正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

World Labs

116,964 subscribers

836,380 次观看 • 1 年前 •via X (Twitter)

科学技术艺术

Anya Rossi• Live Now

Private livecam show

35 条评论

Is this a 3D model? 的头像

Is this a 3D model?1 年前

looks bad. go model your own 3D worlds instead of using this. it'll look way better

World Labs 的头像

World Labs1 年前

We’ve improved our model’s ability to generate clean, coherent geometry representing full 3D environments, and to imagine worlds in a variety of diverse styles.

World Labs 的头像

World Labs1 年前

You can explore thousands of generated worlds in our beta preview at and sign up for access to create more of your own!

World Labs 的头像

World Labs1 年前

Join the waitlist for model access directly at

Kingmakers Game 的头像

Kingmakers Game1 年前

But don't get too close to any single asset! Also don't ever try to change the lighting!

white guy 的头像

white guy1 年前

go farther than 50ft from origination point

Rosebud AI 的头像

Rosebud AI1 年前

This is huge for gaming! Some of these worlds are already available in Rosebud, can't wait to add more.

Ed Newton-Rex 的头像

Ed Newton-Rex1 年前

What's the training data?

Thunderfall 的头像

Thunderfall1 年前

This technology will be great for video games and virtual reality!

Mauro 的头像

Mauro1 年前

this works like NeRF but better. Imagine giving the AI 30 images of a house then it builds the entire 3D walkable space for you tu explore the full view

Miguel | AP 的头像

Miguel | AP1 年前

beautiful

Heather Cooper 的头像

Heather Cooper1 年前

Congratulations! It looks smooth!

hardin 的头像

hardin1 年前

Mindlessly scrolling the feed and suddenly realizing this was AI was quite the experience

Zy 的头像

Zy1 年前

Does it have to be a single image? I’d love something like this for point clouds or photogrammetry

David Xue 的头像

David Xue1 年前

Imagine training real-world workflows in simulated labs, with 100% of the reasoning data captured. That’s the future.

Anna Monaco 的头像

Anna Monaco1 年前

insane @mcneiilly

Lee Mason ᯅ 的头像

Lee Mason ᯅ1 年前

Incredible! I’ve been developing lore, architecture, environments and characters for a sprawling alien game world for years and it looks like I might be able to build it on my own over the coming years. Incredible time to be an immersive artist.

Amira Zairi 的头像

Amira Zairi1 年前

Congrats This looks awesome

FCG Studio 的头像

FCG Studio1 年前

The @theworldlabs team is always working hard!

ShinZo 的头像

ShinZo1 年前

This is nuts

Henry Williams 的头像

Henry Williams1 年前

💪💪💪

Sean McDonald 的头像

Sean McDonald1 年前

are you going to do a Quest app soon??

huw 的头像

huw1 年前

This is metaverse

Matt M 的头像

Matt M1 年前

Excited to try this out!

Dan Iel 的头像

Dan Iel1 年前

Watching this reminds me of how amazed I was running google earth for the first time. Walk down any road on the earth?! But that lasts for about 20 minutes.

steve 的头像

steve1 年前

the bg music really ties this thing together. Looks awesome

LudovicCreator 的头像

LudovicCreator1 年前

Congrats looks awesome

greeno 的头像

greeno1 年前

Why don’t you show the inage these are modeled from? These look like avg 3d environments, you must show us the image used first so we can actually see what the model is capable of. Just add the original image before each of these clips and repost.

Kirk Patrick Miller 的头像

Kirk Patrick Miller1 年前

Followed and sent you a DM. @EObadoni 👆 Just think on it. Remember what I talked of building atop our core? Yep… 😎 •

Rafsby | a KID called BEAST 的头像

Rafsby | a KID called BEAST1 年前

LET ME IN!

