Mykhailo Moroz's banner

Mykhailo Moroz

@Michael_Moroz_ • 13,247 subscribers

Love physics simulations and rendering algorithms Chief Scientist at @ZibraAI https://t.co/awt86lPDfC Discord: misha.m.

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

I finally released VRCFluid: my boundless, high-quality SPH fluid simulation for VRChat worlds! 🌊 Up to 1M particles, simulated on the GPU which works without compute shaders! My demo world: Booth page:

I finally released VRCFluid: my boundless, high-quality SPH fluid simulation for VRChat worlds! 🌊 Up to 1M particles, simulated on the GPU which works without compute shaders! My demo world: Booth page:

97,338 views • 10 days ago

So I've implemented hash grid based fluid simulation in VRChat - its absolutely incredible. Because its hash based its literally boundless, so fluid can occupy the entire world. Currently I only have the "Mentos" particle rendering, but I plan on trying to make isosurface work

So I've implemented hash grid based fluid simulation in VRChat - its absolutely incredible. Because its hash based its literally boundless, so fluid can occupy the entire world. Currently I only have the "Mentos" particle rendering, but I plan on trying to make isosurface work

358,962 views • 1 month ago

So if you thought Doom on Linux in a fragment shader in VRChat was crazy... Turns out if you optimize it enough to run Quake 3 Arena! I also added VR controls. And even a barely working LAN connection between users via Udon. World:

So if you thought Doom on Linux in a fragment shader in VRChat was crazy... Turns out if you optimize it enough to run Quake 3 Arena! I also added VR controls. And even a barely working LAN connection between users via Udon. World:

84,865 views • 19 days ago

So I'm considering releasing my VRChat fluid simulation on Booth. I've ported it into Udon so it is faster and is easier to use. I used the Radix Sort from my 3DGS plugin, allowing me to do a true SPH sim without approximations. I'd love to head what you'd want to do with it 😄

So I'm considering releasing my VRChat fluid simulation on Booth. I've ported it into Udon so it is faster and is easier to use. I used the Radix Sort from my 3DGS plugin, allowing me to do a true SPH sim without approximations. I'd love to head what you'd want to do with it 😄

218,713 views • 2 months ago

People having fun in my VRChat fluid simulation test world 🙃 Improving the performance bit by bit. Also thank god it works on AMD GPU's from the beginning somehow (that never happened before 🤨)

People having fun in my VRChat fluid simulation test world 🙃 Improving the performance bit by bit. Also thank god it works on AMD GPU's from the beginning somehow (that never happened before 🤨)

134,949 views • 2 months ago

Its insane what AI can do nowadays, I've let Opus 5.5 in a loop for 2 days optimize a RISC-V emulator written in a fragment shader running in VRChat and it got to a working window manager, Doom running at playable speeds, and a an emulated GPU with OpenGL 1.x

Its insane what AI can do nowadays, I've let Opus 5.5 in a loop for 2 days optimize a RISC-V emulator written in a fragment shader running in VRChat and it got to a working window manager, Doom running at playable speeds, and a an emulated GPU with OpenGL 1.x

35,752 views • 29 days ago

I finally released the LOD version of VRChat Gaussian splatting that supports 100M scale splats! Compared to v3 it has a huge changelist!

I finally released the LOD version of VRChat Gaussian splatting that supports 100M scale splats! Compared to v3 it has a huge changelist!

91,569 views • 3 months ago

Using GPT-6 Astra I was able to quickly protorype a sparse grid allocator fluid simulation for VRChat using my specified architecture, but honestly as cool as it is its absolutely overkill for VRChat. Isosurface ray tracing could be done here, but its too complex to work with.

Using GPT-6 Astra I was able to quickly protorype a sparse grid allocator fluid simulation for VRChat using my specified architecture, but honestly as cool as it is its absolutely overkill for VRChat. Isosurface ray tracing could be done here, but its too complex to work with.

41,365 views • 1 month ago

Made a gaussian splat of a norwegian fjord from a youtube video using my tool slang-splat ( Really love how these places look. Turned out better than I expected from a yt vid. Photometric compensation helped a lot with floaters.

Made a gaussian splat of a norwegian fjord from a youtube video using my tool slang-splat ( Really love how these places look. Turned out better than I expected from a yt vid. Photometric compensation helped a lot with floaters.

81,245 views • 4 months ago

$For the last week I've been working on a fast enough way to render realistic light refraction through multiple layers of liquid in my VRChat fluid simulation. Ended up using a multilayer screen space ray marching solution to approximate the path of light.$

For the last week I've been working on a fast enough way to render realistic light refraction through multiple layers of liquid in my VRChat fluid simulation. Ended up using a multilayer screen space ray marching solution to approximate the path of light.

