Loading video...

Video Failed to Load

Go Home

today, sync. is excited to announce react-1 a ten billion parameter masked video diffusion model built for one purpose: giving you full creative control over performances in post

synclabs's profile picture

sync. labs

11,002 subscribers

27,155 views • 6 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

1/n: We are excited to share that our paper on Chroma, a general purpose diffusion model for proteins, is out today in nature! A couple of my favorite highlights in the 🧵below 👇
0:21

1/n: We are excited to share that our paper on Chroma, a general purpose diffusion model for proteins, is out today in nature! A couple of my favorite highlights in the 🧵below 👇

Andrew Beam

362,073 views • 2 years ago

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.
0:57

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,129,754 views • 1 month ago

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks
1:51

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

46,962 views • 5 months ago

We're excited to announce our partnership with Prime Intellect to allow anyone to train browser agents. General-purpose models aren't optimized for your browser workflows, BrowserEnv lets you train one that is. Checkout and train your own custom model in a few hours.
0:29

We're excited to announce our partnership with Prime Intellect to allow anyone to train browser agents. General-purpose models aren't optimized for your browser workflows, BrowserEnv lets you train one that is. Checkout and train your own custom model in a few hours.

Browserbase

190,980 views • 3 months ago

Today, we’re excited to announce that LTX Studio is coming out of beta, bringing new tools for video creation and major upgrades to your creative workflow. Learn more below.
1:01

Today, we’re excited to announce that LTX Studio is coming out of beta, bringing new tools for video creation and major upgrades to your creative workflow. Learn more below.

LTX.io

137,829 views • 1 year ago

🚨 I’m so excited to announce Expert Agents. AI-powered workflows built by the best creative strategists in the world.
1:05

🚨 I’m so excited to announce Expert Agents. AI-powered workflows built by the best creative strategists in the world.

Reza Khadjavi

32,317 views • 1 year ago

Excited to announce our $9M USD seed round led by Initialized Capital and the first large-scale interpretable LLM: an 8 billion parameter model capable of explaining its outputs through mechanisms humans can actually understand.
2:33

Excited to announce our $9M USD seed round led by Initialized Capital and the first large-scale interpretable LLM: an 8 billion parameter model capable of explaining its outputs through mechanisms humans can actually understand.

Guide Labs

10,514 views • 7 months ago

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.
2:25

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.

Y Combinator

50,846 views • 6 months ago

Omegance A Single Parameter for Various Granularities in Diffusion-Based Synthesis
0:43

Omegance A Single Parameter for Various Granularities in Diffusion-Based Synthesis

AK

19,283 views • 1 year ago

react-1 by sync. labs the first model of its kind, allowing you to not just change what the speaker says, but how they say it available in research preview today
1:00

react-1 by sync. labs the first model of its kind, allowing you to not just change what the speaker says, but how they say it available in research preview today

sync. labs

29,439 views • 7 months ago

editing a conversation should be as easy as having one. today we are excited to announce the launch of the sync. assistant - a whole new way to lipsync your videos
1:29

editing a conversation should be as easy as having one. today we are excited to announce the launch of the sync. assistant - a whole new way to lipsync your videos

sync. labs

11,354 views • 4 months ago

Introducing Marey by Moonvalley, the world’s first fully licensed AI video model built for professional production. Marey transforms filmmaking today. Its unprecedented creative controls enable you to realize expansive visions, execute complex VFX sequences, and maintain complete creative authority throughout your projects. This is generative filmmaking for those who need to control every frame. We can't wait to see what you make.
1:45

Introducing Marey by Moonvalley, the world’s first fully licensed AI video model built for professional production. Marey transforms filmmaking today. Its unprecedented creative controls enable you to realize expansive visions, execute complex VFX sequences, and maintain complete creative authority throughout your projects. This is generative filmmaking for those who need to control every frame. We can't wait to see what you make.

Moonvalley

91,453 views • 1 year ago

🎬This is from a static MJ 7 image + HeyGen 4! The voice over is human performance, but the nuances the diffusion model picks up is pretty next level for the character. I masked in a video of the cars moving from Kling. Pretty impressive.
0:20

🎬This is from a static MJ 7 image + HeyGen 4! The voice over is human performance, but the nuances the diffusion model picks up is pretty next level for the character. I masked in a video of the cars moving from Kling. Pretty impressive.

Dave Clark

11,224 views • 1 year ago

1/2 Meet Wan2.7-Video — The Comprehensive Model for Controllable Video Storytelling! From single clips to full-scale narrative direction, we’ve built more than just a generator. We’ve built a director’s suite: • Multimodal control over performance and style via text, image, audio, and video. • Character customization with up to 5 reference inputs and voice profiles. • Video editing with simple, intuitive instructions. • Full-stack creative toolkit: generation, editing, cloning, restyling, continuation, and more. • Sustained improvements in visual fidelity, motion stability, and prompt adherence.
1:44

1/2 Meet Wan2.7-Video — The Comprehensive Model for Controllable Video Storytelling! From single clips to full-scale narrative direction, we’ve built more than just a generator. We’ve built a director’s suite: • Multimodal control over performance and style via text, image, audio, and video. • Character customization with up to 5 reference inputs and voice profiles. • Video editing with simple, intuitive instructions. • Full-stack creative toolkit: generation, editing, cloning, restyling, continuation, and more. • Sustained improvements in visual fidelity, motion stability, and prompt adherence.

Wan

25,571,161 views • 3 months ago

Today, we launch Viggle V4 + Character Refine. - Strong character consistency with precise motion control - Upload 1 image → auto-generate multi-angle references - 1:1 motion transfer from reference videos - Multi-character swap in complex scenes - Generate in SECONDS at lower cost - Up to 60s videos Powered by our proprietary 3D foundation model, built for speed, reliability, and full creative control. Try it for free! 👇
0:37

Today, we launch Viggle V4 + Character Refine. - Strong character consistency with precise motion control - Upload 1 image → auto-generate multi-angle references - 1:1 motion transfer from reference videos - Multi-character swap in complex scenes - Generate in SECONDS at lower cost - Up to 60s videos Powered by our proprietary 3D foundation model, built for speed, reliability, and full creative control. Try it for free! 👇

ViggleAI

400,326 views • 4 months ago

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇
0:50

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

Edward Johns

74,680 views • 1 year ago

We release Cosmos Policy 💫: a state-of-the-art robot policy built on a video diffusion model backbone. - policy + world model + value function — in 1 model - no architectural changes to the base video model - SOTA in LIBERO (98.5%), RoboCasa (67.1%), & ALOHA tasks (93.6%) 🧵👇
1:31

We release Cosmos Policy 💫: a state-of-the-art robot policy built on a video diffusion model backbone. - policy + world model + value function — in 1 model - no architectural changes to the base video model - SOTA in LIBERO (98.5%), RoboCasa (67.1%), & ALOHA tasks (93.6%) 🧵👇

Moo Jin Kim

149,139 views • 5 months ago

UE5.6 real-time motion capture plugin with native MetaHuman support. It requires only a webcam or uploaded video, and uses a 1-billion-parameter model to convert video into 3D motion data in real time, enabling automatic retargeting.
0:55

UE5.6 real-time motion capture plugin with native MetaHuman support. It requires only a webcam or uploaded video, and uses a 1-billion-parameter model to convert video into 3D motion data in real time, enabling automatic retargeting.

CYANPUPPETS

47,564 views • 3 months ago