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.

today, we're making another step towards the future. introducing our first Real-time Video generation model. join the beta 👇

Krea

118,428 subscribers

1,108,828 views • 1 year ago •via X (Twitter)

Science & Technology Education Arts

Anya Rossi• Live Now

Private livecam show

36 Comments

madpencil_1 year ago

Just in two years 🔥

Krea1 year ago

🥹

Emad1 year ago

I remember back in the days of real time drawing augmentation, can't wait to try :)

Boldtron1 year ago

🚀🚀🚀

Krea1 year ago

❤️‍🔥

mickey friedman1 year ago

this is amazing

kache1 year ago

super cool

Dylan White1 year ago

Amazing you guys always kill it. I’ve been supportive from the beginning you know I’m joining that beta.

Gabriel Foulon1 year ago

🔥🔥🔥🔥

Boz1 year ago

impressive!

beccu1 year ago

This is insaaaneeee 😍😍😍 super exciting 💖

Tom Blake1 year ago

Wait, whaaaaaaat!?! 🤯

Krea1 year ago

it's happening!

Heather Cooper1 year ago

Yes.

Minh Do1 year ago

Massive. This is amazing. I thought we wouldn’t have realtime video til next year! Just wow.

Jacopo Bettinaldi1 year ago

Wow, what a milestone! I truly believe this is one of the most significant steps towards the future of content creation and communication. I can't even begin to imagine all the applications this will unlock. Amazing work!

grafismo1 year ago

👏👏 joined the beta waiting list.

Diego Rodriguez1 year ago

congratulations to the chef! this is incredible!

kie1 year ago

👀

William Lamkin1 year ago

@viccpoes what are the key differences between a real-time image gen model and a real-time video gen model?

Waniss Lrg1 year ago

This is FUCKING Huge

aadilpickle1 year ago

this is fking insane

madpencil_1 year ago

This is something really really cool

vittorio1 year ago

Insane

goo.vision1 year ago

🔥🔥🔥

VentureMind AI1 year ago

Major step 👏

Gavin Purcell1 year ago

👀

Alex Patrascu1 year ago

Crazy, wild, insane! Everything all at once 🥳

Charlie L.1 year ago

yooo this looks sick

hiwith.ai1 year ago

@venturetwins Real-time video generation means we can finally "sketch" in motion - turning rough storyboard ideas into animated sequences instantly. This could revolutionize how AI artists pitch concepts to clients, going from static mockups to live, iterative presentations.

Dreaming Tulpa 🥓👑1 year ago

ooh sick

speedphantom1 year ago

get this ai slop ad out of my timeline

CuddlySalmon1 year ago

👀

Sway Molina1 year ago

That track tho

JK VIS ENT1 year ago

Wow! Game Changing...

Alex Secara1 year ago

Video, generated live.

Related Videos

Real-time World Models are the next AI frontier. Today, we're taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:

Real-time World Models are the next AI frontier. Today, we're taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:

reactor

10,296,687 views • 6 months ago

Introducing Starchild-1 from Odyssey, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear. Starchild-1 represents a big step towards a general-purpose world simulator.

Introducing Starchild-1 from Odyssey, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear. Starchild-1 represents a big step towards a general-purpose world simulator.

Oliver Cameron

247,268 views • 5 months ago

Another step towards the future of media

Another step towards the future of media

BP26-Sakura

14,735 views • 3 months ago

1/ We're unwrapping the new architecture + benchmarks behind Playground v3 - our new foundation model focused on graphic design. This is our first step towards making a powerful AI graphic designer. It's state-of-the-art at text rendering, prompt understanding, and color precision. Paper + details in the reply tweet 👇

1/ We're unwrapping the new architecture + benchmarks behind Playground v3 - our new foundation model focused on graphic design. This is our first step towards making a powerful AI graphic designer. It's state-of-the-art at text rendering, prompt understanding, and color precision. Paper + details in the reply tweet 👇

Suhail

334,636 views • 2 years ago

Today we’re rolling out Daily.fun We're making markets ridiculously fun to play, and we're just getting started. Join our beta today.

Today we’re rolling out Daily.fun We're making markets ridiculously fun to play, and we're just getting started. Join our beta today.

armand type beat

346,008 views • 19 days ago

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Today, we're introducing GLM-5.2 Fast: our GLM-5.2 Model API designed for the most demanding real-time use cases. The Fast tier delivers 2-3x higher TPS than the standard GLM-5.2 MAPI.