29,001 views • 1 month ago

I'm finishing up the VRChat fluid simulation world, adding a bunch of stuff like basic VRChat Light Volumes support to the fluid and a world night mode, liquid looks really pretty due to the glinting of the light sources.

I'm finishing up the VRChat fluid simulation world, adding a bunch of stuff like basic VRChat Light Volumes support to the fluid and a world night mode, liquid looks really pretty due to the glinting of the light sources.

21,187 views • 1 month ago

I improved the VRChat cloth simulation, now it is actually rendered as a mesh and finally can handle self collision for proper folds. Also I moved the simulation to CRTs so it kinda works for non friends(the simulation is on the avatar!). But the collision still requires cameras.

363,768 views • 3 years ago

Okay I figured out a pretty decent and fast way to get nice looking isosurfaces for sparse liquids in VRChat. But its applicable in general. I suspect I could make it even faster if I had access to compute shaders. Oh well, its already impressive as is

Okay I figured out a pretty decent and fast way to get nice looking isosurfaces for sparse liquids in VRChat. But its applicable in general. I suspect I could make it even faster if I had access to compute shaders. Oh well, its already impressive as is

23,067 views • 1 month ago

Over the last week added a bunch of nice-to-have features to the VRChat fluid simulation - almost ready now! -Collider buoyancy! Fluid applies force on (some) objects now -Simulation & performance presets -Mini explainer in the world -日本語ローカライズを追加しました

Over the last week added a bunch of nice-to-have features to the VRChat fluid simulation - almost ready now! -Collider buoyancy! Fluid applies force on (some) objects now -Simulation & performance presets -Mini explainer in the world -日本語ローカライズを追加しました

11,501 views • 1 month ago

I've been implementing multi-object combined LODs (actual LODs this time) for gaussian splats. It is insanely cool, due to the way I select LOD's I *always* render the same amount of splats no matter how many splats are in the scene. This scene has 108M total combined splats.

I've been implementing multi-object combined LODs (actual LODs this time) for gaussian splats. It is insanely cool, due to the way I select LOD's I always render the same amount of splats no matter how many splats are in the scene. This scene has 108M total combined splats.

33,620 views • 4 months ago

The idea was to basically use minimum blending and use all 4 color channels on the screen to write 4 depths: Nearest frontsurface, nearest backsurface, furthest frontsurface and furthest backsurface. (you can do min and max by inverting the numbers) Rendering the liquid with ZTest Off gives a pretty good approximation of the surfaces the liquid has that are within the field of view. Combining this with screen space ray marching of the scene depth and one can get a pretty decent emulation of how a multibounce ray traced fluid would have looked like, while being much faster. Without the 4 depths it would have been impossible to properly show the optical depth of absorption of light of the entire mass of fluid with air in-between.

The idea was to basically use minimum blending and use all 4 color channels on the screen to write 4 depths: Nearest frontsurface, nearest backsurface, furthest frontsurface and furthest backsurface. (you can do min and max by inverting the numbers) Rendering the liquid with ZTest Off gives a pretty good approximation of the surfaces the liquid has that are within the field of view. Combining this with screen space ray marching of the scene depth and one can get a pretty decent emulation of how a multibounce ray traced fluid would have looked like, while being much faster. Without the 4 depths it would have been impossible to properly show the optical depth of absorption of light of the entire mass of fluid with air in-between.

11,744 views • 1 month ago

Stress testing the simulation with 4M particles and a 384x384x96 grid. Most of the cost right now goes into the rendering prep, SDF gen and isosurface ray tracing (not ray marching, tracing). Could be substantially optimized if properly skipping unused parts of the grid.

Stress testing the simulation with 4M particles and a 384x384x96 grid. Most of the cost right now goes into the rendering prep, SDF gen and isosurface ray tracing (not ray marching, tracing). Could be substantially optimized if properly skipping unused parts of the grid.

15,172 views • 2 months ago

Implemented LOD splat instancings. Its looks like a pretty cool tool to procedurally combine things out of splats. I tried making a cloud scape out of a bunch of Disney Clouds.

Implemented LOD splat instancings. Its looks like a pretty cool tool to procedurally combine things out of splats. I tried making a cloud scape out of a bunch of Disney Clouds.

24,739 views • 4 months ago

Now that the latest Chrome version has WebGPU support I guess I can finally talk about this. A year ago David A Roberts and Cornus Ammonis were developing a compute shader based Shadertoy alternative called I already had a lot of fun making some toy projects 😳

Now that the latest Chrome version has WebGPU support I guess I can finally talk about this. A year ago David A Roberts and Cornus Ammonis were developing a compute shader based Shadertoy alternative called I already had a lot of fun making some toy projects 😳

125,877 views • 3 years ago