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 JING: From actions, reference images, and observation history to interactive egocentric interactive experience. JING lets you navigate with camera controls, interact with objects, and talk with characters—while generating video and audio together. 🎥 Take control and see what happens next. Explore more ⬇️ 🤗 HF: 🦊 GitHub: 📖 Blog:

XGEN Labs

1,365 subscribers

13,998 views • 23 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 Comments

Art Diffuser23 days ago

do you have API? I could integrate you into my app. check my posts to see what's it about. if you offer subscriptions please support OAuth 👌

Vantix AI Agency22 days ago

Interactive worlds become much more compelling when actions truly shape what happens next

varick lim21 days ago

this is perfect for story driven games! i've been dreaming of a world model where i can interact with the world and not just navigate it

Vera Ai | Tools & Updates21 days ago

Making complex AI workflows accessible without needing a full-time specialist is a strong pitch

Elara AI22 days ago

This feels genuinely immersive mind-blowing work folks congrats

Whale Elite22 days ago

Kindly check inbox 📥

Learn to use AI22 days ago

crazy

ikan laut22 days ago

this is very interesting

varick lim21 days ago

when @reactorworld ?

ZenithAi20 days ago

Egocentric interactive video audio generation is wild future tech

SOLANA EMBASSY22 days ago

Let’s build something big together. DM open. 🔥📩

Sol Empress 👑22 days ago

Great work here! 🚀 Open to collaboration? 🤝 @XGEN_labs

Related Videos

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-world engine. The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer. Conditioned on actions and observation history, JING enables agent navigate, manipulate, and communicate from a first-person perspective in the world. Watch our demo video to see it in action! On the official WBench leaderboard as of September 17, 2026, XGEN-JING ranked #1 on the Full split, and #2 on the Navi split. 🎉 DAO maintains shared world state and rules, computes the consequences of actions, and provides JING with only what the current observer can perceive. It also supports autonomous agent decision-making, enabling agents to act independently within an evolving shared world. Together, DAO and JING move beyond generating the next frame toward simulating the world behind it. This marks a small step towards OASIS: not just a world that responds to you, but a world—and a society—that evolves with and without you. 💪 Explore XGEN Labs～: 🔗 Website: 🤗 HF: 🦊 GitHub:

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-world engine. The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer. Conditioned on actions and observation history, JING enables agent navigate, manipulate, and communicate from a first-person perspective in the world. Watch our demo video to see it in action! On the official WBench leaderboard as of September 17, 2026, XGEN-JING ranked #1 on the Full split, and #2 on the Navi split. 🎉 DAO maintains shared world state and rules, computes the consequences of actions, and provides JING with only what the current observer can perceive. It also supports autonomous agent decision-making, enabling agents to act independently within an evolving shared world. Together, DAO and JING move beyond generating the next frame toward simulating the world behind it. This marks a small step towards OASIS: not just a world that responds to you, but a world—and a society—that evolves with and without you. 💪 Explore XGEN Labs～: 🔗 Website: 🤗 HF: 🦊 GitHub:

XGEN Labs

1,503,888 views • 26 days ago

Introducing Agents 3.0: Four new features expand what agents can do and how you can interact with them. - Full Terminal Use to use REPLs, debuggers, and more - /plan for spec-driven development - Interactive Code Review - New Slack, Linear, and GitHub Actions integrations

Introducing Agents 3.0: Four new features expand what agents can do and how you can interact with them. - Full Terminal Use to use REPLs, debuggers, and more - /plan for spec-driven development - Interactive Code Review - New Slack, Linear, and GitHub Actions integrations

Warp

149,437 views • 10 months ago

We’ve just launched multi-reference in LTX Studio. You can now seamlessly integrate and composite objects, scenes, and characters from different images into a single frame with more control and precision. Now live.

We’ve just launched multi-reference in LTX Studio. You can now seamlessly integrate and composite objects, scenes, and characters from different images into a single frame with more control and precision. Now live.

