Krish retweeted
We just open-sourced an entire 3D team for Blender.
Introducing the Scenario plugin.
Use it inside Blender, or let Claude Code run it through MCP.
📁/scenario-plugin
┃
┣ 📁 Concept Artist
┃ ┣ 📁 Concept Art From a Prompt
┃ ┗ 📁 References From Your Viewport
┃
┣ 📁 3D Artist
┃ ┣ 📁 Meshes From Text or a Photo
┃ ┗ 📁 Retexture or Remesh the Selected Mesh
┃
┣ 📁 Animator
┃ ┣ 📁 Rig the Selected Character
┃ ┗ 📁 Motion From Text
┃
┣ 📁 Surfacing Artist
┃ ┣ 📁 PBR Materials Onto Any Slot
┃ ┗ 📁 Maps From a Photo
┃
┣ 📁 Layout Artist
┃ ┣ 📁 Greybox From a Description
┃ ┗ 📁 360 Worlds and Skies
┃
┣ 📁 Camera Operator
┃ ┣ 📁 Camera Path From a Sentence
┃ ┗ 📁 Orbits, Dollies, Cranes and Flyovers
┃
┣ 📁 Render Artist
┃ ┣ 📁 Viewport to Finished Still
┃ ┗ 📁 Playblast to Finished Shot
┃
┗ 📁 Sound Designer
┣ 📁 Music, Voice and SFX
┗ 📁 Dropped on Your Sequencer
Comment "BLENDER" and I'll send you the GitHub repo.
Krish retweeted
Kimi K3 is still a beast in frontend coding
this lakeside cabin scene costed only $4.1
it's basically 90% of Opus5.5 but 8x cheaper
building a lakeside cabin scene in 2024:
> a 3D artist
> modeling, texturing, lighting
> a game engine just to walk around it
> one fixed render at the end
Stillwater, 2026:
> one prompt
> a forest lake with a cabin on stilts, a rowboat at the dock and an island in the middle
> an old mossy shack hiding back in the trees
> runs in a browser tab... drag, zoom, pan, or hit Tour and it flies you through 5 stops
the part i keep coming back to is the detail
lily pads with little white flowers, cattails at the waterline, the whole cabin mirrored in the lake
Krish retweeted
Forget lidar.
One single camera.
Runs in real time & is open source:
A streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences.
End-to-end.
Optimization tricks, cleanup steps?
Nope.
And it beats both streaming and even some offline methods.
Perception is becoming software-first.
Closer to machines that see and understand the world as it unfolds.
Thanks for sharing, @YinghaoXu1
📍Models: huggingface.co/robbyant/ling…
Project page: technology.robbyant.com/ling…
Code: github.com/Robbyant/lingbot-…
Paper: arxiv.org/abs/2604.14141
——
Weekly robotics and AI insights.
Subscribe free: 22astronauts.com
Krish retweeted
HOY UNA INDUSTRIA ENTERA DEJÓ DE TENER SENTIDO
alguien subió a GitHub un repo que coge cualquier foto y te devuelve un mundo 3d explorable: mallas con físicas, splat del fondo, audio ambiente. todo.
entra una imagen.
sale un mundo. cinco minutos.
la gente que lleva diez años aprendiendo Blender se ha pasado el día mirando esto en silencio.
se llama image-blaster.
os dejo el repo abajo.
Krish retweeted
exiting whoop after 18 months.
kept the strap, ditched the subscription. it now runs fully local on zhoop (my fork of noop). no fluff metrics, my data stays on my phone.
ai killed vendor lock-in.
Krish retweeted
A pivotal moment for real estate! 🏡
Capturing a property in 3D used to mean a $5,000 LiDAR scanner. This house was scanned with a $500 @insta360 X5 - a consumer 360 camera.
And best of all? All of the software is free and open source! It's based on a technique called 3D Gaussian splatting:
🪄 Splat creation: Spirula Studio
🖼️ Splat rendering: @PlayCanvas
So for $500, you can present any property online and let prospective purchasers freely explore as if it was a videogame. 🎮
[1/3]
Krish retweeted
🚨Architects are going to hate this.
Someone just open-sourced a full 3D building editor that runs entirely in your browser.
No AutoCAD. No Revit. No $5,000/year licenses.
It's called Pascal Editor.
