Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

SimReady assets generated from a simple prompt! No 3D artist needed. Last week at SIGGRAPH, Lightwheel launched SimReadyGen - an agentic SimReady asset generator. Since then, our team has been improving the experience, including an in browser asset viewer. I recorded this quick video to give you a peek... show more

Jonathan Stephens

13,540 subscribers

11,553 Aufrufe • vor 1 Monat •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 Kommentare

Profilbild von YajvinTandon

YajvinTandonvor 1 Monat

@LightwheelAI Sadly

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI The team is aware, you can access it here: or

Profilbild von Lightwheel

Lightwheelvor 1 Monat

Prompt to simready assets in minutes! Thanks for sharing our latest release.

Profilbild von Martin Elbs

Martin Elbsvor 1 Monat

@LightwheelAI Great demo!

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI Thanks! Full review coming to my YouTube channel next week.

Profilbild von Numan

Numanvor 1 Monat

@LightwheelAI 10 dollas per asset is out of the question - ill rather hire a real 3d artist or just become one

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI What would be a fair price in your opinion?

Profilbild von TBD

TBDvor 1 Monat

@LightwheelAI add a www handler otherwise is 404 on the link

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI 🤦‍♂️ I will let my team know

Profilbild von Rad3k

Rad3kvor 1 Monat

@LightwheelAI Also fix SSL, just trying to be helpful :-)

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

@LightwheelAI No 3d artist needed, that job market shrinking fast

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI Sadly it has been for a while.

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

@LightwheelAI Tough shift for a lot of skilled folks, hard to ignore.

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI It’s early days. But it’s been coming and getting good quick. @tripoai is also doing excellent work creating mesh assets for games, animation, etc.

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

@LightwheelAI @tripoai Will check out tripoai, good to see more players pushing this forward.

Profilbild von Ilya

Ilyavor 1 Monat

This is an important step for simulation workflows. The easier it becomes to generate high-quality SimReady assets, the easier it becomes to create diverse environments and edge cases at scale. The real unlock is turning that flexibility into better training and faster iteration for physical AI.

Profilbild von illeatmyhat

illeatmyhatvor 1 Monat

@LightwheelAI For something at SIGGRAPH they kind of skipped over all of the important stuff like how does the geometry even get made?

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI Nobody knows. It’s AI 🤣 I plan to do a more technical deep dive on my YouTube channel.

Profilbild von clankr

clankrvor 1 Monat

@LightwheelAI Wow. Unfortunately, there are some issues accessing the site. Is it possible to generate assets by referencing and describing real-world objects, or is it limited to the two options shown?

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

@LightwheelAI Didn't realize we had redirect issues. You can access it here: We are still developing the generator. Currently you just text prompt. In the future, you may be able to add reference image and prompt.

Profilbild von Jonathan Stephens

Jonathan Stephensvor 1 Monat

If you all tried the link and it was broken, you can access it here:

Ähnliche Videos

Introducing SimReadyGen. Agentic simulation generation for Physical AI. From a text prompt to physically accurate SimReady assets at scale. Robot training demands physically accurate environments at a scale traditional asset creation can't match. SimReadyGen closes that gap. Every generated asset carries measured physics, not estimates. Behind it is SimReady Foundry, our measured-physics pipeline: we measure how real objects behave — contact, friction, dynamics — and turn those measurements into ground-truth simulation parameters. Built on OpenUSD and integrated with NVIDIA Robotics Omniverse Libraries, SimReadyGen moves directly into Isaac Sim and Isaac Lab workflows. Try it today: Read the announcement: #PhysicalAI #Robotics #Simulation #OpenUSD

Introducing SimReadyGen. Agentic simulation generation for Physical AI. From a text prompt to physically accurate SimReady assets at scale. Robot training demands physically accurate environments at a scale traditional asset creation can't match. SimReadyGen closes that gap. Every generated asset carries measured physics, not estimates. Behind it is SimReady Foundry, our measured-physics pipeline: we measure how real objects behave — contact, friction, dynamics — and turn those measurements into ground-truth simulation parameters. Built on OpenUSD and integrated with NVIDIA Robotics Omniverse Libraries, SimReadyGen moves directly into Isaac Sim and Isaac Lab workflows. Try it today: Read the announcement: #PhysicalAI #Robotics #Simulation #OpenUSD

Lightwheel

12,221 Aufrufe • vor 2 Monaten

Just tried Lux3D: an AI 3D generator built by Manycore Tech You drop in an image or text prompt… and it gives you a full, editable 3D asset with solid geometry + materials. No 3D modeling skills needed. This one actually feels different.

Just tried Lux3D: an AI 3D generator built by Manycore Tech You drop in an image or text prompt… and it gives you a full, editable 3D asset with solid geometry + materials. No 3D modeling skills needed. This one actually feels different.

