Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing a creator—first platform for interactive AI films and games. While world models like Genie 3 showed us real-time generated worlds from prompts, Yoroll takes it further: native video-native interaction designed for storytellers and game makers — turning passive generative video into playable, branching narratives. Turn worlds, characters, and... show more

Yoroll

2,027 subscribers

123,787 views • 9 months ago •via X (Twitter)

Science & Technology Gaming

Anya Rossi• Live Now

Private livecam show

45 Comments

Atal9 months ago

This is like AI is enabling an entirely new media format.

Yoroll9 months ago

Exactly—that’s how we see it too. Not just generative video, but a new medium where stories are played, not just watched.

EyeingAI9 months ago

This makes sense. Interactive video has a lot of unexplored space.

Victoria Blake2 months ago

Amazing vision for the future of storytelling and gaming! 🚀 Giving creators the power to build interactive AI-driven worlds opens endless possibilities for creativity. Would love to explore collaboration opportunities and support this innovative journey. 🤝

neuralamp9 months ago

Since your tool is so great, you should consider building a ton of tier-1 PC Games and getting rich quickly.🙃

Yoroll9 months ago

Haha 😄 appreciate that. We’re more excited about enabling creators to build playable stories at scale.

Aaliya9 months ago

This is a really cool shift from just watching to actually playing.

Yoroll9 months ago

Exactly. Turning passive video into something you can act on is the core idea behind Yoroll.

旺旺大李包9 months ago

Love the idea of turning video into something playable！Would love to try this—are beta invites available?

魏超7 months ago

Hi @YorollAI, I'm a newly laid-off single dad. Hoping to use Linear Game to build games and support my child. Grateful for a beta invite! 🙏

Arthur.eth7 months ago

来啦来啦！

Meer | AI Tools & News9 months ago

Excited to get its access.

Yoroll9 months ago

Appreciate the excitement 🙌 We’ll be sharing more soon.

Sanchit9 months ago

Excited to see this in action.

Peter Cruckshank9 months ago

I mean just, wow 🤩 what an incredible idea!! And the fact you have it working is just nuts 🤯 Congrats I want to play with this *so freaking bad!*

Yoroll9 months ago

Love the energy 🤩 We’re building toward making this playable for creators and audiences alike — more updates soon.

Usman9 months ago

Very exciting—turning generative video into truly playable, branching stories feels like the next evolution. Well done! "

Yoroll9 months ago

Thanks！！When stories are designed to branch and be played, entirely new creative possibilities open up.

ZOYA ✪9 months ago

I think this is the beginning of interactive-first storytelling.

Yoroll9 months ago

Love that framing. Interactive-first is exactly the shift we’re building for—designed native to video, not adapted from games.

jiang dongqin6 months ago

I need the blogger's software invitation code.

Morgan9 months ago

As a YouTube first creator, this would be amazing to incorporate! My vision can actually become reality.

Yoroll9 months ago

This is what it’s all about. Giving creators a native way to turn video into something playable opens up entirely new creative possibilities.

Morgan9 months ago

Are you guys doing any creator partnerships? If so, I’m interested! Would love to talk story with you 🫶🏻

Yoroll9 months ago

Appreciate the interest 🫶 We’ll be opening up creator collaborations in the future and will be excited to connect then！

CatBunaga9 months ago

damn, this looks sick. the choice integration looks way smoother than what i've seen elsewhere. hyped for this

Yoroll9 months ago

Thanks! A big focus for us is making choices feel native to video—not game UI layered on top. Glad that came through.

xiaoai669 months ago

Cool～

Yoroll9 months ago

Thanks! More updates coming soon 🙌

Farhan9 months ago

genie 3 showed the tech was possible; yoroll is making it usable. productizing the research is where the value gets unlocked.

Yoroll9 months ago

Totally agree. The leap from “possible” to “playable” is where new formats are born.

AIBN9 months ago

Really Cool

也毛8 months ago

啥时候公测啊

Yoroll8 months ago

Our games will be available very soon!

