Logo
Picture

Ulf @stilfuchs

møpmøp Berlin, Deutschland Joined October 2019
  • Tweets
    7K
  • Followers
    123
  • Following
    431
  • Likes
    24K
Ulf retweeted
alexfredo87 Profile Picture

Alex @alexfredo87

3 days ago

I’m testing Rodin Gen-2.5 Extreme-High and its 12K texture with a custom skin shader I created. The result is pretty good. @DeemosTech

Ulf retweeted
victormustar Profile Picture

Victor M @victormustar

3 days ago

Before the week ends, let's acknowledge one of the most INSANE week ever for open AI, with 25+ notable open-weight drops across every modality: 🧠 LLMs → NVIDIA Nemotron 3 Ultra: 550B hybrid Mamba-MoE, only 55B active, 1M context, MMLU 89.1. NVFP4 variant claims ~5x throughput on Blackwell. First openly-weighted 550B hybrid Mamba-Transformer, closing the gap with frontier closed models. → Google Gemma 4 12B: fully open dense any-to-any (text/image/audio/video), 256k context, encoder-free, 140+ languages, AIME 2026 at 77.5. Shipped with a 23-checkpoint QAT wave (mobile ONNX + MLX). Most deployable model of the week. → StepFun Step-3.7-Flash: 198B sparse MoE VLM, ~11B active, SWE-Bench PRO 56.3. Apache 2.0. → Liquid AI LFM2.5-8B-A1B: edge MoE, just 1.5B active, 128k ctx, MATH500 88.8, MLX-ready. Best on-device option this week. → JetBrains Mellum2-12B-A2.5B-Thinking: their first open MoE, near-Qwen3-14B coding at 2.5B active. Apache 2.0. 🎨 Image gen (the surprise of the week) → Ideogram 4: their FIRST-EVER open weights. 9.3B flow-matching DiT trained from scratch. #2 overall behind GPT Image 2, top open-weight model on Design Arena + LMArena. Strongest open checkpoint for text-rich images, full stop. It has taste. Still can't believe this is open weights. 🔊 Audio & Speech (a breakout week for open TTS, 4 labs shipped) → Boson Higgs Audio v3 4B: 102 languages, 21 emotions, singing/whispering/shouting, sub-second TTFA. → RedNote dots.tts: the only fully continuous (no codec) open TTS pipeline, Apache 2.0. → Google Magenta RealTime 2: real-time music gen, <200ms latency, text+audio+MIDI. multimodalart ported it to PyTorch within hours with live ZeroGPU demos. → NVIDIA Nemotron-3.5 ASR: 600M streaming, 17x more concurrent streams vs Parakeet RNNT 1.1B. 👁️ Vision & VLMs → PaddleOCR-VL-1.6: SOTA document parsing at 1B params, Apache 2.0. → Baidu NAVA: 6.3B joint audio-video gen, best-in-class A/V sync, Apache 2.0. 🎬 Video, 3D & World Models → NVIDIA Cosmos3-Super: 64B omnimodal world model coupling action trajectories with video+audio gen, for Physical AI. → JD JoyAI-Echo: up to 5-min multi-shot text-to-video on LTX-2.3. → ByteDance Bernini-R + VAST TripoSplat (single-image-to-3D Gaussian splats, MIT).

stilfuchs Profile Picture

Ulf @stilfuchs

3 days ago

@PurzBeats The haters 🤣🤣

Ulf retweeted
KIRI_Engine_App Profile Picture

KIRI Engine - 3D Scanner App @KIRI_Engine_App

4 days ago

Gaussian Splats can now be animated in Blender New 3DGS Render addon update: - Blender 5.1 support - 4DGS / .ply sequence export - Experimental rigging tools - Experimental light baking Check below for links 👇

Ulf retweeted
SpenserFX Profile Picture

Spenser Dickerson @SpenserFX

4 days ago

Trying out @DanyBittel Fruit gaussian splats for the first time with @OTOY Octane 2026, pretty remarkable the level of detail in these. If you're looking for the highest fidelity berries on the market - look no further! 🔥🔥🔥

Ulf retweeted
80Level Profile Picture

80 LEVEL @80Level

5 days ago

Take a look at Thomas Schreiter's impressively realistic 3D portrait of actor Willem Dafoe. All the skin details were made by hand: 80.lv/articles/reali…

Ulf retweeted
carlosedubarret Profile Picture

Carlos Barreto @carlosedubarret

5 days ago

CEB SAM 3d Body V1 Free Download at patreon.com/posts/160132662 #mocap #b3d

Ulf retweeted
ostrisai Profile Picture

Ostris @ostrisai

5 days ago

Today I am releasing Ostris Cloud. If you want to help support the open source development of AI Toolkit while renting compute, this is a great way to do that. Link in 🧵

Ulf retweeted
KIRI_Engine_App Profile Picture

KIRI Engine - 3D Scanner App @KIRI_Engine_App

6 days ago

Featureless objects break most photogrammetry pipelines. Glossy, monochrome, no surface texture. Nothing for feature matching to grab onto. We built a dedicated Featureless Object Scan Mode for exactly this. The chess knight here is basically worst-case: uniform color, smooth curves, specular highlights everywhere. Left is Photo Scan Mode. Right is Featureless Object Mode.

