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.

Learn how to create expressive character performances with Act-Two, our most advanced motion capture yet. Now supporting hand and upper body tracking as well as an even wider variety of characters and styles.

Runway

253,033 subscribers

22,972 views • 1 year ago •via X (Twitter)

Science & Technology Arts

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise customers and Creative Partners. Learn more about Act-Two below. 1/4

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise customers and Creative Partners. Learn more about Act-Two below. 1/4

Runway

499,508 views • 1 year ago

Introducing, Act-One. A new way to generate expressive character performances inside Gen-3 Alpha using a single driving video and character image. No motion capture or rigging required. Learn more about Act-One below. (1/7)

Introducing, Act-One. A new way to generate expressive character performances inside Gen-3 Alpha using a single driving video and character image. No motion capture or rigging required. Learn more about Act-One below. (1/7)

Runway

1,138,744 views • 1 year ago

Act-Two allows you to create highly expressive scenes entirely driven by the nuanced performances of your actors. The timing, delivery, body language and subtle expressions are all faithfully transposed from your driving performances to your generated characters. Learn more below. 1/3

Act-Two allows you to create highly expressive scenes entirely driven by the nuanced performances of your actors. The timing, delivery, body language and subtle expressions are all faithfully transposed from your driving performances to your generated characters. Learn more below. 1/3

Runway

24,226 views • 1 year ago

At Unreal Fest Stockholm, Voice to Visuals brought together Unreal Engine’s most powerful animation tools, showing how expressive performances can come to life in real time. Using Take Recorder, Sequencer, MetaHuman Animator, Live Link Hub, and Performance Capture Manager — alongside Captury’s markerless motion capture — the demo showcased end-to-end performance capture and playback inside UE. From voice-driven lip sync to real-time retargeting across diverse characters, and even dynamic character swaps, this workflow demonstrates a new era of speed, creativity, and flexibility for animation and more!

At Unreal Fest Stockholm, Voice to Visuals brought together Unreal Engine’s most powerful animation tools, showing how expressive performances can come to life in real time. Using Take Recorder, Sequencer, MetaHuman Animator, Live Link Hub, and Performance Capture Manager — alongside Captury’s markerless motion capture — the demo showcased end-to-end performance capture and playback inside UE. From voice-driven lip sync to real-time retargeting across diverse characters, and even dynamic character swaps, this workflow demonstrates a new era of speed, creativity, and flexibility for animation and more!

Unreal Engine

13,745 views • 9 months ago

The two bad things about supporting arbitrary 3d models as characters is that I have to actually learn how to use the unity animator, and character sprites interact incredibly poorly with other 3d geometry that gets really close to them.

The two bad things about supporting arbitrary 3d models as characters is that I have to actually learn how to use the unity animator, and character sprites interact incredibly poorly with other 3d geometry that gets really close to them.

TheDoddlerRO

25,229 views • 4 months ago

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,533 views • 3 years ago

We use our warmup to MOVE with our 3D Movement Prep system. This means training the brain as well as the body with a variety of patterns and positions in different planes.

We use our warmup to MOVE with our 3D Movement Prep system. This means training the brain as well as the body with a variety of patterns and positions in different planes.

Zach Dechant

46,793 views • 1 year ago

Kling 2.6 Motion Control is out NOW 💥 Complex moves under control, with full-body sync and expression mapping Upload an image of your character and a motion reference to track face expressions, body motion, and hand moves. Up to 30-sec generations Available for all plans

Kling 2.6 Motion Control is out NOW 💥 Complex moves under control, with full-body sync and expression mapping Upload an image of your character and a motion reference to track face expressions, body motion, and hand moves. Up to 30-sec generations Available for all plans

Magnific

23,263 views • 7 months ago

What exactly is "Wuxia," and how does Phantom Blade Zero define it? In a recent interview in China, our Director Soulframe shares how we capture the spirit of wuxia, drawing from authentic kung fu and blending it with motion capture to create distinct fighting styles and layered narrative design. 👇

What exactly is "Wuxia," and how does Phantom Blade Zero define it? In a recent interview in China, our Director Soulframe shares how we capture the spirit of wuxia, drawing from authentic kung fu and blending it with motion capture to create distinct fighting styles and layered narrative design. 👇

Phantom Blade Zero

127,368 views • 3 months ago

How to CREATE Long AI Videos with Consistent Characters in (2026) Learn how to create long cinematic AI videos with consistent characters, environments, and motion. Learn how build reference assets, chain clips together with previous video generations, and structure prompts so the final result feels like one continuous film instead of disconnected AI shots. This information is for both the new and existing Youtube creators, who want to learn how to create good videos, with consistent characters. Watch to the end, to learn properly. Like, Share and Retweet. Follow BIG CHRIS