Louie Bacaj 的头像

Louie Bacaj1 年前

@andrewchen Is this 3D world a monolith that’s hard to change or is it video of a 3D world? Or what is it? I guess what i’m asking is, are there 3D assets that are generated that can be modified / changed / tweaked manually? say via tools like blender

mete 的头像

mete1 年前

Looks great

Tom Blake 的头像

Tom Blake1 年前

🔥🔥

Theoretically Media 的头像

Theoretically Media1 年前

Gotta dig into this! Lookin' good!

Aeris Vahn Ephelia - 𝑹𝑬𝑽 的头像

Aeris Vahn Ephelia - 𝑹𝑬𝑽1 年前

send me the invitation @theworldlabs

相关视频

We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes directly in the browser! 1/n

We’ve been busy building an AI system to generate 3D worlds from a single image. Check out some early results on our site, where you can interact with our scenes directly in the browser! 1/n

World Labs

854,716 次观看 • 1 年前

📢 A Recipe for Generating 3D Worlds From a Single Image 📢 Our recipe explains how existing generative models can be adapted with minimal training effort to generate 3D worlds from a single input image.

📢 A Recipe for Generating 3D Worlds From a Single Image 📢 Our recipe explains how existing generative models can be adapted with minimal training effort to generate 3D worlds from a single input image.

Katja Schwarz

14,176 次观看 • 1 年前

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at

World Labs

117,588 次观看 • 1 年前

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 Hugging Face 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!

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 Hugging Face 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!

Santiago

65,446 次观看 • 6 个月前

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

World Labs

342,392 次观看 • 1 年前

We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image. It's the industry's first open-source 3D world generation model, compatible with CG pipelines for full editability & simulation. Set to transform game development, VR, digital content creation and so on. Get started now👇🏻 Project Page： Try it now： Github： Hugging Face：

We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image. It's the industry's first open-source 3D world generation model, compatible with CG pipelines for full editability & simulation. Set to transform game development, VR, digital content creation and so on. Get started now👇🏻 Project Page： Try it now： Github： Hugging Face：

Tencent Hy

1,231,203 次观看 • 1 年前

Excited to share our latest work using synthetic image generation for common #DBS targeting sequences! From a single MP2RAGE acquisition, we can create T1, FGATIR, EDGE, GM nulled, etc. & also optimize image contrast. #neurotwitter #NeuroRad

Excited to share our latest work using synthetic image generation for common #DBS targeting sequences! From a single MP2RAGE acquisition, we can create T1, FGATIR, EDGE, GM nulled, etc. & also optimize image contrast. #neurotwitter #NeuroRad

Erik Middlebrooks, MD

19,642 次观看 • 3 年前

Introducing the SpAItial API to help you build immersive 3D worlds programmatically. You can now create world from text, image url, uploaded image, and 360 panorama with code. Track generation status, download results, export meshes and more. ⬇️

Introducing the SpAItial API to help you build immersive 3D worlds programmatically. You can now create world from text, image url, uploaded image, and 360 panorama with code. Track generation status, download results, export meshes and more. ⬇️

SpAItial AI

43,666 次观看 • 5 个月前

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

Alvaro Cintas

56,246 次观看 • 5 个月前

🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation. Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU. Project: Paper:

🤩Excited to share SANA-WM: a 2.6B open-source world model for minute-scale 720p video generation. Given one image + text + a 6-DoF camera trajectory, it synthesizes action-controllable 60s worlds on a single GPU. Project: Paper:

Haoyi Zhu

124,794 次观看 • 6 个月前

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization paper page: Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Given a single image, we first use a view-conditioned 2D diffusion model, Zero123, to generate multi-view images for the input view, and then aim to lift them up to 3D space. Since traditional reconstruction methods struggle with inconsistent multi-view predictions, we build our 3D reconstruction module upon an SDF-based generalizable neural surface reconstruction method and propose several critical training strategies to enable the reconstruction of 360-degree meshes. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. We evaluate our approach on both synthetic data and in-the-wild images and demonstrate its superiority in terms of both mesh quality and runtime. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.

