DEZ Expert in Design and AI. Design Generation Evangelist.
Toronto
Joined January 2016
- Tweets27.2K
- Following0
- Followers227
- Likes4.3K
XR Multiverse retweeted
here is the github repo!
github.com/Leonxlnx/procedur…
XR Multiverse retweeted
Slop is spreading around the globe!! I created a new repository to track which cities have been infected by @mrdoob’s #threejs New York AI slop
Feel free to create PRs for more cities.
-> github.com/zz85/slop-cities
Some of favorites: Abuja, London, Toronto, Warsaw
XR Multiverse retweeted
World to World
I gave Claude Opus 5.5 a Gaussian splat of a garden and asked it to rebuild the scene in Blender
Procedural objects, Geometry Nodes, Shader Nodes, then captured textures mapped onto selected surfaces
XR Multiverse retweeted
new stream, following paper on fiber-level cloth detail kuiwuchn.github.io/rtfr.html, using math, #threejs and little baking in Blender,
demo: knitstream.vercel.app/
video: youtube.com/live/nZk9gI4y8E8
XR Multiverse retweeted
I just built a WaveFold quantum calculator last night. I just modified it to do Chain Theory.
XR Multiverse retweeted
Inspired by @mrdoob, I built Abuja in 3D. Every street. 37,373 buildings. Aso Rock at full height.
Search any place, get directions, then walk, drive an FCT green taxi or fly there. In your browser.
Every shot in this trailer is the real app 🇳🇬
XR Multiverse retweeted
Introducing Qwen Image 2.1 Realtime ⚡️
I'm releasing V1 of my *2-step* distilled LoRA, and it runs in *realtime* on ZeroGPU ⚡️⚡️
(live editing part of the video was not sped up!)
> DMD2, rank 32
> 2 steps, with quality competitive with Turbo (8-step) and Base (40-step)
> realtime on ZeroGPU (half of an RTX Pro 6000)
LoRA: huggingface.co/linoyts/Qwen-…
Space: huggingface.co/spaces/linoyt…
XR Multiverse retweeted
Qwen 2.1 distilled to just 2 steps and keeping up on quality!
Unlocking real time use-cases on RTX 4090 and above!
Introducing Qwen Image 2.1 Realtime ⚡️
I'm releasing V1 of my *2-step* distilled LoRA, and it runs in *realtime* on ZeroGPU ⚡️⚡️
(live editing part of the video was not sped up!)
> DMD2, rank 32
> 2 steps, with quality competitive with Turbo (8-step) and Base (40-step)
> realtime on ZeroGPU (half of an RTX Pro 6000)
LoRA: huggingface.co/linoyts/Qwen-…
Space: huggingface.co/spaces/linoyt…
XR Multiverse retweeted
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
XR Multiverse retweeted
Spent a bunch of tokens over the last few weeks building a fully procedural New York simulation.
mrdoob.github.io/slop-newyor…
It's only 784KB gzipped and the code is on github, so you can do whatever you want with it ✌️
XR Multiverse retweeted
Kromoss, a new finetune of MOSS Image for even better quality and consistency
huggingface.co/lodestones/Kr…
XR Multiverse retweeted
MuTracer out in the wild 👀 Really cool to see it rendering such detailed models. Thanks for putting it to work, @DeemosTech!
🔥Real-time path tracing for million-polygon PBR 3D Asset generated by AI—in your browser.
🤖Built by @pissang1, this WebGPU renderer combines progressive path tracing, OpenPBR materials, and denoising.
🔍We integrated it into Hyper3D.AI to reveal every detail.
XR Multiverse retweeted
We built a robotics data engine with Astra-level performance at 125x lower cost. And we are open-sourcing the weights today! Introducing Flora, a suite of open models to parse the physical world and turn raw footage into rich training signals.
Flora already powers our in-house data engine, labeling 200K hours of videos a day on 500 GPUs. We created it to scale the frontier for robot learning. Now you own the weights too.
Flora gives you:
- High-quality, timestamped captions to curate and filter human egocentric and robot data;
- Dense progress rewards for quality control and RL post-training;
- Rubrics scoring for real-world benchmarking
Try it today, links in thread:
XR Multiverse retweeted
1/4 Today, we’re releasing Mercury 3. Mercury 3 is by far our most powerful model and the most intelligent diffusion LLM ever released. It outperforms GPT-6 Luna and Haiku 5.5 on quality while running at 1000+ tok/sec.
🤖 Made with AI
XR Multiverse retweeted
Here’s the source & tutorial. Play with it yourself!
chenglou.me/handwired/
github.com/chenglou/handwire…