Sharon Riley

21,697 Aufrufe • vor 1 Monat

Codex is unusable. I generated one image with GPT Image 2.0, gave it to Codex, and used one simple prompt: “Create me a web game from this image.” You give it a simple image like this, and suddenly you realize you can build: • a voxel map • an editor • tile animations • a playable browser prototype This is getting ridiculous.

Codex is unusable. I generated one image with GPT Image 2.0, gave it to Codex, and used one simple prompt: “Create me a web game from this image.” You give it a simple image like this, and suddenly you realize you can build: • a voxel map • an editor • tile animations • a playable browser prototype This is getting ridiculous.

Givros

83,376 Aufrufe • vor 4 Monaten

I failed at using the draw on 3D feature properly last time 😅 So let's try it again! how did I do this time? 💖 If you want any of the asset codes in this video feel free to leave a comment!

I failed at using the draw on 3D feature properly last time 😅 So let's try it again! how did I do this time? 💖 If you want any of the asset codes in this video feel free to leave a comment!

かたや・りにあ💖 C107水曜西へ35b

201,805 Aufrufe • vor 1 Jahr

If you have an idea for an app and you want to build it fast and deploy it with a lot of the controls that a developer would want, the experience on Replit ⠕ is pretty amazing. I recorded this quick video while I'm sitting here at Philz before dinner tonight. Let me know your thoughts: Who's using Replit? Who likes it? What don't you like? What works? What doesn't?

If you have an idea for an app and you want to build it fast and deploy it with a lot of the controls that a developer would want, the experience on Replit ⠕ is pretty amazing. I recorded this quick video while I'm sitting here at Philz before dinner tonight. Let me know your thoughts: Who's using Replit? Who likes it? What don't you like? What works? What doesn't?

Ryan Carson

29,729 Aufrufe • vor 1 Jahr

GPT-6 coded an entire world: a busy harbor you can step inside. From a single prompt and an asset pack, it assembled a container port with towering cranes, docked ships, rows of containers, and forklifts across the yard, all within an explorable 3D scene. A first look at our upcoming Code-for-3D benchmark, featuring the text-to-scene setting.

GPT-6 coded an entire world: a busy harbor you can step inside. From a single prompt and an asset pack, it assembled a container port with towering cranes, docked ships, rows of containers, and forklifts across the yard, all within an explorable 3D scene. A first look at our upcoming Code-for-3D benchmark, featuring the text-to-scene setting.

SimWorld

25,141 Aufrufe • vor 25 Tagen

An awesome new feature is available in the Bulk Generator since a few days ago, allowing you to import any existing league from Football Kit Archive into the generator. Also available on FM Kit Creator. Have you given it a try already? 🎲🔥

An awesome new feature is available in the Bulk Generator since a few days ago, allowing you to import any existing league from Football Kit Archive into the generator. Also available on FM Kit Creator. Have you given it a try already? 🎲🔥

EAFC Kit Creator

28,594 Aufrufe • vor 6 Monaten

Omniforge First Looks | v1 Genesis Preview In an era where platforms claim the lions share of the profit and control the access, Omniforge delivers digital sovereignty through our $KNDX pipelines that turn your ideas into tokenized, interoperable, and evolving 3D assets. No coding or developer experience needed. Watch your ideas & creations transform into high-fidelity 3D assets, mint it as a kNFT in OpenUSD, and see it land in your wallet with royalties baked into our smart contracts that offer recurring payments to you; no matter what platform your asset travels to.

Omniforge First Looks | v1 Genesis Preview In an era where platforms claim the lions share of the profit and control the access, Omniforge delivers digital sovereignty through our $KNDX pipelines that turn your ideas into tokenized, interoperable, and evolving 3D assets. No coding or developer experience needed. Watch your ideas & creations transform into high-fidelity 3D assets, mint it as a kNFT in OpenUSD, and see it land in your wallet with royalties baked into our smart contracts that offer recurring payments to you; no matter what platform your asset travels to.

