Sabitlenmiş Tweet
Andrew M
1.4K posts

Andrew M
@DrewzeeFX
3D Artist just going on adventures✌🏼
Katılım Şubat 2022
416 Takip Edilen266 Takipçiler

@miketuritzin @YeheLiu this could be wonderful for surfacing high stiffness mpm sims
English

@StephenDDGames dude np I think Ive been following your game since 2021
I tried making a music game during the pandemic but the latency issues killed the concept I had
love your concept btw and very cool execution on the style!
English

Music I made for the animation below… 🎧
(+ original plan on piano)
STEPHEN DDUNGU | GAMES@StephenDDGames
When you use the plot to win a fight…
English

New OctaneRender 2026.3.0.0 for Houdini Production (2026.3.0.0) @OTOY forum:
render.otoy.com/forum/viewtopi…

English

@RikOostenbroek your work is great dude, I’m a bit bummed I didnt get to see your talk at OFFF, I was one room over w all the sidefx ppl chattin bout gaussian splats
English

@danialghods_ The whitewater
Me too, shelf tools are nice but a bit bloated sometimes
English

@DrewzeeFX Which part do you mean? Flip or the Whitewater? I seldom use shelf tools nowadays.
English

@heydoughogan @LTXStudio @ltx_model @ComfyUI edit:
the hdr in blender is acting similar to png
even tho more headroom, incorrect light distribution (pixel values), ie adding too much “blue” light from the window causing a magenta cast
creative? sure
realistic? no
fun experiment? yes
thanks for saving us the time 🙏🏼
English

I've got some pretty cool new tech to share with ya...
@LTXStudio (the team behind LTX @ltx_model and my current favorite video model) reached out and asked me to test out their newly released HDR LoRA. So I loaded up @ComfyUI and took it for a spin!
I've been talking about this for a while now but this REALLY is one of the bigger gaps preventing AI video from integrating into a VFX pipeline right now as I see it.
Fun fact: 99% of video models currently only output 8-bit SDR! Which is fine for YouTube, but it falls apart REAL quick in a VFX production pipeline. Highlights clip, shadows break, and it’s hard to integrate with CG. It just doesn't meet production delivery standards.
LTX-2.3's newest LoRA is promising to us help with this! It can output scene-linear EXRs, which means you might actually be able use AI outputs in tools like Nuke or Resolve now without it all falling apart.
So the question I wanted to answer in this video was simple...can AI-generated footage FINALLY move beyond previs and actually produce production-ready data?
Let’s find out... youtu.be/_XJGXO9ATqk?si…
—
Model: lnkd.in/ePYXUrN8
Workflow: lnkd.in/ePe_dhz9HDR
Demo: lnkd.in/eDk2mwr6
#ComfyUI #LTX #sponsored #LTXModel #HDR #AIVideo #VFX

YouTube
English

I had the opportunity to work on #PrimitiveWar . I worked on the feather/fur sim rigs for multiple dinos (and a few other things). These two slow-motion shots are really cool and I am glad to have them in my reel. #houdini #sidefx
English

very handy!
MysteryPancake@MysteryPancake1
I added a "Transform by Attribute" option to my Volumetric Deform node. Now it's the only node I know that properly distorts rigid bodies inside another object :) Download below: #hda-volumetric-deform" target="_blank" rel="nofollow noopener">github.com/MysteryPancake…
#proceduralart #procedural #sidefx #houdini English

in #houdini, while in a solver [vellum in this case], you can dynamically/procedurally add geometry into the simulation as it's running. For vellum, you just need to make sure the total points on the geometry matches the total points in the constraints. Free HIP soon.
English

@KIRI_Engine_App I would call this a lenticular splat
how far can you push this? could a character do a walk cycle?
English

This is a single Gaussian Splat scan, not a .PLY sequence or 4DGS. What would you call this, 3.5D?
We trained a scan on various frames of an animation per view, resulting in a single file and no massive file sequence. The results may seem limited, but image this for a full werewolf transformation or other VFX?!
What else should we try to "morph" using this method?
English

A new #Blender version has been released and there's a lot of good talk about optimizations and speed ups 🏃♀️
But why has no-one mentioned we can turn our 3D scenes and models into cartoons so easily now 🤩
Grab the free demo file to try it out!
English

@Tks_Yoshinaga What software did you use for camera alighment and pose estimation?
English

@theworldlabs The pipeline runs end to end and produces this scene in under 2 minutes on a single A6000 GPU.
English

I build a pipeline that can turn any monocular video into a fully immersive 4DGS scene that you can explore it in realtime.
Stop watching videos. Start playing with them!
@theworldlabs #4DGS
English


Lighting is key to creating believable VFX. @Simulon generates accurate 360 hdr lighting in seconds.
But there’s something much stranger going on in this video. The chrome ball is being moved through the world as if it is actually there.
How do you think this is possible? 👀
We’ve built something that will completely change how 3D visual effects are made and it’s coming to Simulon next week.
English




