Loading video...

Video Failed to Load

Go Home

This is Genesis. Revolutionary new AI physics engine. You can turn text into 3D worlds; Simulate robots, humans, & objects; Runs at 43M FPS (yes, millions!) 8 wild demos:

minchoi's profile picture

Min Choi

376,676 subscribers

786,101 views • 1 year ago •via X (Twitter)

EducationNews & PoliticsScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

12 Comments

Min Choi's profile picture
Min Choi1 year ago

1. Humanoid walks forward - Sim2Real

Min Choi's profile picture
Min Choi1 year ago

2. Generating 4D dynamical & physical world

Min Choi's profile picture
Min Choi1 year ago

3. Quadraped double-backflip - Sim2Real

Min Choi's profile picture
Min Choi1 year ago

4. Character Motion Generation

Min Choi's profile picture
Min Choi1 year ago

5. Quadraped locomotion with various gaits - Sim2Real

Min Choi's profile picture
Min Choi1 year ago

6. 3D & Fully Interactive Scene Generation - Restaurant

Min Choi's profile picture
Min Choi1 year ago

7. Quadraped performs handstand with its 2 front legs. - Sim2Real

Min Choi's profile picture
Min Choi1 year ago

8. Speech Audio, Facial Animation & Emotion Generation

Min Choi's profile picture
Min Choi1 year ago

Project page here: GitHub repo:

Min Choi's profile picture
Min Choi1 year ago

If you enjoyed this thread, Follow me @minchoi and please Bookmark, Like, Comment & Repost the first Post below to share with your friends:

Min Choi's profile picture
Min Choi1 year ago

Official Genesis Project Announcement:

Evgeny Grishakof's profile picture
Evgeny Grishakof1 year ago

🤖 Survive Among Broken Robots Discover a mysterious junkyard planet where broken robots rule. Build, craft, farm and uncover secrets in this captivating survival game. 🎮 Add to your wishlist on Steam:

Related Videos

It's happening... Google DeepMind is about to drop Genie 3 This AI can generate interactive 3D worlds with just text... And you can interact with objects in real time 🤯
0:57

It's happening... Google DeepMind is about to drop Genie 3 This AI can generate interactive 3D worlds with just text... And you can interact with objects in real time 🤯

Min Choi

727,432 views • 5 months ago

Step into a new era of creation. With Cube 3D, turn simple text prompts into 3D objects in seconds. What will you build?
0:44

Step into a new era of creation. With Cube 3D, turn simple text prompts into 3D objects in seconds. What will you build?

Roblox

1,058,658 views • 1 year ago

3D AI is getting wild! Meshy AI can now build an entire 3D worlds with Blender.
0:35

3D AI is getting wild! Meshy AI can now build an entire 3D worlds with Blender.

el.cine

188,690 views • 1 year ago

They Don’t Want To Turn Robots Into Humans… They Want To Turn Humans Into Robots. 🤖👁️
1:07

They Don’t Want To Turn Robots Into Humans… They Want To Turn Humans Into Robots. 🤖👁️

vegastar

19,090 views • 1 month ago

ELON MUSK: THE FINAL TEST FOR AI IS NEW PHYSICS “If an AI cannot figure out new physics, it’s clearly not equal to humans, nor has surpassed humans because humans have figured out new physics. Physics is just deepening one’s insight into how reality works.”
3:21

ELON MUSK: THE FINAL TEST FOR AI IS NEW PHYSICS “If an AI cannot figure out new physics, it’s clearly not equal to humans, nor has surpassed humans because humans have figured out new physics. Physics is just deepening one’s insight into how reality works.”

Lacey

65,840 views • 6 months ago

This is wild. China's Alibaba just dropped Live Avatar. This AI turns any voice into a realtime, talking avatar with infinite length at 20 FPS. 10 wild demos:👇 1. Ilya interview that never happened
1:26

This is wild. China's Alibaba just dropped Live Avatar. This AI turns any voice into a realtime, talking avatar with infinite length at 20 FPS. 10 wild demos:👇 1. Ilya interview that never happened

Min Choi

220,656 views • 7 months ago

MoVerse turns an image into a navigable 3D world. Runs at 8 FPS on a single RTX 4090.
0:32

MoVerse turns an image into a navigable 3D world. Runs at 8 FPS on a single RTX 4090.

