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。

wow.. AI now lets you walk inside a 3D world while it's being generated tested PixVerse R2 today. moved around with WASD, then started selecting an option to have a giant dragon block my path. it appeared in real time as i kept moving this is the part that... show more

el.cine

145,860 subscribers

11,875 次观看 • 5 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 条评论

el.cine 的头像

el.cine5 天前

quick context: R2 is a real-time world model. it keeps generating the world while you move with WASD, and you can type prompts to change characters, objects or the environment on the fly #PixVerse check it out here:

The Becket List 的头像

The Becket List5 天前

@PixVerse Open World Gaming is going to be amazing soon.

Erika S 的头像

Erika S5 天前

@PixVerse not knowledgable at all about the rendering side, but I'm 90% sure the drift comes from no persistent world state between frames. is that the actual bottleneck?

𝑨𝒇𝒓𝒊𝒏 的头像

𝑨𝒇𝒓𝒊𝒏5 天前

@PixVerse walking inside a 3d world during generation must be a unique immersion

NAMAN RAJ 的头像

NAMAN RAJ5 天前

@PixVerse Mind. Blown. 🤯 I need to know, did the dragon's scales get generated along with the terrain? 🐉

Harshil Tomar 的头像

Harshil Tomar4 天前

@PixVerse the prompt-as-game-control part is wild. that's a different interaction model entirely.

相关视频

🚨 AI video just got a “WALK INTO THE WORLD” Button. Most AI video works like this: prompt → generate → watch. PixVerse World Model changes the interaction. With WASD, you can: → Move through the generated world → Control the camera as you explore → Use prompts to influence the environment, characters, and actions → Keep interacting instead of generating a completely new clip every time The interesting part is how movement + prompting work together. You’re not just telling AI what video to generate. You’re inside the generated world, influencing what happens next. That makes PixVerse World Model feel less like traditional AI video and more like an interactive, playable environment. Try it here 👇 #PixVerseWorldModel

🚨 AI video just got a “WALK INTO THE WORLD” Button. Most AI video works like this: prompt → generate → watch. PixVerse World Model changes the interaction. With WASD, you can: → Move through the generated world → Control the camera as you explore → Use prompts to influence the environment, characters, and actions → Keep interacting instead of generating a completely new clip every time The interesting part is how movement + prompting work together. You’re not just telling AI what video to generate. You’re inside the generated world, influencing what happens next. That makes PixVerse World Model feel less like traditional AI video and more like an interactive, playable environment. Try it here 👇 #PixVerseWorldModel

Anthara Fairooz

45,107 次观看 • 7 天前

🚨 AI Video are DEAD ! Because The FUTURE is all about Interactive AI Worlds! PixVerse R2 isn't just generating an AI video.. It generates a WORLD that responds to what you're doing I can literally CONTROL it with WASD keys. And this isn't a pre-rendered game. Watch this 👇 #PixVerseWorldModel PixVerse

🚨 AI Video are DEAD ! Because The FUTURE is all about Interactive AI Worlds! PixVerse R2 isn't just generating an AI video.. It generates a WORLD that responds to what you're doing I can literally CONTROL it with WASD keys. And this isn't a pre-rendered game. Watch this 👇 #PixVerseWorldModel PixVerse

SARAH

95,362 次观看 • 6 天前

What happens when an AI world reacts to you in real time? That’s what makes PixVerse R2 interesting. You can move through generated worlds with WASD. You can explore freely. You can type what should happen next. And the world responds while you’re still inside it. It starts to feel less like watching AI video and more like interacting with a world that keeps evolving around your input. Still early, but I can already see the potential for game ideation, rapid prototyping, interactive stories, and new kinds of playable experiences. Try it: PixVerse #PixVerseWorldModel