也毛8 months ago

Could you please send me an invitation code? I'd really like to participate in the closed beta test.

Yoroll8 months ago

Thanks for your interest! Please join our waitlist and we'll notify you as soon as the next round opens!

Snail9 months ago

It's really great

Bisma AI9 months ago

Seamless branching video games from text? This is huge. Just signed up

Yoroll9 months ago

Yep. Appreciate you signing up 🙌 Excited to share more soon！

SongwriterJT9 months ago

🔥🔥🔥

fengtong xu8 months ago

你好，已申请邀请码，辛苦尽快反馈呢

Yoroll8 months ago

Thanks for waiting! We're seeing a lot of excitement and are sending out invite codes in batches to keep things running smoothly!

Feety W6 months ago

怎么获得邀请码！

Nayeem Sheikh9 months ago

This feels like the future of AI-native storytelling.

Yoroll9 months ago

We feel the same. AI-native storytelling opens up formats that simply weren’t possible before.

Related Videos

Introducing Yoroll Game Editor. Upload your videos. Connect scenes with branches and transitions. Add gameplay components like tap, swipe, shoot, puzzle, voice, and balance. Then publish it as a playable interactive episode. No engine. No code. 🎮 Turn any video into a playable game.

Introducing Yoroll Game Editor. Upload your videos. Connect scenes with branches and transitions. Add gameplay components like tap, swipe, shoot, puzzle, voice, and balance. Then publish it as a playable interactive episode. No engine. No code. 🎮 Turn any video into a playable game.

Yoroll

20,583 views • 4 months ago

🚨 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.

🚨 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 views • 9 months ago

“A world builder, for everyone.” 🌐 We sat down with the Google DeepMind team behind Project Genie for a rapid-fire Q&A about turning prompts into interactive, playable worlds. Here’s Logan Kilpatrick and the research scientists behind the magic ↓

“A world builder, for everyone.” 🌐 We sat down with the Google DeepMind team behind Project Genie for a rapid-fire Q&A about turning prompts into interactive, playable worlds. Here’s Logan Kilpatrick and the research scientists behind the magic ↓

Google

115,653 views • 9 months ago

I tried @ReelQuestAI recently, and it honestly feels like turning imagination directly into a playable game. Create your own playable world here: You describe the world, characters, gameplay, story, enemies, quests and even the vibe, AI builds a playable experience from it without needing to code. What normally takes weeks of planning, designing, and prototyping can now happen in minutes. It’s especially useful for creators who want to test ideas fast, experiment with different concepts, or bring cinematic worlds to life without a full dev team. Feels less like a game tool and more like an AI-powered game studio for creators.

I tried @ReelQuestAI recently, and it honestly feels like turning imagination directly into a playable game. Create your own playable world here: You describe the world, characters, gameplay, story, enemies, quests and even the vibe, AI builds a playable experience from it without needing to code. What normally takes weeks of planning, designing, and prototyping can now happen in minutes. It’s especially useful for creators who want to test ideas fast, experiment with different concepts, or bring cinematic worlds to life without a full dev team. Feels less like a game tool and more like an AI-powered game studio for creators.

Sharon Riley

32,307 views • 5 months ago

Introducing fal Worlds. A new way to create and interact with AI-generated worlds in real time. Build characters, explore environments, direct scenes, and watch worlds respond to your actions as they unfold. Get hands-on with the latest frontier world models, including LingBot World, H3 Max Director and more.

