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。

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

World Labs

69,798 subscribers

339,753 次观看 • 8 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!

Odyssey

704,428 次观看 • 1 年前

RTFM can be seen as a learned renderer: it is an autoregressive diffusion transformer trained end-to-end on large-scale video data, and it learns to model 3D geometry, reflections, shadows and more just by observing them in its training set.

RTFM can be seen as a learned renderer: it is an autoregressive diffusion transformer trained end-to-end on large-scale video data, and it learns to model 3D geometry, reflections, shadows and more just by observing them in its training set.

World Labs

15,870 次观看 • 8 个月前

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

LemonSlice

170,779 次观看 • 1 年前

🚀 We open-sourced LongLive — interactive, real-time long-video generation. 👥Generates video in real time as users enter text prompts. ⚡️20.7 FPS on a single H100,⏱️up to 240s per clip. 🎬Fine-tunes SOTA short-video models (e.g., Wan) into long-video generators. 🌍One step closer to World Models. All code for training & inference, model weights, demo page, and videos released! Paper: Code: Model: Demo Page: Introduction Video:

🚀 We open-sourced LongLive — interactive, real-time long-video generation. 👥Generates video in real time as users enter text prompts. ⚡️20.7 FPS on a single H100,⏱️up to 240s per clip. 🎬Fine-tunes SOTA short-video models (e.g., Wan) into long-video generators. 🌍One step closer to World Models. All code for training & inference, model weights, demo page, and videos released! Paper: Code: Model: Demo Page: Introduction Video:

Yukang Chen

11,752 次观看 • 8 个月前

Our third announcement is GWM Worlds. A world model for real-time environment simulation. You give the model a static scene, and it generates an immersive, infinite, explorable space as you move through it, with geometry, lighting and physics. All in real-time. You can travel to any place, real or imagined. You can become any agent, a person walking through a city, a drone flying over a snowy mountain or a robot navigating a warehouse.

Our third announcement is GWM Worlds. A world model for real-time environment simulation. You give the model a static scene, and it generates an immersive, infinite, explorable space as you move through it, with geometry, lighting and physics. All in real-time. You can travel to any place, real or imagined. You can become any agent, a person walking through a city, a drone flying over a snowy mountain or a robot navigating a warehouse.

Runway

80,279 次观看 • 6 个月前

Introducing Agora-1, a multi-agent world model. Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time. Try our playable research preview today, with Agora-1 simulating a multiplayer GoldenEye deathmatch!

Introducing Agora-1, a multi-agent world model. Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time. Try our playable research preview today, with Agora-1 simulating a multiplayer GoldenEye deathmatch!

Odyssey

903,724 次观看 • 29 天前

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

Odyssey

2,180,747 次观看 • 1 个月前

Odyssey releases AI interactive video technology that generates and streams frames every 40ms, offering free real-time interaction without game engines. - Introduces "interactive video" where users can both watch and interact with AI-generated content in real-time. - Technology bypasses traditional game engines, streaming video frames every 40 milliseconds. - Currently free to try, subject to GPU availability, representing an early stage of a new storytelling medium. - Combines elements of video games and films, hinting at future immersive digital experiences. This marks a pivotal advancement in digital storytelling, potentially transforming entertainment by enabling on-demand, interactive narratives. Quick demo below:

Odyssey releases AI interactive video technology that generates and streams frames every 40ms, offering free real-time interaction without game engines. - Introduces "interactive video" where users can both watch and interact with AI-generated content in real-time. - Technology bypasses traditional game engines, streaming video frames every 40 milliseconds. - Currently free to try, subject to GPU availability, representing an early stage of a new storytelling medium. - Combines elements of video games and films, hinting at future immersive digital experiences. This marks a pivotal advancement in digital storytelling, potentially transforming entertainment by enabling on-demand, interactive narratives. Quick demo below:

Kol Tregaskes

33,878 次观看 • 1 年前

StreamDiT Real-Time Streaming Text-to-Video Generation StreamDiT enables real-time text-to-video generation at 16 FPS on a single GPU (H100)

StreamDiT Real-Time Streaming Text-to-Video Generation StreamDiT enables real-time text-to-video generation at 16 FPS on a single GPU (H100)

AK

43,659 次观看 • 11 个月前

Genie 3 generates minutes of consistent worlds in real-time at 720p!

Genie 3 generates minutes of consistent worlds in real-time at 720p!

Tim Rocktäschel

40,641 次观看 • 10 个月前

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

Runway

1,160,597 次观看 • 3 个月前

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

28,871 次观看 • 5 个月前

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

15,968 次观看 • 4 个月前

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

World Labs

833,743 次观看 • 9 个月前

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

UE5.6 AI Real-Time Motion Generation Plugin — powered by a 1-billion-parameter motion model trained on NVIDIA CUDA. It runs locally in real time with 8GB of VRAM and converts webcam or video footage into real-time XYZ skeletal point data and rotation values.

CYANPUPPETS

28,846 次观看 • 4 个月前

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

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

117,016 次观看 • 7 个月前

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that directly generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

Stan Szymanowicz

125,828 次观看 • 1 年前

🚨 PixVerse just dropped R1 and it's the end of game development as we know it. A Real-time World Model that generates interactive, voice-controlled worlds from raw video. No assets. No scripting. No waiting. Here's everything you need to know: 👇

🚨 PixVerse just dropped R1 and it's the end of game development as we know it. A Real-time World Model that generates interactive, voice-controlled worlds from raw video. No assets. No scripting. No waiting. Here's everything you need to know: 👇

Hasan Toor

56,786 次观看 • 3 个月前

We present MotionStream — real-time, long-duration video generation that you can interactively control just by dragging your mouse. All videos here are raw, real-time screen captures without any post-processing. Model runs on a single H100 at 29 FPS and 0.4s latency.

We present MotionStream — real-time, long-duration video generation that you can interactively control just by dragging your mouse. All videos here are raw, real-time screen captures without any post-processing. Model runs on a single H100 at 29 FPS and 0.4s latency.

Xun Huang

98,047 次观看 • 7 个月前

World Model meets robot policy! Robbyant's LingBot-VA: unifies video world modeling and robotic policy learning. - A single model generates both future video and the actions to make it real. - Long-term memory enables long-horizon tasks. - Claims significant outperformance over π₀.₅ in real-world tasks. - It's open-source

World Model meets robot policy! Robbyant's LingBot-VA: unifies video world modeling and robotic policy learning. - A single model generates both future video and the actions to make it real. - Long-term memory enables long-horizon tasks. - Claims significant outperformance over π₀.₅ in real-world tasks. - It's open-source

The Humanoid Hub

17,721 次观看 • 4 个月前