What happens when an AI world reacts to you in real time? That’s what makes PixVerse R2 interesting. You can move through generated worlds with WASD. You can explore freely. You can type what should happen next. And the world responds while you’re still inside it. It starts to feel less like watching AI video and more like interacting with a world that keeps evolving around your input. Still early, but I can already see the potential for game ideation, rapid prototyping, interactive stories, and new kinds of playable experiences. Try it: PixVerse #PixVerseWorldModel

Alamin

90,609 次观看 • 4 天前

I just walked into an AI-generated world… and started controlling what happened next. 🤯 I opened PixVerse R2, picked a world from the Gallery, and started exploring with WASD. Here’s what I tried: → Moved around the world with WASD → Controlled the camera as I explored → Used prompts to change what was happening → Watched the world respond while I was still inside it And that’s what surprised me. I wasn’t just watching an AI-generated video. I was actually interacting with the world and influencing what happened next. It feels like AI video is moving beyond just creating clips… …and toward creating experiences you can actually step into and play with.

I just walked into an AI-generated world… and started controlling what happened next. 🤯 I opened PixVerse R2, picked a world from the Gallery, and started exploring with WASD. Here’s what I tried: → Moved around the world with WASD → Controlled the camera as I explored → Used prompts to change what was happening → Watched the world respond while I was still inside it And that’s what surprised me. I wasn’t just watching an AI-generated video. I was actually interacting with the world and influencing what happened next. It feels like AI video is moving beyond just creating clips… …and toward creating experiences you can actually step into and play with.

Toha Khan

50,699 次观看 • 5 天前

This familiar game started as a single phrase. A prompt simple enough to begin the process: "Create a Flappy Bird-style game." With CreoPlay AI, that prompt becomes more than just text. It becomes the starting point for building something playable. The system helps turn the idea into game structure, mechanics, and logic, so the result is not just generated, but something you can test, refine, and continue improving. This is the direction we are building toward with CreoPlay AI. Not just generating a game, but creating a workflow where creators can start with an idea, shape the experience, test the result, and keep building from there. Today, it starts with a "Flappy Bird-style" game. Tomorrow, it'll start with YOUR idea. CreoPlay AI. From prompt to playable.

This familiar game started as a single phrase. A prompt simple enough to begin the process: "Create a Flappy Bird-style game." With CreoPlay AI, that prompt becomes more than just text. It becomes the starting point for building something playable. The system helps turn the idea into game structure, mechanics, and logic, so the result is not just generated, but something you can test, refine, and continue improving. This is the direction we are building toward with CreoPlay AI. Not just generating a game, but creating a workflow where creators can start with an idea, shape the experience, test the result, and keep building from there. Today, it starts with a "Flappy Bird-style" game. Tomorrow, it'll start with YOUR idea. CreoPlay AI. From prompt to playable.

Creo Engine

11,562 次观看 • 18 天前

I Created a 520% Trading Strategy With One Prompt I have been testing the just-released “Index” product by Fraction AI. This is basically the “ChatGPT for trading,” where you can: > explain your trading strategy in one prompt > let agents create it for you > backtest it with real market data With one prompt, I was able to create a trading strategy that returned 520% APY with a 93% win rate. The prompt is in the video, but basically, it is long $BTC and $HYPE while shorting $SOL. Impressive how easy it is today to create and backtest incredibly profitable trading strategies. Extra note: the free version is already very powerful. I do NOT have the premium account.

I Created a 520% Trading Strategy With One Prompt I have been testing the just-released “Index” product by Fraction AI. This is basically the “ChatGPT for trading,” where you can: > explain your trading strategy in one prompt > let agents create it for you > backtest it with real market data With one prompt, I was able to create a trading strategy that returned 520% APY with a 93% win rate. The prompt is in the video, but basically, it is long $BTC and $HYPE while shorting $SOL. Impressive how easy it is today to create and backtest incredibly profitable trading strategies. Extra note: the free version is already very powerful. I do NOT have the premium account.

Diego

12,607 次观看 • 5 个月前

Everything starts with something simple. A prompt. But the prompt is only the beginning. CreoPlay AI is built to take an idea further, helping turn a prompt into something you can play, test, and keep refining. Different ideas. Different games. The same starting point. Describe what you want to create, then build from there. This is the direction we are building toward with CreoPlay AI. From prompt to playable!