Introducing fal Worlds. A new way to create and interact with AI-generated worlds in real time. Build characters, explore environments, direct scenes, and watch worlds respond to your actions as they unfold. Get hands-on with the latest frontier world models, including LingBot World, H3 Max Director and more.

fal

40,019 views • 29 days ago

Most AI video tools generate clips. This one generates worlds. Alibaba Group and HappyOyster are taking it a step further, they generate worlds. Create interactive, explorable experiences where viewers can move through scenes, choose directions, and uncover stories in real time. The line between video games and AI video is starting to disappear. 🧵👇

Most AI video tools generate clips. This one generates worlds. Alibaba Group and HappyOyster are taking it a step further, they generate worlds. Create interactive, explorable experiences where viewers can move through scenes, choose directions, and uncover stories in real time. The line between video games and AI video is starting to disappear. 🧵👇

Parul Gautam

81,553 views • 4 months 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:

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

373,275 views • 7 months ago

In our research lab, we are building “real-time dreaming” - the ability to generate fully playable video worlds prompted from any text or image. Our real-time, action conditioned world model (currently running internally at 16fps at 832x480p) is trained on a combination of data, including proprietary Roblox 3D avatar/world interaction data. World models are different from multiplayer engines in that they store state and memory in video latents. Roblox is multiplayer, and we are actively researching optimal ways to simultaneously store state for thousands of players, and keep them in sync with their environment. Our world model leverages database technology which stores all user interactions on Roblox in a vector format that can be used to re-render video and interaction from any camera angle. We see several immediate uses for our Roblox world model. We will use it side-by-side text, image and video prompts as a way to launch auto-generation of immersive worlds. In Roblox Studio, a creator could walk around and use prompts to “paint” a world and then convert it into a 3D representation or direct to Roblox native as a way for many people to play simultaneously. All of this comes alive as we explore the notion of a “Dream Theater” - where one user is dreaming, while others watch and prompt them. 2/4

Roblox

4,419,334 views • 9 months ago

Turn Your Favorite Fantasy Movies into Playable Worlds! What if you could step inside your favorite film? HappyOyster just turned the world of All wishes come true into a fully playable game demo! 🎬Shared by our Discord Creator Unlock your dream world—comment your favorite movie and let’s build it!

Turn Your Favorite Fantasy Movies into Playable Worlds! What if you could step inside your favorite film? HappyOyster just turned the world of All wishes come true into a fully playable game demo! 🎬Shared by our Discord Creator Unlock your dream world—comment your favorite movie and let’s build it!

HappyOyster

1,433,128 views • 3 months ago

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):

Etched

24,727,616 views • 2 years ago

🚨BREAKING: This new AI just turned a text prompt into a fully playable 3D game with NPCs, physics, multiplayer, and persistent state. Not a video. Not a demo. An actual playable world. Backed by NVIDIA, YouTube's founder, and $28M in funding. Here's everything you need to know:

🚨BREAKING: This new AI just turned a text prompt into a fully playable 3D game with NPCs, physics, multiplayer, and persistent state. Not a video. Not a demo. An actual playable world. Backed by NVIDIA, YouTube's founder, and $28M in funding. Here's everything you need to know:

Hasan Toor

91,243 views • 8 months ago

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

90,721 views • 1 month ago

Restyling games is much harder than generating a video. Games can’t unintentionally “reset” at every frame: • Your character should stay the same when the camera moves • Damage, lighting, and objects must persist • A room should look the same when you look away and look back And it all has to run in real-time. Reverie v0.1.0 is our first stab at a real-time generative model for playable worlds. Below is a comparison with ours (left) with MirageLSD v2 (right). It’s early and far from perfect but watch what stays consistent as the video continues. 🧵 Prompts below (GPT-5.2).

Restyling games is much harder than generating a video. Games can’t unintentionally “reset” at every frame: • Your character should stay the same when the camera moves • Damage, lighting, and objects must persist • A room should look the same when you look away and look back And it all has to run in real-time. Reverie v0.1.0 is our first stab at a real-time generative model for playable worlds. Below is a comparison with ours (left) with MirageLSD v2 (right). It’s early and far from perfect but watch what stays consistent as the video continues. 🧵 Prompts below (GPT-5.2).

Sharon Lee

30,737 views • 11 months ago

Claude Fable 5.2 by Anthropic in action across 17 generations on Arena, from detailed 3D worlds and playable games, to website UI, data visualizations, and interactive code-generated animations.

