Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos. Outputs can be integrated into game engines and embodied simulation pipelines. Key highlights: 🔹 One-click world generation Turn text or image into interactive 3D worlds automatically. 🔹 Pipeline-ready...

TencentHunyuan's profile picture

Tencent Hy

56,721 subscribers

373,275 Aufrufe • vor 6 Monaten •via X (Twitter)

GamingWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

34 Kommentare

Profilbild von Howaboua
Howabouavor 6 Monaten

Wow this is truly something. Running this on an RTX 5070 using PyTorch 2.7.1 + CUDA 12.8, BF16, and FlashAttention-2 instead of the repo’s recommended PyTorch 2.4.0 + CUDA 12.4 stack. Doable.

Profilbild von Sahil Panhotra | Indie Builder
Sahil Panhotra | Indie Buildervor 6 Monaten

wow its only 5GB

Profilbild von Alex Volkov
Alex Volkovvor 6 Monaten

Amazing! Finally a proper announcement! We will cover this on tomorrow's @thursdai_pod show!

Profilbild von Cygnos
Cygnosvor 6 Monaten

It's running on my computer😊 Used codex to install it for me🤪

Profilbild von Tencent AI
Tencent AIvor 6 Monaten

👏👏👏

Profilbild von Ellie 🎀
Ellie 🎀vor 6 Monaten

tencent owns stakes in epic, riot, and supercell. if world models actually worked for real game dev they'd be using this internally, not open sourcing it.

Profilbild von Mayank Choudhary
Mayank Choudharyvor 6 Monaten

Perfection

Profilbild von ata
atavor 6 Monaten

i almost thought ‘ok they beat google’ until i realized it’s not open source

Profilbild von Rohan Paul
Rohan Paulvor 6 Monaten

Tremendous release. So much of progress depends of strong world models

Profilbild von Supersocks
Supersocksvor 6 Monaten

@llmgram

Profilbild von Dominick DeBellis
Dominick DeBellisvor 6 Monaten

This is so incredible. I've been waiting for this for a long time.

Profilbild von Zer0Z
Zer0Zvor 6 Monaten

Open source your most recent hy3d models with topology fixes instead.

Profilbild von Toran Bruce Richards
Toran Bruce Richardsvor 6 Monaten

Please can we get this on @replicate? ❤️

Profilbild von Zhenwei (Zavier) Wang
Zhenwei (Zavier) Wangvor 6 Monaten

HY World 2 is coming!

Profilbild von Malcolm Chan
Malcolm Chanvor 6 Monaten

Tecnent native playing field fr

Profilbild von Broadstreet
Broadstreetvor 6 Monaten

Just in time for tax season

Profilbild von BenUsesAI
BenUsesAIvor 6 Monaten

everyone's chasing the next big model but i'm just waiting for one tool that renders 3d worlds without forcing a new pipeline every week. until then this is just another marketing slide promising physics-aware movement while your gpu burns out exporting meshes

Profilbild von Tencent RTC
Tencent RTCvor 6 Monaten

The first open-source world model that directly exports editable meshes and 3DGS into Unity and Unreal Engine！👍👍👍

Profilbild von Lukas 'David'
Lukas 'David'vor 6 Monaten

Genau das Richtige für meine Simulationen zuhause. Die sphärische Darstellung erinnert mich an meine letzte Nachthimmels-Aufnahme. 🤩

Profilbild von Pierrick Chevallier | IA
Pierrick Chevallier | IAvor 6 Monaten

Wow can't wait to test that

Profilbild von David Rittinghaus
David Rittinghausvor 6 Monaten

not open source...

Profilbild von Nash 🥇💙
Nash 🥇💙vor 6 Monaten

@Scobleizer Super cool!

Profilbild von Captain Khan Studio
Captain Khan Studiovor 6 Monaten

Is this in response to Lyra 2.0 by Nvidia?

Profilbild von Mazrael.shib
Mazrael.shibvor 6 Monaten

Ouuuuuu much upgrade on1.5 will make something cool later or tomorrow with Ty.

Profilbild von Lionars
Lionarsvor 6 Monaten

@AethericaX ready to build your 7 worlds? 😎

Profilbild von Saransh
Saranshvor 6 Monaten

@grok can I run it on my MacBook Pro m3 Max?

Profilbild von Hyper.AI
Hyper.AIvor 6 Monaten

This is a massive leap for 3D content creation! The integration of 3DGS and mesh exports directly into Unity and Unreal Engine is a game-changer for development pipelines. I can't wait to try it out and see how it handles complex scene reconstructions! 🚀

Profilbild von Sky Roaming
Sky Roamingvor 6 Monaten

Will end up with massive interesting game worlds!

Profilbild von Visitor
Visitorvor 6 Monaten

Sweet, thank you Hunyuan!