Kondux

27,676 Aufrufe • vor 1 Jahr

I love our little simulation tool. you can ask it to record a video and it can even resize. all from a slack bot here's an improved prompt input in opencode at small sizes

I love our little simulation tool. you can ask it to record a video and it can even resize. all from a slack bot here's an improved prompt input in opencode at small sizes

James Long

41,537 Aufrufe • vor 1 Monat

This is how I cook spaghetti aglio olio. Simple, quick, cheap and delicious. Give it a try, you probably won’t want to eat Maggi anymore at the middle of the night 😄

This is how I cook spaghetti aglio olio. Simple, quick, cheap and delicious. Give it a try, you probably won’t want to eat Maggi anymore at the middle of the night 😄

Roman Akramovich

83,192 Aufrufe • vor 4 Monaten

Built a simple flare generator in IlluGen today. Really fun to play around with the procedural nature of the tool and just make some cool things! Infinite variations and really easy to find something to leap off of quickly. If you want to give the generator a shot in IlluGen, feel free to download it here:

Built a simple flare generator in IlluGen today. Really fun to play around with the procedural nature of the tool and just make some cool things! Infinite variations and really easy to find something to leap off of quickly. If you want to give the generator a shot in IlluGen, feel free to download it here:

Nick Seavert

24,664 Aufrufe • vor 1 Jahr

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh

122,572 Aufrufe • vor 3 Monaten

This guy's in a foreign country and I've not spoken to him, but I was struck by what an ingenious design this perpetual motion generator. By the size of the generator, it looks like it's a 20 kilowatt, which equates to about 60 amps @ 230 volts. Enough for a small house. GREAT

This guy's in a foreign country and I've not spoken to him, but I was struck by what an ingenious design this perpetual motion generator. By the size of the generator, it looks like it's a 20 kilowatt, which equates to about 60 amps @ 230 volts. Enough for a small house. GREAT

DeepWebSlinger

67,516 Aufrufe • vor 1 Jahr

This feels like the GPT-3 moment for browser agents. I used to waste hours trying to get commit counts for the 73k people who starred our repo⭐️ (there’s still no real API for this). Today I recorded the workflow once for a single profile - (<5s). The agent then (<5min): - learned the pattern - generalized it to hundreds of profiles & repos - generated a clean API I can call from anywhere This is the moment browser agents stopped being a demo - and became actually useful. Reply “skill” and I’ll send you the generator.

Magnus Müller

18,381 Aufrufe • vor 10 Monaten

With Veo 3’s new image to video feature, you can transform a photo into an 8-second video with sound. Just create a prompt describing how you want your image to move, then watch it come to life. Try it in Google Vids today at

With Veo 3’s new image to video feature, you can transform a photo into an 8-second video with sound. Just create a prompt describing how you want your image to move, then watch it come to life. Try it in Google Vids today at

Google Workspace

87,692 Aufrufe • vor 1 Jahr

GPT-6 Astra can already plan, code, and build. The more interesting question is what happens when it can call a dedicated 3D tool at the exact moment a project needs an asset. So we connected Hyper3D Rodin MCP and asked Astra to build an interactive Solar System Explorer. Astra handled the app logic and integration. When it needed 3D models, it called Hyper3D Rodin directly. Hyper3D Rodin generated the required assets, and Astra brought them back into the project and continued building from there. That is where the workflow gets useful. Instead of stopping to search for assets or creating them manually, Astra can keep moving while Hyper3D handles the specialized 3D generation, with more control over the output and assets that are easier to integrate into the final project. The result is a browser-based solar system where the generated 3D models are part of the actual experience, not just outputs sitting in a model viewer.

GPT-6 Astra can already plan, code, and build. The more interesting question is what happens when it can call a dedicated 3D tool at the exact moment a project needs an asset. So we connected Hyper3D Rodin MCP and asked Astra to build an interactive Solar System Explorer. Astra handled the app logic and integration. When it needed 3D models, it called Hyper3D Rodin directly. Hyper3D Rodin generated the required assets, and Astra brought them back into the project and continued building from there. That is where the workflow gets useful. Instead of stopping to search for assets or creating them manually, Astra can keep moving while Hyper3D handles the specialized 3D generation, with more control over the output and assets that are easier to integrate into the final project. The result is a browser-based solar system where the generated 3D models are part of the actual experience, not just outputs sitting in a model viewer.

GitHub Projects Community

11,097 Aufrufe • vor 24 Tagen

“This took less than an hour." Interactive 3D is becoming essential across industries - but for a lot of teams, it’s still out of reach. That’s why we built Unity Studio - an intuitive, web-based, no-code editor that helps teams across industries, from manufacturing to retail, turn existing 3D assets into interactive experiences, straight from the browser. Check out what it looks like to go from a static 3D file to a fully interactive demo in under an hour. 🔗 Try it out yourself with a free 30 day Unity Studio trial:

“This took less than an hour." Interactive 3D is becoming essential across industries - but for a lot of teams, it’s still out of reach. That’s why we built Unity Studio - an intuitive, web-based, no-code editor that helps teams across industries, from manufacturing to retail, turn existing 3D assets into interactive experiences, straight from the browser. Check out what it looks like to go from a static 3D file to a fully interactive demo in under an hour. 🔗 Try it out yourself with a free 30 day Unity Studio trial:

Unity

10,408 Aufrufe • vor 4 Monaten