LTX.io

1,521,337 views • 1 year ago

🚀 Introducing H3 Reference Turbo Realtime, the latest model by MiniMax (official). Stream video with audio and guide generation with up to 9 reference images, giving you more control than ever. Available today on Reactor. Start building now!

🚀 Introducing H3 Reference Turbo Realtime, the latest model by MiniMax (official). Stream video with audio and guide generation with up to 9 reference images, giving you more control than ever. Available today on Reactor. Start building now!

reactor

2,910,113 views • 1 month ago

From 48 World Cup nations to an interactive 3D flower world. Tripo turns each nation into photorealistic 3D flowers, each designed with its own form, color palette, material texture, and cultural reference, and brings them into an interactive experience with GPT-5.5. The full collection is interactive, so every flower can be viewed, rotated, and explored in 3D. Tripo AI turns ideas into 3D experiences you can actually see, share, and explore.

From 48 World Cup nations to an interactive 3D flower world. Tripo turns each nation into photorealistic 3D flowers, each designed with its own form, color palette, material texture, and cultural reference, and brings them into an interactive experience with GPT-5.5. The full collection is interactive, so every flower can be viewed, rotated, and explored in 3D. Tripo AI turns ideas into 3D experiences you can actually see, share, and explore.

Tripo 🔜 gamescom

13,551 views • 3 months ago

One prompt → your next landing page. We hooked up Gemini 3.7 Flash with Nano Banana and Omni in Google Antigravity to build an interactive landing page from scratch, generating the copy, images, and video in a single shot.

One prompt → your next landing page. We hooked up Gemini 3.7 Flash with Nano Banana and Omni in Google Antigravity to build an interactive landing page from scratch, generating the copy, images, and video in a single shot.

Google

421,860 views • 1 month ago

Today, we're introducing Vivix-A1, a real-time interactive multimodal model for AI characters. With A1, characters are no longer limited to talking faces in a fixed frame. You can bring the characters you imagine to life. They can move through scenes, interact with objects, and respond with their whole bodies. Talking to an A1 character feels like talking to someone right there with you. It listens, speaks, and acts at once. With ultra-low latency, you can interrupt or redirect it at any moment, and it adapts immediately. You can shape what happens next through voice, text, images, and other multimodal inputs. A1 powers experiences across companionship, customer service, e-commerce, education, and more. At Vivix, we're building a future where content moves beyond passive viewing into experiences that unfold with you. Meet Vivix-A1 at

Today, we're introducing Vivix-A1, a real-time interactive multimodal model for AI characters. With A1, characters are no longer limited to talking faces in a fixed frame. You can bring the characters you imagine to life. They can move through scenes, interact with objects, and respond with their whole bodies. Talking to an A1 character feels like talking to someone right there with you. It listens, speaks, and acts at once. With ultra-low latency, you can interrupt or redirect it at any moment, and it adapts immediately. You can shape what happens next through voice, text, images, and other multimodal inputs. A1 powers experiences across companionship, customer service, e-commerce, education, and more. At Vivix, we're building a future where content moves beyond passive viewing into experiences that unfold with you. Meet Vivix-A1 at

Vivix.AI

942,765 views • 2 months ago

Introducing Buzzy 3D Director Console, powered by GPT-6 Astra. Let GPT-6 turn your words into fully interactive 3D world, and then to stunning video on Buzzy. >Build complex 3D characters & scenes with simple prompts >Control cameras, characters, lighting, and environments easily >Direct and refine every detail with simple prompts Experience OpenAI's strongest model on Buzzy!

Introducing Buzzy 3D Director Console, powered by GPT-6 Astra. Let GPT-6 turn your words into fully interactive 3D world, and then to stunning video on Buzzy. >Build complex 3D characters & scenes with simple prompts >Control cameras, characters, lighting, and environments easily >Direct and refine every detail with simple prompts Experience OpenAI's strongest model on Buzzy!