Claude Fable 5.2 by Anthropic in action across 17 generations on Arena, from detailed 3D worlds and playable games, to website UI, data visualizations, and interactive code-generated animations.

Arena.ai

23,911 views • 4 days ago

🚨 Passive video is dead. Welcome to real-time AI video. With Synthesia 3.0, your videos don’t just play — they engage, respond, and act. Add your content → and create fully interactive AI-powered experiences in minutes. ✅ Video Agents ✅ Realistic Avatars ✅ Express Voice All generated and ready to interact from your first prompt. This isn’t just “better video.” It’s video that thinks, reacts, and communicates like a real human. Why Synthesia 3.0 is a game-changer: ⚡ Turn training, onboarding, and customer support into conversations. ⚡ Lifelike avatars with gestures, expressions, and natural movement. ⚡ Build custom avatars anywhere — office, beach, or performing actions. ⚡ Translate videos into 120+ languages with perfect lip sync. Whether you’re a creator, business leader, or educator — Synthesia 3.0 makes video intelligent, interactive, and actionable. ✨ Experience the future of video and engagement. ⚡ Try it today: #AI #Synthesia #VideoInnovation #FutureOfWork #MadeWithSynthesia

🚨 Passive video is dead. Welcome to real-time AI video. With Synthesia 3.0, your videos don’t just play — they engage, respond, and act. Add your content → and create fully interactive AI-powered experiences in minutes. ✅ Video Agents ✅ Realistic Avatars ✅ Express Voice All generated and ready to interact from your first prompt. This isn’t just “better video.” It’s video that thinks, reacts, and communicates like a real human. Why Synthesia 3.0 is a game-changer: ⚡ Turn training, onboarding, and customer support into conversations. ⚡ Lifelike avatars with gestures, expressions, and natural movement. ⚡ Build custom avatars anywhere — office, beach, or performing actions. ⚡ Translate videos into 120+ languages with perfect lip sync. Whether you’re a creator, business leader, or educator — Synthesia 3.0 makes video intelligent, interactive, and actionable. ✨ Experience the future of video and engagement. ⚡ Try it today: #AI #Synthesia #VideoInnovation #FutureOfWork #MadeWithSynthesia

Laxmi Rani Bodana

14,656 views • 1 year ago

Social media promised self-expression. Why are we becoming the same? Our creator made that question playable in Template: Self as Product on Yoroll. Images and video came from natural-language prompts. Yoroll’s built-in puzzle components made it playable. Would you take the selfie — or refuse?

Social media promised self-expression. Why are we becoming the same? Our creator made that question playable in Template: Self as Product on Yoroll. Images and video came from natural-language prompts. Yoroll’s built-in puzzle components made it playable. Would you take the selfie — or refuse?

Yoroll

64,338 views • 3 months ago

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time

Jack Parker-Holder

2,091,976 views • 1 year ago

Just a month later and the first AI model that can generate live and interactive playable dynamic worlds is here It's called GameNGen and is trained on the classic game DOOM

Just a month later and the first AI model that can generate live and interactive playable dynamic worlds is here It's called GameNGen and is trained on the classic game DOOM

@levelsio

519,246 views • 2 years ago

Roblox was just the beginning. Game creation is going from: slow, technical, expensive → to instant, AI-native, massively multiplayer. Today, we took a big step. Arcade AI now generates: not just worlds, but gameplay + game logic. Fully playable games. In minutes.

Roblox was just the beginning. Game creation is going from: slow, technical, expensive → to instant, AI-native, massively multiplayer. Today, we took a big step. Arcade AI now generates: not just worlds, but gameplay + game logic. Fully playable games. In minutes.

Remi

52,677 views • 6 months ago

Google's Genie 3 was just announced. This is a world model capable of generating fully interactive 3D worlds. This has major implications for video games and giving agents infinite self-play environments.

Google's Genie 3 was just announced. This is a world model capable of generating fully interactive 3D worlds. This has major implications for video games and giving agents infinite self-play environments.

Matthew Berman

76,362 views • 1 year ago