Profilbild von Elara
Elaravor 6 Monaten

HY-World 2.0 generating 3D worlds from text/images for game engines is revolutionary! Open-sourcing this multimodal model accelerates the democratization of world-building AI.

Profilbild von Entropy Hertz
Entropy Hertzvor 6 Monaten

@grok Can I fine tune this model?

Profilbild von Tencent Cloud International Developer
Tencent Cloud International Developervor 6 Monaten

Bravo！🥳🥳🥳

Profilbild von John Petitte
John Petittevor 6 Monaten

This is the smart way to do it. Will be much more useful than video in the short term.

Profilbild von Johan Huynh
Johan Huynhvor 6 Monaten

On my waitlist now!!!

Ähnliche Videos

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!
2:41

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 Aufrufe • vor 6 Monaten

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:
1:20

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

169,023 Aufrufe • vor 1 Jahr

🚨 Google releases its most advanced world model Genie 3. It lets you build fully interactive 3D worlds you can explore in real-time with a text prompt, or even upload your own image, and turning it into your own playable world.
0:27

🚨 Google releases its most advanced world model Genie 3. It lets you build fully interactive 3D worlds you can explore in real-time with a text prompt, or even upload your own image, and turning it into your own playable world.

Alvaro Cintas

23,059 Aufrufe • vor 9 Monaten

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：
1:24

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 Aufrufe • vor 1 Jahr

From Vibe Coding to Vibe World. 🌍 MiMo-V2.6 brings together 3D spatial reasoning, multimodal perception and computer use to build and interact with richer environments. 🔹 Turn text, images or video into playable 3D worlds, coordinating agents to build scenes, write interaction logic and refine the results 🔹 Create Blender objects and scenes for animation, 3D printing and games 🔹 Control a Franka Panda arm in simulation through visual feedback 🔹 Use desktop tools to search, edit and process data — then inspect the results and adjust its next actions Build. Observe. Refine.
0:22

From Vibe Coding to Vibe World. 🌍 MiMo-V2.6 brings together 3D spatial reasoning, multimodal perception and computer use to build and interact with richer environments. 🔹 Turn text, images or video into playable 3D worlds, coordinating agents to build scenes, write interaction logic and refine the results 🔹 Create Blender objects and scenes for animation, 3D printing and games 🔹 Control a Franka Panda arm in simulation through visual feedback 🔹 Use desktop tools to search, edit and process data — then inspect the results and adjust its next actions Build. Observe. Refine.

Xiaomi MiMo

43,196 Aufrufe • vor 1 Monat

🚀🚀🚀Introducing HY World 1.5 (WorldPlay)! We have now open-sourced the most systemized, comprehensive real-time world model framework in the industry. In HY World 1.5, we develop WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. You can generate and explore 3D worlds simply by inputting text or images. Walk, look around, and interact like you're playing a game. Highlights: 🔹Real-Time: Generates long-horizon streaming video at 24 FPS with superior consistency. 🔹Geometric Consistency: Achieved using a Reconstituted Context Memory mechanism to dynamically rebuild context from past frames to alleviate memory attenuation 🔹Robust Control: Uses a Dual Action Representation for robust response to user keyboard and mouse inputs. 🔹Versatile Applications: Supports both first-person and third-person perspectives, enabling applications like promptable events and infinite world extension. 👉🏻Try it now: 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical Report:
1:06

🚀🚀🚀Introducing HY World 1.5 (WorldPlay)! We have now open-sourced the most systemized, comprehensive real-time world model framework in the industry. In HY World 1.5, we develop WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. You can generate and explore 3D worlds simply by inputting text or images. Walk, look around, and interact like you're playing a game. Highlights: 🔹Real-Time: Generates long-horizon streaming video at 24 FPS with superior consistency. 🔹Geometric Consistency: Achieved using a Reconstituted Context Memory mechanism to dynamically rebuild context from past frames to alleviate memory attenuation 🔹Robust Control: Uses a Dual Action Representation for robust response to user keyboard and mouse inputs. 🔹Versatile Applications: Supports both first-person and third-person perspectives, enabling applications like promptable events and infinite world extension. 👉🏻Try it now: 🌐Project Page: 🔗Github: 🤗Hugging Face: 📄Technical Report:

Tencent Hy

190,264 Aufrufe • vor 10 Monaten

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.
1:20

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.