⚡AI Search⚡

18,555 views • 29 days ago

"I need to simulate this random idea immediately" - this is what delays development of my physics engine. Spikes of curiosity. What would you try simulating if you had access to this physics engine?
0:41

"I need to simulate this random idea immediately" - this is what delays development of my physics engine. Spikes of curiosity. What would you try simulating if you had access to this physics engine?

Zolden

60,288 views • 8 months ago

omg.. I can't believe this.. this Unreal Engine AI plugin lets you generate 3D model in seconds with text prompt, and even chat with AI to optimise your scene.. A revolutionary AI tool for 3D creation. here's how to get started:
0:46

omg.. I can't believe this.. this Unreal Engine AI plugin lets you generate 3D model in seconds with text prompt, and even chat with AI to optimise your scene.. A revolutionary AI tool for 3D creation. here's how to get started:

el.cine

129,956 views • 1 year ago

This is the craziest AI news this month An open source generative physics engine able to generate 4D worlds
3:26

This is the craziest AI news this month An open source generative physics engine able to generate 4D worlds

Allen T.

608,976 views • 1 year ago

This is peak... Google just unveiled Genie 3 This AI generates photorealistic & 3D worlds from a text prompt and image... that you can explore in real-time Clearing a path towards AGI 10 wild examples + how to try below 1. Control a shiny marble
0:20

This is peak... Google just unveiled Genie 3 This AI generates photorealistic & 3D worlds from a text prompt and image... that you can explore in real-time Clearing a path towards AGI 10 wild examples + how to try below 1. Control a shiny marble

Linus ✦ Ekenstam

44,603 views • 5 months ago

3D arrived to Krea. this new feature lets you turn images into 3D objects and use them in our Real-time tool. free for everyone.
0:26

3D arrived to Krea. this new feature lets you turn images into 3D objects and use them in our Real-time tool. free for everyone.

Krea

665,531 views • 1 year ago

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 views • 2 months ago

This is MeshPad. AI that can turn sketches into interactive 3D meshes in seconds. 🤯
2:07

This is MeshPad. AI that can turn sketches into interactive 3D meshes in seconds. 🤯

Min Choi

101,223 views • 1 year ago

You can now use AI to make an interactive 3D world from text prompts 🤯 Watch me use KREA AI's new Scene feature - I created the underground environment, and then prompted to drop in 3D meshes for objects. You can move, resize, or rotate the objects as you please!
0:25

You can now use AI to make an interactive 3D world from text prompts 🤯 Watch me use KREA AI's new Scene feature - I created the underground environment, and then prompted to drop in 3D meshes for objects. You can move, resize, or rotate the objects as you please!

Justine Moore

30,851 views • 1 year ago

Whoa, this is Temporal Gaussian Hierarchy (TGH). This AI can real-time render long volumetric videos in 1080p at 450 fps on a single RTX 4090 GPU. And 18,000 frames (around 10 minutes) long 🤯 7 wild demos: 1. Real-time demos on MobileStage dataset
0:52

Whoa, this is Temporal Gaussian Hierarchy (TGH). This AI can real-time render long volumetric videos in 1080p at 450 fps on a single RTX 4090 GPU. And 18,000 frames (around 10 minutes) long 🤯 7 wild demos: 1. Real-time demos on MobileStage dataset

Min Choi

464,076 views • 1 year ago

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 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:
1:04

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 3D outputs Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds. 🔹 Unified world model system One model family for world generation and reconstruction across synthetic and real-world scenes. 🔹 Interactive character mode Explore generated 3D worlds in real time with physics-aware movement and collision support. ✨ Apply for access: 🔗 GitHub: 🤗 Hugging Face: 📄 Technical Report:

Tencent Hy

370,317 views • 2 months ago

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model
0:22

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

el.cine

142,328 views • 7 months ago

🤖The "Physical Turing Test": Can robots clean rooms & prepare dinners indistinguishably from humans? @Drjimfan explains how @Nvidia overcomes robotics' data bottleneck by simulating thousands of environments with varied physics at AI Ascent.
3:00

🤖The "Physical Turing Test": Can robots clean rooms & prepare dinners indistinguishably from humans? @Drjimfan explains how @Nvidia overcomes robotics' data bottleneck by simulating thousands of environments with varied physics at AI Ascent.

Sequoia Capital

16,911 views • 1 year ago

Built a new tool to turn videos into ascii art in a low fps mode it's actually wild how just symbols can make art this beautiful
0:46

Built a new tool to turn videos into ascii art in a low fps mode it's actually wild how just symbols can make art this beautiful

Ann Nguyen

12,294 views • 27 days ago