Built with React Three Fiber and WebGPU -- meaning it renders directly on your GPU at near-native speed.
Here's what's inside this thing:
→ A full building/level/wall/zone hierarchy you can edit in real time
→ An ECS-style architecture where every object updates through GPU-powered systems
→ Zustand state management with full undo/redo built in
→ Next.js frontend so it deploys as a web app, not a desktop install
→ Dirty node tracking -- only re-renders what changed, not the whole scene
Here's the wildest part:
You can stack, explode, or solo individual building levels. Select a zone, drag a wall, reshape a slab -- all in 3D, all in the browser.
Architecture firms pay $50K+ per seat for BIM software that does this workflow.
This is free.
100% Open Source.
Krish retweeted
Film a place once. Turn it into a 3D model.
Choose your shots later. Any angle. Any camera move.
Castello di Amorosa, Napa Valley.
~20 Million splats from 20min 360 Video.
(10min Insta 360 X5, 10min Avata 360)
Processed locally in Nvidia RTX 5090 Laptop in about 12 hours (6 hours for SFM, 6 hours for Splat training) using AirVis Studio. airvisstudio.com
See in 4K full screen with audio.
Krish retweeted
i gave Grok Bot $80 and told it one thing:
if you can’t pay for yourself within a week - i’m shutting you down
that experiment grew into YGGDRASIL
my GROK PROFIT TREE
after that, i barely touched it
the bot had its own cloud machine, browser, terminal, and access to prediction markets, then set up a routine to run every 20 minutes
→ scan markets closing within the next 24 hours
→ look for gaps above 6% between market price and its own estimate
→ never risk more than 3% of the bankroll on one position
→ adjust the strategy after every losing streak
9 hours in, YGGDRASIL was almost dead
$80 was down to $11
instead of forcing the same strategy, Grok Bot dropped half the markets, switched to short-duration sports events, and reduced position size
36 hours later, the account was at $2,760
i didn’t change the code
i didn’t sit in front of charts
i didn’t tell it which trade to take next
i just gave YGGDRASIL one reason to keep growing:
earn enough to stay alive
the weirdest part isn’t even $80 → $2,760
it’s watching an $80 experiment grow into a GROK PROFIT TREE that now pays for its own existence
Krish retweeted
You better use this open source one
github.com/segfault42/helios…
卧槽
影眸科技(Hyper3D) 发布的世界生成模型 WorldGen 有点东西
它和其他可交互世界模型有不一样,它可以从一张 2D 图片,生成是一个完整的自带物理规律 3D 场景
更牛P的是:
每个物体都是独立的:就是场景里的桌子、椅子、小道具都能单独拉出来拆解成科移动、替换或微调的子3D模型。
自带物理规律:模型能理解空间摆放关系,并自动推断出碰撞、质量、摩擦力等属性。
直接对接生产管线:生成的资产可以无缝导入 Blender、Unity 或团结引擎,直接用于游戏关卡搭建、影视制作、XR 内容以及具身智能(机器人/机械臂)仿真训练
Krish retweeted
No more need to extract video frames at a constant interval for 3DGS!
Came across this tool that extracts frames for optimal inter-frame overlap and parallax! github.com/morishuz/frame-ex…
Krish retweeted
In two years, the level of detail you can capture in a 3D Gaussian Splat has skyrocketed. In this scene on SuperSplat, I can zoom right in on a certificate and the text is perfectly legible. Imagine where we will be in another 2 years. 🪄
Krish retweeted
i like big splats and i cannot lie.
you can now compress, tile and stream city scale 3d gaussian splats -- glTF has an official 3DGS extension now too.
this is what the future of google earth looks like. no more broccoli trees. no more melted powerlines. immaculate ground level detail that actually holds up.
Krish retweeted
EDGS: Eliminating Densification for Efficient Convergence of 3DGS
Contributions:
• We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources.
• Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality.
• Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.
New open-source 3D world-generation model.
I'm rendering a couple of worlds in the video, so check it out.
You'll find the GitHub and the @huggingface links to the model below.
This is a multi-modal world model that you can use for a bunch of things:
• To generate new worlds
• To reconstruct worlds
• To simulate 3D interactive worlds from a prompt, images, or a video
You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds).
You can also generate 3D characters in the world and walk around. Pretty fun stuff!