Ulf retweeted
andrewpprice Profile Picture

Andrew Price @andrewpprice

7 days ago

3D Gaussian Splat support for Blender is finally in development projects.blender.org/blender/blende… 💪

Ulf retweeted
sparseal Profile Picture

Sparseal @sparseal

6 days ago

Introducing CozyBlanket Pro A next-generation mesh optimization and cleanup toolkit, built from the ground up with AI-assisted retopology, cutting-edge UV tools, and powerful tool system to transform complex geometry into clean, efficient, production-ready assets.

stilfuchs Profile Picture

Ulf @stilfuchs

6 days ago

@fofrAI @nvnot_

stilfuchs Profile Picture

Ulf @stilfuchs

7 days ago

@RaphaelRau @OTOY @OctaneRenderIt @Maxon_Cinema4D @MaxonVFX

stilfuchs Profile Picture

Ulf @stilfuchs

7 days ago

👀

mrdoob Profile Picture

mrdoob @mrdoob

4 months ago

Spent a bit more time today and I think the very first alpha is now ready to share. 🎮 mrdoob.github.io/three-descent/ 💻 github.com/mrdoob/three-d… Lots of missing details still but you can already enjoy the glorious SoundBlaster sound bank again.

Ulf retweeted
Aurelien_Gz Profile Picture

Aurelien @Aurelien_Gz

a week ago

this threejs satellite tracking site looks like it came straight out of a sci-fi movie.. » vantafort.com/app wizard » riddell.red

Ulf retweeted
planetzomax Profile Picture

zomax @planetzomax

a week ago

because of limited / ugly osl controls, lensgate now comes with it's own tag (that just controls the osl tag, but still.... more pretty)!

stilfuchs Profile Picture

Ulf @stilfuchs

a week ago

@tripoai @VastAIResearch Wow...😍 Is multi image input planned or an option?

Ulf retweeted
sozoraemon Profile Picture

そぞら@Raspberry Pi 電子工作 @sozoraemon

a week ago

ラズパイと円形ディスプレイで、台風レーダーを作りました。

Ulf retweeted
QingQ77 Profile Picture

Geek Lite @QingQ77

a week ago

让没有 GPU 的机器通过网络远程使用其他机器上的 GPU，像本地显卡一样调用 CUDA。 github.com/lupinemachines… 把远程 GPU 的调用通过网络转发过来，让没有显卡的机器也能跑 CUDA 程序。客户端启动后自动装好 shim 库，应用程序不用改代码就能用。支持同时连多台 GPU 服务器，多卡聚合在一起。Docker 镜像直接拉下来就能用，不用自己编译。

Ulf retweeted
mrdoob Profile Picture

mrdoob @mrdoob

a week ago

Some creepy stuff with WebGPU, SSGI and MediaPipe codepen.io/mrdoob_/full/v…

Trends for United States

#NBAFinals
Josh Hart
Stephon Castle
#Knicks
Carter Bryant
National Anthem
Kornet
Clarkson
Madison Square Garden
Avery Wilson
Stabler
Texas Tech
Adam Silver
#SASvsNYK
Alvarado
Draymond
Booed
DJ Khaled
Corbin
New Yorkers

You might like

Director of Product - 3D Rendering @OTOY // Father - Husband - Part-Time Freelancer - Mograph - VFX - Art Direction - Photography // Tweets are my own!
Dino Muhić
@DinoMFX
3K Followers
Freelance C4D artist/designer, with a focus on Character and Storytelling – I like cats and turntablism and colourful robots 💥🍱🎨🎮😺 ♂
Andreas Gaschka
@gaschka
1K Followers
Scanning, texturing, lighting, compositing. I like making things.
Patrick Letourneau
@polygnsndwch
3K Followers
CG-Generalist based in Hamburg, Germany
Lasse Lauch
@lasse_lauch
2K Followers
Creating Cinema 4D plugins and tools.
Kent Barber
@kentbarber
2K Followers
3D generalist, Illustrator, sculptor. Co-founder of Montreal in Motion @mimevent
Patrick Goski
@Pgoski
4K Followers
Senior Motion Designer. Dad to twins. Dutch directness.
Marc Zwaneveld
@motion_designer
2K Followers
Hi there! I am Can Erduman, a freelance Sculptor, Character Animator and Rigger.
Can Erduman
@Can_Erduman
847 Followers
principal engineer at @perforce | former @epicgames @maxonvfx maker of @actionforge | founder of @snowtrack_io | my opinions originate from craigslist
Sebastian Rath
@_sebastianrath
389 Followers