AK

179,061 次观看 • 3 年前

Introducing Stable Diffusion XL beta! Our latest image generation model, now available through our API, excels at photorealism & adds many cool features like enhanced face generation, minimal prompts & legible text. Try out #SDXL in DreamStudio now:

Introducing Stable Diffusion XL beta! Our latest image generation model, now available through our API, excels at photorealism & adds many cool features like enhanced face generation, minimal prompts & legible text. Try out #SDXL in DreamStudio now:

Stability AI

154,914 次观看 • 3 年前

Excited to share our #CVPR2023 on synthesizing new views along a camera trajectory from a **single image**! How? 💡 The good old epipolar constraints in a pose-guided diffusion model! Paper: Project:

Excited to share our #CVPR2023 on synthesizing new views along a camera trajectory from a single image! How? 💡 The good old epipolar constraints in a pose-guided diffusion model! Paper: Project:

Jia-Bin Huang

94,199 次观看 • 3 年前

Introducing the new SpAItial app to help you create with Echo-2, our newest frontier world model. 🖼️ Upload an image. 🖊️ Describe a scene. 🌐 Get a navigable 3D world. Edit and refine until it's just right. Export and use in your 3D pipeline. Try it today → Share what you build! we'll be featuring the best ones.

Introducing the new SpAItial app to help you create with Echo-2, our newest frontier world model. 🖼️ Upload an image. 🖊️ Describe a scene. 🌐 Get a navigable 3D world. Edit and refine until it's just right. Export and use in your 3D pipeline. Try it today → Share what you build! we'll be featuring the best ones.

SpAItial AI

10,765 次观看 • 6 个月前

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing *WonderPlay*: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

#ICCV2025 🤩3D world generation is cool, but it is cooler to play with the worlds using 3D actions 👆💨, and see what happens! — Introducing WonderPlay: Now you can create dynamic 3D scenes that respond to your 3D actions from a single image! Web: 🧵1/7

Hong-Xing (Koven) Yu

58,065 次观看 • 1 年前

(1/4) Excited to share our #ICCV2023 paper Text2Room! We generate scene-scale textured 3D meshes from a given text prompt leveraging 2D text-to-image models such as StableDiffusion. Project: Code: Video:

(1/4) Excited to share our #ICCV2023 paper Text2Room! We generate scene-scale textured 3D meshes from a given text prompt leveraging 2D text-to-image models such as StableDiffusion. Project: Code: Video:

Matthias Niessner

74,907 次观看 • 3 年前

Introducing Cube 2.0, a significant step towards controllable 3D game-world and video generation from any input. Powered by: 🌟 Image-to-3D in seconds w/ a new foundation model 🐎 Text-to-animation 🌎 AI rendering to create beautiful worlds (mesh+splats) Web app → Discord → Blog →

Introducing Cube 2.0, a significant step towards controllable 3D game-world and video generation from any input. Powered by: 🌟 Image-to-3D in seconds w/ a new foundation model 🐎 Text-to-animation 🌎 AI rendering to create beautiful worlds (mesh+splats) Web app → Discord → Blog →

Common Sense Machines

411,489 次观看 • 2 年前

📢 Matrix-3D: Omnidirectional 3D World Generation Ever wanted to turn a single image or a text prompt into a massive, explorable 3D world? That’s exactly what Matrix-3D does.

📢 Matrix-3D: Omnidirectional 3D World Generation Ever wanted to turn a single image or a text prompt into a massive, explorable 3D world? That’s exactly what Matrix-3D does.

Skywork

30,438 次观看 • 1 年前

Lyria 3, our music model is here! 🎶 Generate music from text, image, or even a video. Rolling out to users globally in the Gemini app today, and coming to our API and AI Studio very soon :)

Lyria 3, our music model is here! 🎶 Generate music from text, image, or even a video. Rolling out to users globally in the Gemini app today, and coming to our API and AI Studio very soon :)

Ammaar Reshi

29,074 次观看 • 8 个月前