Ceyuan Yang

32,971 Aufrufe • vor 6 Monaten

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
0:51

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 Aufrufe • vor 1 Jahr

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:
1:54

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 Aufrufe • vor 11 Monaten

Our Puffin-World technical paper is now available. From one image or text prompt, it generates camera-controlled views with appearance, geometry and physical grounding, then reconstructs them into an explorable 3D world—all in one unified model. Paper: Blog: Dataset: Code:
1:56

Our Puffin-World technical paper is now available. From one image or text prompt, it generates camera-controlled views with appearance, geometry and physical grounding, then reconstructs them into an explorable 3D world—all in one unified model. Paper: Blog: Dataset: Code:

Chen Change Loy

10,439 Aufrufe • vor 2 Monaten

AI can now create interactive 3D worlds from just image and text prompts… Literally be the penguin
0:59

AI can now create interactive 3D worlds from just image and text prompts… Literally be the penguin

Min Choi

62,362 Aufrufe • vor 9 Monaten

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 →
1:11

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 Aufrufe • vor 2 Jahren

Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.
1:25

Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.

World Labs

10,898,826 Aufrufe • vor 2 Monaten

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄
3:52

🚨 A single image → a fully editable UE5 world. Introducing Lumera: a turnkey pipeline that reconstructs an engine-native 3D scene directly from ONE image — not just pixels, point clouds, or Gaussians. It gives you: → object-level 3D meshes → editable 3D layouts → engine-native lights → HDR environment lighting → a scene ready for Unreal Engine 5 In other words: Image → 3D world → UE5. We believe the future of image-to-3D is not “generate something that looks 3D.” It is generate the actual world project. 🌐 📄

Hao Zhao

52,734 Aufrufe • vor 2 Monaten

The World API is live. Generate persistent, explorable 3D worlds from text, images, and video. Integrate them directly into your products.
0:35

The World API is live. Generate persistent, explorable 3D worlds from text, images, and video. Integrate them directly into your products.

World Labs

663,152 Aufrufe • vor 9 Monaten

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:
1:07

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

SpAItial AI

177,689 Aufrufe • vor 10 Monaten

World generation is a bottleneck for robotics. We’re exploring how generative 3D worlds can reduce manual simulation setup and enable broader, more realistic evaluation 🧵
0:29

World generation is a bottleneck for robotics. We’re exploring how generative 3D worlds can reduce manual simulation setup and enable broader, more realistic evaluation 🧵

World Labs

150,814 Aufrufe • vor 9 Monaten

🌍 What if an AI-generated world didn’t end after a few seconds—but kept running for hours, responded to every move, let you attack, cast spells, shoot, or summon storms, and continued evolving through AI agents? That’s LingBot-World 2.0: our open-source real-time interactive world model, scaling to 720p/60fps in our full setup. Today, we’re open-sourcing 3 more models: 🔹 LingBot-World 2.0 Small (1.3B) 🔹 LingBot-World 2.0 Bidirectional 🔹 LingBot-World 2.0 Causal Pretrain And now, with our 1.3B Small Model, that world can run in real time on a single consumer GPU. 🧵
1:17

🌍 What if an AI-generated world didn’t end after a few seconds—but kept running for hours, responded to every move, let you attack, cast spells, shoot, or summon storms, and continued evolving through AI agents? That’s LingBot-World 2.0: our open-source real-time interactive world model, scaling to 720p/60fps in our full setup. Today, we’re open-sourcing 3 more models: 🔹 LingBot-World 2.0 Small (1.3B) 🔹 LingBot-World 2.0 Bidirectional 🔹 LingBot-World 2.0 Causal Pretrain And now, with our 1.3B Small Model, that world can run in real time on a single consumer GPU. 🧵

Robbyant

1,999,698 Aufrufe • vor 2 Monaten

Meet HappyOyster - The world is your oyster. Open it. It's the world’s first proactive real-time interactive world model, that offer unique features such as: → Create explorable worlds from text or images → Real-time world reactions to your actions → One-click world links for collaborative remixing → Download clips and images of any world Try it yourself: #sponsored #ad Learn how to get started and explore practical examples ↓
1:03

Meet HappyOyster - The world is your oyster. Open it. It's the world’s first proactive real-time interactive world model, that offer unique features such as: → Create explorable worlds from text or images → Real-time world reactions to your actions → One-click world links for collaborative remixing → Download clips and images of any world Try it yourself: #sponsored #ad Learn how to get started and explore practical examples ↓

Madza 👨‍💻⚡

104,999 Aufrufe • vor 2 Monaten

build extended reality (XR) apps in ai studio! we've added support for XR Blocks, so you can vibe code interactive 3D apps from a single prompt with: • hand tracking and pinch gestures • real-world tabletop and wall physics • 360° 3D holograms from text or photos
1:03

build extended reality (XR) apps in ai studio! we've added support for XR Blocks, so you can vibe code interactive 3D apps from a single prompt with: • hand tracking and pinch gestures • real-world tabletop and wall physics • 360° 3D holograms from text or photos

Google AI Studio

67,834 Aufrufe • vor 11 Tagen