Everything starts with something simple. A prompt. But the prompt is only the beginning. CreoPlay AI is built to take an idea further, helping turn a prompt into something you can play, test, and keep refining. Different ideas. Different games. The same starting point. Describe what you want to create, then build from there. This is the direction we are building toward with CreoPlay AI. From prompt to playable!

Creo Engine

11,112 次观看 • 20 天前

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

Santiago

185,640 次观看 • 2 年前

Every "AI world model" demo I've seen is the same: watch a video, take their word for it. PixVerse R2 said forget that.... just fly the dragon yourself. So I did. WASD to move, mouse to look, and mid-flight I typed "Breathe Fire"... the whole world reacted right there, live, no render, no waiting. Most models show you a demo. R2 lets you get in and judge it yourself. Go try it firsthand → PixVerse #PixVerseWorldModel

Every "AI world model" demo I've seen is the same: watch a video, take their word for it. PixVerse R2 said forget that.... just fly the dragon yourself. So I did. WASD to move, mouse to look, and mid-flight I typed "Breathe Fire"... the whole world reacted right there, live, no render, no waiting. Most models show you a demo. R2 lets you get in and judge it yourself. Go try it firsthand → PixVerse #PixVerseWorldModel

Nawi

133,924 次观看 • 5 天前

Deepseek 4.1 Flash is an awesome model if we can run this at home were lucky yet again. This is the first fun little game I've made with AI in a while. It's not perfect but it's fun! Recommend turning sound on. Playable link below.

Deepseek 4.1 Flash is an awesome model if we can run this at home were lucky yet again. This is the first fun little game I've made with AI in a while. It's not perfect but it's fun! Recommend turning sound on. Playable link below.

Loktar 🇺🇸

27,892 次观看 • 20 天前

✨ I'm getting very very close to the original vision I had for Photo AI when I started it 3 years ago which was essentially: [ 📸 Photography Simulator 2025 ] I wanted to 100% be able to simulate being a real photographer, and what that means is actually being able to move the camera around a subject I think I'm getting really close now by integrating World Labs, it lets me put real people into a 3d world that you can then move around in with WASD and your mouse Then my idea is you have a [ 📸 Take photo ] button there to turn that shot into a new photo with AI I'm not there yet but I'm getting close I think, one thing is that World Labs still suck at people and faces, although if I just ask the AI to take only the angle of the pic maybe that's not a problem so much I first used World Labs on Interior AI where it lets people move around in their re-styled interior design, I thought it'd be a gimmick maybe and few would use it, but now it's one of the most used features Anyway very exciting!!!! 😊

✨ I'm getting very very close to the original vision I had for Photo AI when I started it 3 years ago which was essentially: [ 📸 Photography Simulator 2025 ] I wanted to 100% be able to simulate being a real photographer, and what that means is actually being able to move the camera around a subject I think I'm getting really close now by integrating World Labs, it lets me put real people into a 3d world that you can then move around in with WASD and your mouse Then my idea is you have a [ 📸 Take photo ] button there to turn that shot into a new photo with AI I'm not there yet but I'm getting close I think, one thing is that World Labs still suck at people and faces, although if I just ask the AI to take only the angle of the pic maybe that's not a problem so much I first used World Labs on Interior AI where it lets people move around in their re-styled interior design, I thought it'd be a gimmick maybe and few would use it, but now it's one of the most used features Anyway very exciting!!!! 😊

@levelsio

423,523 次观看 • 9 个月前

Wow. Just made my first AI video game with Google’s Genie 3 The prompt: “French woman has to climb through a word that defies logic, flying objects everywhere” Is it the end of the gaming industry?

Wow. Just made my first AI video game with Google’s Genie 3 The prompt: “French woman has to climb through a word that defies logic, flying objects everywhere” Is it the end of the gaming industry?