Buzzy Now

1,569,755 views • 1 month ago

🚨 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 views • 21 days ago

Patch 11.09 // #VALORANT • Interactive Object Highlighting - World interactions including Switches, Ropes, Ziplines and Ultimate Orbs have been updated to use the standard green highlight color that other interactive objects in the game use. • Interactive Object Prioritization - Aiming can now prioritize highlighted actions when multiple are possible. So now when you’re in a Deadlock GravNet next to a Rope, you’ll have more control over what you’re interacting with first.

Patch 11.09 // #VALORANT • Interactive Object Highlighting - World interactions including Switches, Ropes, Ziplines and Ultimate Orbs have been updated to use the standard green highlight color that other interactive objects in the game use. • Interactive Object Prioritization - Aiming can now prioritize highlighted actions when multiple are possible. So now when you’re in a Deadlock GravNet next to a Rope, you’ll have more control over what you’re interacting with first.

VALORANT Leaks & News

527,714 views • 11 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

90,708 views • 19 days ago

100 Interactive Maps from Open Data: Explore, Fork, and Build Your Own with GeoLibre 100 interactive maps, all built from free public data, and all open live in your browser. In this tutorial I tour the GeoLibre open data gallery, show how to explore and fork any of the maps, and walk through how they were made with GeoLibre, so you can build the same kind of map from your own data. Video tutorial: The maps cover 12 themes: health, natural hazards, climate, oceans and water, nature, transport, cities, energy, space, history and culture, society and economy, and food. - Gallery: - Official Demos collection: - GeoLibre Web: - GitHub: #geospatial #opensource #GeoLibre

100 Interactive Maps from Open Data: Explore, Fork, and Build Your Own with GeoLibre 100 interactive maps, all built from free public data, and all open live in your browser. In this tutorial I tour the GeoLibre open data gallery, show how to explore and fork any of the maps, and walk through how they were made with GeoLibre, so you can build the same kind of map from your own data. Video tutorial: The maps cover 12 themes: health, natural hazards, climate, oceans and water, nature, transport, cities, energy, space, history and culture, society and economy, and food. - Gallery: - Official Demos collection: - GeoLibre Web: - GitHub: #geospatial #opensource #GeoLibre

Qiusheng Wu

10,153 views • 15 days ago

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Jerrod Lew

30,665 views • 1 year ago

We just wrapped Synthesia 3.0! Here’s what we announced: Video Agents: Video you can talk to in real-time. Add a Video Agent at any point in your video - and let them run training roleplays, do knowledge checks, interview candidates and much more. Avatars: Now they move and talk like professional speakers. Create an Avatar from a single prompt or image - with facial expressions, perfect lip sync, and natural hand & body movements. Copilot: Your very own professional video editor. Writes your script in seconds, connects to knowledge bases, and even suggests visual elements. Interactivity 2.0: Get viewers to engage and take action with interactive elements like quizzes, polls, hotspots, and forms. Courses: Design interactive learning experience that combine Avatars, Video Agents, and Interactivity - and measure performance data. I’ll be sharing more about each specific update in the coming days. More about Synthesia 🎥 next chapter here:

Victor Riparbelli

29,006 views • 1 year ago

Introducing Seedance 2.5, our new-generation video creation model! With advancements in long-form storytelling, multimodal reference, and editing, Seedance 2.5 goes beyond longer single-pass video generation, delivering the journey from idea to finished video with greater control. Key highlights include: 1. Users can generate high-quality, 30-second audio-video clips in a single pass, bringing a complete story to life in one take. 2. Users can input up to 30 images, 10 video clips, and 10 audio clips as reference materials in a single pass. 3. Seedance 2.5 offers timestamp-level control for targeted editing of audio and video content, notably improving efficiency and controllability. Visit project homepage learn more：

