Ulf

møpmøp

[Ulf @stilfuchs]

@fofrAI tactical exit 😁👍

[Flat2VR Modding @Flat2VR]

Morrowind VR Mod Coming To Standalone Quest!

@TeamBeefVR is working on a free and open source for Meta Quest.

Can you imagine going to a huge park and physically walking and questing through part of Tamriel?

[Jake Fitzgerald @earthtojake]

claude fable 5 designed a humanoid and them made it... dance? 🕺

i asked it to write javascript to transform the parametric step file directly in the browser

these motions are simple, but demonstrate deep spatial reasoning capability

[Leandro von Werra @lvwerra]

Fable is the new leader on CADGenBench!

Still long way to go:

[Ulf @stilfuchs]

👀

[Zach Dive @zachdive]

Just let Claude Fable 5 rawdog your CAD software

One @adamdotnew prompt and it designs an entire Boeing 747 in Autodesk Fusion

[Ulf @stilfuchs]

@DanyBittel Waiting for this 😁😉

[aescripts+aeplugins @aescripts]

Save 25% on Projection 3D V5 and other featured products until June 12.

Made with Projection 3D by @mustard_yeah
https://t.co/ufaP2pzFHT
#aftereffects #aescripts #projection3d
Repetition
Repetition.
#motionglitch #glitchartist #motiontracking #creativevfx

[Ulf @stilfuchs]

@threejs

[Michael Rabinovich @MikushRab]

Introducing CADGenBench: measure how well AI systems produce engineering-grade 3D parts!

While current models can generate 3D parts, they are far from precise enough to build functional parts. We built a benchmark to systematically measure their capabilities on two tasks:

1. Generation from an engineering drawing of a part
2. Editing: given an existing STEP file and a requested change

The benchmark is tool-agnostic. It makes no assumptions about how you build the model. You can vary the LLM, and you can vary the environment. Use build123d, Onshape, Autodesk, or a model without an LLM entirely. We open sourced the scoring engine and a reference baseline on top of build123d.

A collaboration between Hugging Face and @mecadoinc!

Submission space: https://t.co/40kfjsd3Dv
Code repository: https://t.co/fvmMjzrIzp

[Alex @alexfredo87]

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

[Victor M @victormustar]

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).

[Ulf @stilfuchs]

@PurzBeats The haters 🤣🤣

[KIRI Engine - 3D Scanner App @KIRI_Engine_App]

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 👇

[Spenser Dickerson @SpenserFX]

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! 🔥🔥🔥

[80 LEVEL @80Level]

Take a look at Thomas Schreiter's impressively realistic 3D portrait of actor Willem Dafoe.

All the skin details were made by hand: https://t.co/2OEPqKOQxe

[Carlos Barreto @carlosedubarret]

CEB SAM 3d Body V1 Free

Download at
https://t.co/OmTiTvpZst

#mocap #b3d

[Ostris @ostrisai]

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 🧵

[KIRI Engine - 3D Scanner App @KIRI_Engine_App]

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.

[Andrew Price @andrewpprice]

3D Gaussian Splat support for Blender is finally in development https://t.co/kMAPL6smXq 💪

[Sparseal @sparseal]

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.