Slazac 🇪🇺🇺🇦🇹🇼🌐

3,251,345 次观看 • 8 个月前

I'm a man of my word, since you guys really needed it spelled out this way: Is this a 3D model? called us out so now we have to add the following disclaimer to this post: This is not a 3D model or gameplay footage in any regard. It is merely a dumb AI generated video clip. This post was sponsored by SocialKettle. Would you play a game like this?

I'm a man of my word, since you guys really needed it spelled out this way: Is this a 3D model? called us out so now we have to add the following disclaimer to this post: This is not a 3D model or gameplay footage in any regard. It is merely a dumb AI generated video clip. This post was sponsored by SocialKettle. Would you play a game like this?

Morph

68,674 次观看 • 9 个月前

GPT-6 makes me scared as a 3D artist, cuz it's freaking insane. I mean, I'm testing this first hand everyday, but this time it is massive leap. look, 4 month ago I was testing GPT & Claude in Blender and they were not able to position simple objects in simple scene.. And look now... Whole car assembled from primitives in ONE prompt and animate it (hate to say that, but it was indeed one prompt). Yes, yes, it is not perfect and maybe not really usable still at this stage. BUT WHAT A JUMP.

GPT-6 makes me scared as a 3D artist, cuz it's freaking insane. I mean, I'm testing this first hand everyday, but this time it is massive leap. look, 4 month ago I was testing GPT & Claude in Blender and they were not able to position simple objects in simple scene.. And look now... Whole car assembled from primitives in ONE prompt and animate it (hate to say that, but it was indeed one prompt). Yes, yes, it is not perfect and maybe not really usable still at this stage. BUT WHAT A JUMP.

Stefan 3D AI

188,774 次观看 • 24 天前

The AI gaming question I am most interested in is not whether AI can make better assets. It is whether video models can eventually become part of interactive worlds. PixVerse is exploring that question through PixVerse Game, combining real-time generative video, AI Agents, game mechanics, and user-defined worlds in an early technical experiment. My starting point for that question is here: I do not think AI gaming is solved, and this is not a finished platform. But if video models become more controllable and responsive, what role could they play inside future games? If the question interests you enough to test the idea yourself, share your take below. A few invitation codes are available, with priority going to the first thoughtful replies.

The AI gaming question I am most interested in is not whether AI can make better assets. It is whether video models can eventually become part of interactive worlds. PixVerse is exploring that question through PixVerse Game, combining real-time generative video, AI Agents, game mechanics, and user-defined worlds in an early technical experiment. My starting point for that question is here: I do not think AI gaming is solved, and this is not a finished platform. But if video models become more controllable and responsive, what role could they play inside future games? If the question interests you enough to test the idea yourself, share your take below. A few invitation codes are available, with priority going to the first thoughtful replies.

Deborah

77,604 次观看 • 2 个月前

Real-time controllable video is here! Watch me demo the new Odyssey model ⬇️ You create a scene and then prompt actions or changes via text prompt or suggestions that pop-up. It's not perfect (you'll see some artifacts) - but it's INSANELY fast and very fun.

Real-time controllable video is here! Watch me demo the new Odyssey model ⬇️ You create a scene and then prompt actions or changes via text prompt or suggestions that pop-up. It's not perfect (you'll see some artifacts) - but it's INSANELY fast and very fun.

Justine Moore

18,246 次观看 • 11 个月前

✨ It's not even 2026 yet, but you can start using AI world models today! This is World Labs running inside my app 🏡 Interior AI letting you redesign your home with AI and then walk through it! It's really cool and of course not perfect especially since for now it's based on just one image, but multi-image will allow for more precise understanding of the room As always this is just the first version, and it'll get better from here World Labs is founded by Fei-Fei Li, a Computer Science professor from Stanford University, and other people like Justin Johnson, Christoph Lassner, and Ben Mildenhall "each a world-renowned technologist in computer vision and graphics" The tech essentially comes down to img2splat, search what a guassian splat is if you don't know It's in beta and wait list, but I'm trying to get this live for everyone as soon as possible as it seems like such an essential feature for interior design P.S. I also tried to worldify people photos (for Photo AI) but World Labs for safety right now seems to block it off and make it a black square, maybe in the future