Introducing Seedance 2.5, our new-generation video creation model! With advancements in long-form storytelling, multimodal reference, and editing, Seedance 2.5 goes beyond longer single-pass video generation, delivering the journey from idea to finished video with greater control. Key highlights include: 1. Users can generate high-quality, 30-second audio-video clips in a single pass, bringing a complete story to life in one take. 2. Users can input up to 30 images, 10 video clips, and 10 audio clips as reference materials in a single pass. 3. Seedance 2.5 offers timestamp-level control for targeted editing of audio and video content, notably improving efficiency and controllability. Visit project homepage learn more：

ByteDance Seed

604,936 views • 2 months ago

I gave Gemini 3.7 Flash a handful of reference images and a rough idea of what I wanted. Ran /grill-me to align on the vision. Hit /goal & /teamwork-preview and let it cook. A couple of iterations later, this is what came out! An interactive kind of experience.. built with Three.js, WebGL, GLSL shaders, and Web Audio engine. Turn up your volume a bit...

I gave Gemini 3.7 Flash a handful of reference images and a rough idea of what I wanted. Ran /grill-me to align on the vision. Hit /goal & /teamwork-preview and let it cook. A couple of iterations later, this is what came out! An interactive kind of experience.. built with Three.js, WebGL, GLSL shaders, and Web Audio engine. Turn up your volume a bit...

Bee

972,594 views • 1 month ago

Vidu S1, the World’s Most Advanced Model for Real-Time AI Interaction Vidu S1 introduces a new era of real-time interactive video. Voice-Driven Character Control: Go beyond voice-driven lip sync with real-time behavior generation. Characters understand, react, and respond naturally. Unlimited Real-Time Generation: Experience seamless real-time video generation with unlimited interaction duration. 540P at 25 FPS, built for live interaction: Generate video in real time at 540P / 25 FPS, with support for up to 42 FPS for even smoother experiences. Create Custom Characters from Images & Voices: Customize both appearance and voice. Bring humans, anime characters, pets, and more to life with personalized AI characters. Use code VIDUS1 to get started for free.

Vidu S1, the World’s Most Advanced Model for Real-Time AI Interaction Vidu S1 introduces a new era of real-time interactive video. Voice-Driven Character Control: Go beyond voice-driven lip sync with real-time behavior generation. Characters understand, react, and respond naturally. Unlimited Real-Time Generation: Experience seamless real-time video generation with unlimited interaction duration. 540P at 25 FPS, built for live interaction: Generate video in real time at 540P / 25 FPS, with support for up to 42 FPS for even smoother experiences. Create Custom Characters from Images & Voices: Customize both appearance and voice. Bring humans, anime characters, pets, and more to life with personalized AI characters. Use code VIDUS1 to get started for free.

Vidu AI

1,537,934 views • 3 months ago

Meet Veo 3.1 👋 With Veo 3.1, you can generate videos with richer audio, better narrative control, and enhanced realism. This new update also comes with a suite of additional features built for creative control. Including the ability to: — Extend your videos to make them longer (with audio) — Set the first and last frame of your video to control your output (with audio) — Upload multiple ingredient images to craft your scene (with audio) — Add or remove objects directly in your video These features are available in Flow by Google, the Gemini API, and Google Cloud Vertex AI. Veo 3.1 is also available in the Google Gemini. We’re so excited to see what you create!

Meet Veo 3.1 👋 With Veo 3.1, you can generate videos with richer audio, better narrative control, and enhanced realism. This new update also comes with a suite of additional features built for creative control. Including the ability to: — Extend your videos to make them longer (with audio) — Set the first and last frame of your video to control your output (with audio) — Upload multiple ingredient images to craft your scene (with audio) — Add or remove objects directly in your video These features are available in Flow by Google, the Gemini API, and Google Cloud Vertex AI. Veo 3.1 is also available in the Google Gemini. We’re so excited to see what you create!

Google AI

71,238 views • 1 year ago