 3D modeling just hits different. Check out this Houdini setup by Pepe Buendia. Why this is cool: Instead of manually placing every building and car, this system generates an NYC-style city that builds itself -- automatically spawning buildings with unique variations, plus a traffic system where cars actually obey traffic lights and avoid crashing into each other (all orchestrated through houdini VEX code). Each car knows exactly which road it's on and makes real-time decisions about navigation. The whole thing runs on custom algorithms that handle everything from road directions to building placement. If you did this with generative AI, even approaches to conditioning and taming the chaos -- you'd still get a ton of variance which might be an issue for visual and spatial consistency. To me this is procedural modeling at its finest - precise control meets infinite scalability. Immensely useful for media & entertainment, but also synthetic training data for robotics and augmented reality. I of course can't wait until multimodal LLMs to have the spatial understanding to write these kind of controllable 3D worlds for us. Claude counting 2D pixels on a screen is a step in this direction. Soon they'll be able to manipulate 2D ortho viewports, and eventually spawn procedural 3D worlds.

Bilawal Sidhu

527,545 Aufrufe • vor 1 Jahr

Aneesh Komanduri is a fourth-year Ph.D. student in the Department of Electrical Engineering & Computer Science at the University of Arkansas, with a focus on causality, generative modeling, and trustworthy AI. (1/2)
3:30

Aneesh Komanduri is a fourth-year Ph.D. student in the Department of Electrical Engineering & Computer Science at the University of Arkansas, with a focus on causality, generative modeling, and trustworthy AI. (1/2)

Improve The Dream

13,279 Aufrufe • vor 1 Jahr

Generative video is dope but AI motion capture is just as cool. Pretty much James Cameron ish in your living room — and that too with just a 2D camera
0:24

Generative video is dope but AI motion capture is just as cool. Pretty much James Cameron ish in your living room — and that too with just a 2D camera

Bilawal Sidhu

89,178 Aufrufe • vor 1 Jahr

One of the strengths of flow matching is that it decouples generative modeling from a specific noise process and choice of source distribution. You can select from a variety of initial distributions like a Gaussian or a uniform distribution and still train a valid flow model.
0:21

One of the strengths of flow matching is that it decouples generative modeling from a specific noise process and choice of source distribution. You can select from a variety of initial distributions like a Gaussian or a uniform distribution and still train a valid flow model.

Alec Helbling

48,656 Aufrufe • vor 7 Monaten

Just tried Lux3D: an AI 3D generator built by Manycore Tech You drop in an image or text prompt… and it gives you a full, editable 3D asset with solid geometry + materials. No 3D modeling skills needed. This one actually feels different.
0:36

Just tried Lux3D: an AI 3D generator built by Manycore Tech You drop in an image or text prompt… and it gives you a full, editable 3D asset with solid geometry + materials. No 3D modeling skills needed. This one actually feels different.

Sharon Riley

21,697 Aufrufe • vor 7 Tagen

This is crazy. Ideas become game-ready 3D models in 4 minutes with no modeling skills and no cleanup needed. Tripo has evolved again and AI 3D just got effortless:
0:20

This is crazy. Ideas become game-ready 3D models in 4 minutes with no modeling skills and no cleanup needed. Tripo has evolved again and AI 3D just got effortless:

Future Stacked

126,204 Aufrufe • vor 7 Monaten

We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: #CVPR #AI #CVML👇
3:59

We present Neural Riemannian Motion Fields (NRMF) as a promising paradigm for generative modeling of articulated motion. Unlike various diffusion based models, NRMF is useful both in generation and in deployment as a prior across tasks: #CVPR #AI #CVML👇

Tolga Birdal

16,795 Aufrufe • vor 11 Monaten

Wear your favorite dress using Adobe Generative AI (Currently this feature is only available on Photoshop Beta and Firefly)
0:43

Wear your favorite dress using Adobe Generative AI (Currently this feature is only available on Photoshop Beta and Firefly)

Photoshop Tricks!

91,723 Aufrufe • vor 1 Jahr

1/ Spent the past few days testing Lux3D, a 3D generative model. You give it an image or a text prompt and it hands you back a full, editable 3D asset. No modeling skills required. Tried all 3 core features. A thread:
0:32

1/ Spent the past few days testing Lux3D, a 3D generative model. You give it an image or a text prompt and it hands you back a full, editable 3D asset. No modeling skills required. Tried all 3 core features. A thread:

Chubby♨️

21,355 Aufrufe • vor 5 Tagen

This might be the beginning of a new field.. Researchers just reconstructed sounds from human brain activity using an fMRI and a generative AI model.
0:41

This might be the beginning of a new field.. Researchers just reconstructed sounds from human brain activity using an fMRI and a generative AI model.

Lior Alexander

208,384 Aufrufe • vor 3 Jahren

ifacialmocap + webcam tracking is literally so goated!!! this is all done from the ifacialmocap app on an ipad/iphone and just my webcam!
0:44

ifacialmocap + webcam tracking is literally so goated!!! this is all done from the ifacialmocap app on an ipad/iphone and just my webcam!

Junie 🐰🦴 CentiBunny Vtuber 「V-SPOOKYGIRLS 」

72,113 Aufrufe • vor 4 Monaten

Today, generative AI can create a 3D race car. Roblox is now working on 4D generative AI, where that race car has an engine, moveable parts and a physics rig that enables it to drive down a track — all generated with just a text or voice prompt.
0:26

Today, generative AI can create a 3D race car. Roblox is now working on 4D generative AI, where that race car has an engine, moveable parts and a physics rig that enables it to drive down a track — all generated with just a text or voice prompt.

David Baszucki

467,854 Aufrufe • vor 2 Jahren

📁 Fei Fei Li says that a key breakthrough in generative AI is the next token prediction objective, perfectly aligned with the task of producing language. She adds that vision and world modeling are harder because the real world is multimodal and demands observation, interpretation and reasoning. She notes that understanding and creating worlds is far more complex than generating text.
2:28

📁 Fei Fei Li says that a key breakthrough in generative AI is the next token prediction objective, perfectly aligned with the task of producing language. She adds that vision and world modeling are harder because the real world is multimodal and demands observation, interpretation and reasoning. She notes that understanding and creating worlds is far more complex than generating text.

Jon Hernandez

75,087 Aufrufe • vor 9 Monaten

this is soooo cool. in an industry that uses generative ai more and more, it’s so refreshing to see real art being used for a concept photoshoot
0:47

this is soooo cool. in an industry that uses generative ai more and more, it’s so refreshing to see real art being used for a concept photoshoot

drea 🍓

444,677 Aufrufe • vor 1 Jahr