Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

This one took me almost 2 years to master, soon every Threejs dev will master it with a simple Import: Smoothed Particle Hydrodynamics Simulation, 2D and 3D, optimized with Spatial Hashing and Compute Shaders. Optimized for WebGPURenderer with complete TSL compatibility!!

Renaud

12,698 subscribers

131,113 Aufrufe • vor 11 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Launching Vibeviz 2.0 Create music visual videos with ThreeJS MIT license, link below Features: - 3D Shapes - Keyframe Animations and Easing - GLB model import w keyframed Animations - Background Shaders w TSL - Waveform Visualizers (MeshInstance, Lines, Particles) - Particle Systems with Repulsors and Attractors - Postprocessing Effects (Chromatic Aberration, Bloom, After Image) - Camera Switching with Keyframes - Lights - PBR Materials - Lots of Love for every ThreeJS contributor <3

Launching Vibeviz 2.0 Create music visual videos with ThreeJS MIT license, link below Features: - 3D Shapes - Keyframe Animations and Easing - GLB model import w keyframed Animations - Background Shaders w TSL - Waveform Visualizers (MeshInstance, Lines, Particles) - Particle Systems with Repulsors and Attractors - Postprocessing Effects (Chromatic Aberration, Bloom, After Image) - Camera Switching with Keyframes - Lights - PBR Materials - Lots of Love for every ThreeJS contributor <3

robot 2.0

17,105 Aufrufe • vor 11 Monaten

Almost done with the interaction of my WebGPU fluid simulation! After testing BVH geometry and marching cubes with compute shaders, I chose raymarching for hands interaction & rendering. It adapts well with MLS-MPM and enables precise interaction in real-time for <2ms. #threejs

Almost done with the interaction of my WebGPU fluid simulation! After testing BVH geometry and marching cubes with compute shaders, I chose raymarching for hands interaction & rendering. It adapts well with MLS-MPM and enables precise interaction in real-time for <2ms. #threejs

Renaud

10,095 Aufrufe • vor 1 Jahr

Sneak peek at our latest test for the upcoming PixiJS 3D engine 👀 WebGPU first with WebGL fallback Optimized for performance from day one Really excited to get this into your hands... More to come soon! Models by Quaternius and Kenney 🙏

Sneak peek at our latest test for the upcoming PixiJS 3D engine 👀 WebGPU first with WebGL fallback Optimized for performance from day one Really excited to get this into your hands... More to come soon! Models by Quaternius and Kenney 🙏

PixiJS

12,631 Aufrufe • vor 2 Monaten

Oh my god guys. I did it! I beat the entire Masters Collection with the title of a Master Ninja. I did every difficulty for each game as well (exception of UN for RE) and it took me a total of 1 month and a half to complete this entire journey.

Oh my god guys. I did it! I beat the entire Masters Collection with the title of a Master Ninja. I did every difficulty for each game as well (exception of UN for RE) and it took me a total of 1 month and a half to complete this entire journey.

Y u m i 🌿

51,920 Aufrufe • vor 5 Monaten

Combining 2D and 3D in After Effects. In Foldspace, not every surface needs to be bent. Keep one flat for 2D artwork, and let the others exist in 3D space. This allows you to combine 2D and 3D objects in a single animation with no masks or tricks needed.

Combining 2D and 3D in After Effects. In Foldspace, not every surface needs to be bent. Keep one flat for 2D artwork, and let the others exist in 3D space. This allows you to combine 2D and 3D objects in a single animation with no masks or tricks needed.

Motion Princess

21,963 Aufrufe • vor 5 Monaten

I'm back to working on my water simulator for interactive experiences using #threejs + #r3f. This time, I'm experimenting with #WebGPU and #TSL for better performance. I'm loving it more and more by the minute. The link and potentially a tutorial will be available soon. But if you want to play with the current version, it's available here: #creativecoding #r3f

I'm back to working on my water simulator for interactive experiences using #threejs + #r3f. This time, I'm experimenting with #WebGPU and #TSL for better performance. I'm loving it more and more by the minute. The link and potentially a tutorial will be available soon. But if you want to play with the current version, it's available here: #creativecoding #r3f

Anderson Mancini

12,581 Aufrufe • vor 1 Jahr

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

Over the Reality 🌐

14,829 Aufrufe • vor 4 Monaten

Revealing my first avatar I will release soon! With VeenanNorvius.bsky.social(Commissions Open) as the 3D artist, we've come together to create Reed, The Fishing Cat. Optimized to Medium rank with all features, like the fishing rod + a unique fish school follower that shows your saved fish, and more :)