✨ It's not even 2026 yet, but you can start using AI world models today! This is World Labs running inside my app 🏡 Interior AI letting you redesign your home with AI and then walk through it! It's really cool and of course not perfect especially since for now it's based on just one image, but multi-image will allow for more precise understanding of the room As always this is just the first version, and it'll get better from here World Labs is founded by Fei-Fei Li, a Computer Science professor from Stanford University, and other people like Justin Johnson, Christoph Lassner, and Ben Mildenhall "each a world-renowned technologist in computer vision and graphics" The tech essentially comes down to img2splat, search what a guassian splat is if you don't know It's in beta and wait list, but I'm trying to get this live for everyone as soon as possible as it seems like such an essential feature for interior design P.S. I also tried to worldify people photos (for Photo AI) but World Labs for safety right now seems to block it off and make it a black square, maybe in the future

@levelsio

430,981 次观看 • 1 年前

This is from today's #WCWS game. This was ruled a base hit when it happened (you can see the 'H' pop up), but was changed to a missed catch error by the first baseman at the bottom of the fourth. This is an impossible catch for the first baseman with a ball thrown from that angle, that hard. This throw has to be to the glove, and while it's not a wild throw, it's low enough that the first baseman cannot get her glove around it in time. This is where replay gets you in trouble. The slo-mo replay makes it look like it's a catchable ball, but it isn't. In real time, at live speed, this isn't an error. This isn't a missed catch or a drop. I was loving the call of a single, especially because it was the first hit, and then, when it was changed, it felt like it was to protect a no-hitter. Everything about this screams "above ordinary effort" ... I would have left this as a single.

This is from today's #WCWS game. This was ruled a base hit when it happened (you can see the 'H' pop up), but was changed to a missed catch error by the first baseman at the bottom of the fourth. This is an impossible catch for the first baseman with a ball thrown from that angle, that hard. This throw has to be to the glove, and while it's not a wild throw, it's low enough that the first baseman cannot get her glove around it in time. This is where replay gets you in trouble. The slo-mo replay makes it look like it's a catchable ball, but it isn't. In real time, at live speed, this isn't an error. This isn't a missed catch or a drop. I was loving the call of a single, especially because it was the first hit, and then, when it was changed, it felt like it was to protect a no-hitter. Everything about this screams "above ordinary effort" ... I would have left this as a single.

MLB Scoring Changes

30,825 次观看 • 4 个月前

Today I realized something absolutely with BitRobot Network You dont need to own a robot… to actually control one I was just sitting at my laptop and somehow I was moving a real robotic arm in real time At first I thought it would feel like a video game It didnt Theres a completely different feeling when you know this is happening in the real world not just on a screen Every movement matters. Every action generates data And then it hit me… This is how AI is learning to interact with the real world Not from code alone but from people like us Platforms like BitRobot are opening this to everyone No setup No cost No experience Just curiosity and the internet Someone sitting at home can now help train the next generation of robotics. The future isnt coming its happening right now. If you could control a robot right now what would you try first? 🤖👇

Today I realized something absolutely with BitRobot Network You dont need to own a robot… to actually control one I was just sitting at my laptop and somehow I was moving a real robotic arm in real time At first I thought it would feel like a video game It didnt Theres a completely different feeling when you know this is happening in the real world not just on a screen Every movement matters. Every action generates data And then it hit me… This is how AI is learning to interact with the real world Not from code alone but from people like us Platforms like BitRobot are opening this to everyone No setup No cost No experience Just curiosity and the internet Someone sitting at home can now help train the next generation of robotics. The future isnt coming its happening right now. If you could control a robot right now what would you try first? 🤖👇

RAJU

40,141 次观看 • 5 个月前