How to CREATE Long AI Videos with Consistent Characters in (2026) Learn how to create long cinematic AI videos with consistent characters, environments, and motion. Learn how build reference assets, chain clips together with previous video generations, and structure prompts so the final result feels like one continuous film instead of disconnected AI shots. This information is for both the new and existing Youtube creators, who want to learn how to create good videos, with consistent characters. Watch to the end, to learn properly. Like, Share and Retweet. Follow BIG CHRIS

BIG CHRIS

46,409 views • 2 months ago

The release of our next generation motion capture model, Act-Two. How to use it. And some great work from the community. Get caught up on what happened This Week with Runway.

The release of our next generation motion capture model, Act-Two. How to use it. And some great work from the community. Get caught up on what happened This Week with Runway.

Runway

27,030 views • 1 year ago

Sam Levinson describes himself as an "emotional writer," explaining that he begins with a character and allows the plot to flow as a stream of consciousness. | Variety A Night in the Writers’ Room

Sam Levinson describes himself as an "emotional writer," explaining that he begins with a character and allows the plot to flow as a stream of consciousness. | Variety A Night in the Writers’ Room

Variety

22,594 views • 2 months ago

Today we introduced Gemini Enterprise, built with our most advanced Gemini models. It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context. Have a look at how it helps you build an agent for almost anything:

Today we introduced Gemini Enterprise, built with our most advanced Gemini models. It allows you to chat with your company’s documents, data and apps as well as build and deploy AI agents, all grounded in your information and context. Have a look at how it helps you build an agent for almost anything:

Sundar Pichai

1,105,606 views • 9 months ago

#midjourney #LumaDreamMachine Midjourney v6.1 does a great job with light and shadow, but for anime styles, it tends to make the characters look younger. It still can't accurately create fanart, but it does capture the feel of fireflies quite well.

#midjourney #LumaDreamMachine Midjourney v6.1 does a great job with light and shadow, but for anime styles, it tends to make the characters look younger. It still can't accurately create fanart, but it does capture the feel of fireflies quite well.

Michi

19,742 views • 2 years ago

Introducing Character Motion Control for Video Diffusion Models Creators currently lack control over how characters move and act in the videos they generate with AI. Today, we’re changing that. With Character Motion Control, you can act it out and bring your exact vision to life. How it works: 1️⃣ Describe the scene with a prompt 2️⃣ Upload an acting video to guide character movement 🎥 Generate a video where character motion is driven by the acting video. Register for Early Access via the link in the comments.

Introducing Character Motion Control for Video Diffusion Models Creators currently lack control over how characters move and act in the videos they generate with AI. Today, we’re changing that. With Character Motion Control, you can act it out and bring your exact vision to life. How it works: 1️⃣ Describe the scene with a prompt 2️⃣ Upload an acting video to guide character movement 🎥 Generate a video where character motion is driven by the acting video. Register for Early Access via the link in the comments.

Kinetix

97,871 views • 1 year ago

Roblox is testing an advanced Avatar Creator that allows you to fully customize the shape, size, and color of body parts, as well as draw and add stickers anywhere on the body. You can then Publish the body to the Marketplace to use as your main avatar across Roblox.

Bloxy News

117,216 views • 1 year ago

Today we're adding Voices to Act-Two, giving you even more control and expressiveness within your workflow. With Voices, you can easily change how your performance sounds to better suit your generated character. Learn how with today's Runway Academy.

Today we're adding Voices to Act-Two, giving you even more control and expressiveness within your workflow. With Voices, you can easily change how your performance sounds to better suit your generated character. Learn how with today's Runway Academy.

Runway

54,197 views • 11 months ago

it IS misogynistic to ignore the character she does have and now insist her only character trait is being pregnant/moxxie’s wife and nothing else. don’t devolve characters down to one trait and then act disappointed as if you’re not the one choosing the most shallow view

it IS misogynistic to ignore the character she does have and now insist her only character trait is being pregnant/moxxie’s wife and nothing else. don’t devolve characters down to one trait and then act disappointed as if you’re not the one choosing the most shallow view

striker’s biggest glazer

333,848 views • 4 months ago

Some more V2V tests as I patiently wait for Act One. I played around with creating split screen videos of myself to get two characters, and I think it worked really well 🖤🦾

Some more V2V tests as I patiently wait for Act One. I played around with creating split screen videos of myself to get two characters, and I think it worked really well 🖤🦾

Rob

28,584 views • 1 year ago