Liindy

17,611 Aufrufe • vor 1 Jahr

managed to drive the Flex Avatar GS models with my webcam, also computed custom avatars (created with FLUX KLEIN) and added a feature to compute a 3D avatar from the webcam and it makes me happy :) I'll try to add morph, shaders, WebGL renderer etc. but this is already quite promising ! (2x playback)

Nicolas Barradeau

11,505 Aufrufe • vor 2 Monaten

From 2D video to a very rough 4D Gaussian Splatting POC on the Apple Vision Pro 👀 Took Big Buck Bunny frames, turned them into Gaussian splats with Sharp (Apple), compressed them with PlayCanvas splat transform to SOG, and played all frames via WebXR + spark Still rough and not fully optimized, but wow, dynamic GS in AVP feels wild 🤯 Second part of the video is on my laptop #threejs

From 2D video to a very rough 4D Gaussian Splatting POC on the Apple Vision Pro 👀 Took Big Buck Bunny frames, turned them into Gaussian splats with Sharp (Apple), compressed them with PlayCanvas splat transform to SOG, and played all frames via WebXR + spark Still rough and not fully optimized, but wow, dynamic GS in AVP feels wild 🤯 Second part of the video is on my laptop #threejs

Stijn Spanhove

20,258 Aufrufe • vor 8 Monaten

working on some simulated corals reefs using #tsl compute shaders, I think I got the simulation somehow right. I vibe-coded this in Omma AI, it was useful for the prototype to generate the models as well with a prompt. I am trying to replicate the anemone whre the clown fish lives, will need some more polish on the rendering then we're there ✌️

working on some simulated corals reefs using #tsl compute shaders, I think I got the simulation somehow right. I vibe-coded this in Omma AI, it was useful for the prototype to generate the models as well with a prompt. I am trying to replicate the anemone whre the clown fish lives, will need some more polish on the rendering then we're there ✌️

Marco Fugaro

28,401 Aufrufe • vor 3 Monaten

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,747 Aufrufe • vor 1 Jahr

In a small workshop, raw sand and glowing molten brass sat waiting — shapeless and unfinished. A master craftsman took them in his hands, shaping every mold with patience and staying with the process from start to finish. Slowly the metal cooled, was refined, ground, and polished until it found its true form. What began as simple materials became a beautiful handmade brass cup, shining and ready to hold warmth for years to come.

In a small workshop, raw sand and glowing molten brass sat waiting — shapeless and unfinished. A master craftsman took them in his hands, shaping every mold with patience and staying with the process from start to finish. Slowly the metal cooled, was refined, ground, and polished until it found its true form. What began as simple materials became a beautiful handmade brass cup, shining and ready to hold warmth for years to come.

Luna

899,288 Aufrufe • vor 9 Tagen

⚡️Live: Very proud to complete this project with Neotix Transformação Digital made in partnership with using #threejs and #r3f. A digital experience for DFC / PLC. Experience sustainable farming on a 3D virtual Canadian dairy farm 😍. #threejsJourney

⚡️Live: Very proud to complete this project with Neotix Transformação Digital made in partnership with using #threejs and #r3f. A digital experience for DFC / PLC. Experience sustainable farming on a 3D virtual Canadian dairy farm 😍. #threejsJourney

Anderson Mancini

19,829 Aufrufe • vor 3 Jahren

Took Grok 4.6 out for a spin this weekend and built this horde shooter prototype on ThreeJS. It is a big step up from Grok 4.5! I've always wanted to try building a horde shooter game with thousands of enemies onscreen and used Grok 4.6 for pretty much everything (including UI, vfx, and even the sfx!), except the 3D models for the characters, which were made and rigged with Meshy. I'm also amazed that ThreeJS with WebGPU can really handle thousands of enemies onscreen at the same time, though I think I pushed the limit here with Depth of Field and some other fancy shaders. Very fun!

Took Grok 4.6 out for a spin this weekend and built this horde shooter prototype on ThreeJS. It is a big step up from Grok 4.5! I've always wanted to try building a horde shooter game with thousands of enemies onscreen and used Grok 4.6 for pretty much everything (including UI, vfx, and even the sfx!), except the 3D models for the characters, which were made and rigged with Meshy. I'm also amazed that ThreeJS with WebGPU can really handle thousands of enemies onscreen at the same time, though I think I pushed the limit here with Depth of Field and some other fancy shaders. Very fun!

Danny Limanseta

65,105 Aufrufe • vor 1 Monat

OK. Been teaching myself Unreal for almost a year. Bits and pieces of stuff here and there. I wanted to try and game-a-fy it and see if it feels fun. This is riddled with bugs, super un-optimized and a visual nightmare BUT what I have so far. 😅😎 #indiedev #UnrealEngine

OK. Been teaching myself Unreal for almost a year. Bits and pieces of stuff here and there. I wanted to try and game-a-fy it and see if it feels fun. This is riddled with bugs, super un-optimized and a visual nightmare BUT what I have so far. 😅😎 #indiedev #UnrealEngine

Torrian OmgIworkinGames🤩

36,933 Aufrufe • vor 2 Jahren

🚨 New Tutorial Alert 🚨 Rendering Google Earth Engine & Cloud-Optimized GeoTIFF Tiles in 3D with Google Earth In this tutorial, I demonstrate how to visualize Google Earth Engine tile layers and Cloud Optimized GeoTIFFs (COGs) directly in Google Earth’s 3D environment. This approach lets you bring together high-resolution historical imagery and Street View data into one powerful platform. It’s a simple but effective way to make your geospatial data more accessible—just like sharing a Google Doc link. 🔗 Notebook: ▶️ Video: #geospatial #googleearth #dataviz #earthengine

🚨 New Tutorial Alert 🚨 Rendering Google Earth Engine & Cloud-Optimized GeoTIFF Tiles in 3D with Google Earth In this tutorial, I demonstrate how to visualize Google Earth Engine tile layers and Cloud Optimized GeoTIFFs (COGs) directly in Google Earth’s 3D environment. This approach lets you bring together high-resolution historical imagery and Street View data into one powerful platform. It’s a simple but effective way to make your geospatial data more accessible—just like sharing a Google Doc link. 🔗 Notebook: ▶️ Video: #geospatial #googleearth #dataviz #earthengine

Qiusheng Wu

16,480 Aufrufe • vor 1 Jahr

What is really useful is how GPT-6 Astra got better in spatial understanding. I'm still shocked how good it navigates 3D space. Here I gave it Blender MCP and Tripo P2.0 to generate optimized 3D models and put them together, rig and animate. Result is freaking awesome! Doing 3D objects procedurally with Astra is fun, but quality is not compared with what 3D Gen can do. Like you don't ask GPT to draw image with pen when there is GPT Image, same here. And token cost also speaks for it, 3D gen simply cheaper. But the way it assemble thing together, characters and scene, that is shocking ngl. And rigging of course, I have so much hope on it, it is most annoying part of 3d for me lol

What is really useful is how GPT-6 Astra got better in spatial understanding. I'm still shocked how good it navigates 3D space. Here I gave it Blender MCP and Tripo P2.0 to generate optimized 3D models and put them together, rig and animate. Result is freaking awesome! Doing 3D objects procedurally with Astra is fun, but quality is not compared with what 3D Gen can do. Like you don't ask GPT to draw image with pen when there is GPT Image, same here. And token cost also speaks for it, 3D gen simply cheaper. But the way it assemble thing together, characters and scene, that is shocking ngl. And rigging of course, I have so much hope on it, it is most annoying part of 3d for me lol

Stefan 3D AI

19,476 Aufrufe • vor 10 Tagen

Someone is building a game they dreamed of for 15 years using GPT-6 Astra and on day 10, five creature animations that used to take weeks at a 3D studio took an hour and a half, with the Scorpid running in Unity an hour after that. → Scorpid modeled in Tripo P2.0 with optimized mesh and well-organized parts for easier bone placement → Video references generated with SD 2.5 using the same workflow → About an hour and a half with GPT-6 Astra on xhigh for five animations including feedback rounds → Another hour to get it running in Unity

Someone is building a game they dreamed of for 15 years using GPT-6 Astra and on day 10, five creature animations that used to take weeks at a 3D studio took an hour and a half, with the Scorpid running in Unity an hour after that. → Scorpid modeled in Tripo P2.0 with optimized mesh and well-organized parts for easier bone placement → Video references generated with SD 2.5 using the same workflow → About an hour and a half with GPT-6 Astra on xhigh for five animations including feedback rounds → Another hour to get it running in Unity

0xMarioNawfal

38,719 Aufrufe • vor 4 Tagen

Inspired by Built a 3d learning platform for DSA with one prompt. Not live yet still testing. Will push it to github soon. Do comment how it looks and what all I can add to this

Inspired by Built a 3d learning platform for DSA with one prompt. Not live yet still testing. Will push it to github soon. Do comment how it looks and what all I can add to this

Neeraj Walia

29,528 Aufrufe • vor 1 Monat