Baseten

115,626 views • 3 months ago

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

977,092 views • 2 years ago

$Every day, we're one step closer to our TGE and our ultimate goal - bringing real estate investment opportunities to the masses. 🏡🏙️🌍 📺 Our feature on CryptoKnightsShow is coming soon, introducing EstateX to over 300 million households! 🚀 The future of fractionalized real estate is being built in real-time. Watch us make it happen. Join our community on Telegram 👇 Read all about us 📖$

Every day, we're one step closer to our TGE and our ultimate goal - bringing real estate investment opportunities to the masses. 🏡🏙️🌍 📺 Our feature on CryptoKnightsShow is coming soon, introducing EstateX to over 300 million households! 🚀 The future of fractionalized real estate is being built in real-time. Watch us make it happen. Join our community on Telegram 👇 Read all about us 📖

EstateX

73,758 views • 1 year ago

Real-time World Models are the next AI frontier. Today, we reactor are taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:

Real-time World Models are the next AI frontier. Today, we reactor are taking the first step towards this reality: our early preview lets you experience worlds generated in real-time, running on our global low-latency infrastructure. Try it now:

Bryce Schmidtchen

8,491,928 views • 6 months ago

Introducing fal's H3 Max Director, the first natively continuous real-time frontier video model for action-controlled long-form generation. Unlike H3 Max and other video models, H3 Max Director generates a single continuous video stream, maintaining context over time rather than chaining together discrete clips. It’s the technology behind our experimental infinite AI livestream where viewers interact with and shape what gets generated in real time. Now, we’re making the underlying model available via API. For the first two weeks, all H3 Max Director generations are 75% off.

Introducing fal's H3 Max Director, the first natively continuous real-time frontier video model for action-controlled long-form generation. Unlike H3 Max and other video models, H3 Max Director generates a single continuous video stream, maintaining context over time rather than chaining together discrete clips. It’s the technology behind our experimental infinite AI livestream where viewers interact with and shape what gets generated in real time. Now, we’re making the underlying model available via API. For the first two weeks, all H3 Max Director generations are 75% off.

fal

547,529 views • 2 months ago

introducing Realtime Edit. now, like with Nano Banana, you can edit images with complex instructions in real time. join the beta 👇

introducing Realtime Edit. now, like with Nano Banana, you can edit images with complex instructions in real time. join the beta 👇

Krea

8,783,583 views • 9 months ago

today, we're introducing our first image model: Krea 1. Krea 1 offers superior aesthetic control and image quality. It has a wide range of artistic knowledge and supports style references and custom trainings. learn how to try our free beta 👇

today, we're introducing our first image model: Krea 1. Krea 1 offers superior aesthetic control and image quality. It has a wide range of artistic knowledge and supports style references and custom trainings. learn how to try our free beta 👇

Krea

1,181,823 views • 1 year ago

Step into the future with Usual: This marks the launch of our first revolutionary stablecoin product: USD0. Usual isn't just another stablecoin; it's a shift towards financial freedom, redistributing power back to the users. Join the alternative 🔮🦝 🔗

Step into the future with Usual: This marks the launch of our first revolutionary stablecoin product: USD0. Usual isn't just another stablecoin; it's a shift towards financial freedom, redistributing power back to the users. Join the alternative 🔮🦝 🔗

Usual

165,182 views • 2 years ago

At Physical Intelligence (π) our mission is to bring general-purpose AI into the physical world. We're excited to show the first step towards this mission - our first generalist model π₀ 🧠 🤖 Paper, blog, uncut videos:

At Physical Intelligence (π) our mission is to bring general-purpose AI into the physical world. We're excited to show the first step towards this mission - our first generalist model π₀ 🧠 🤖 Paper, blog, uncut videos:

Physical Intelligence

567,061 views • 2 years ago

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning. ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on AMD. 🧵

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning. ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on AMD. 🧵

Zyphra

335,093 views • 5 months ago

Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of making general-purpose robots a reality, we're pushing the frontiers of what end-to-end AI models can achieve in the real world. Here's a preview of our early results in autonomous general-purpose dexterous capabilities – fast, reactive, smooth, precise, bi-manual coordinated sensorimotor control.

Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of making general-purpose robots a reality, we're pushing the frontiers of what end-to-end AI models can achieve in the real world. Here's a preview of our early results in autonomous general-purpose dexterous capabilities – fast, reactive, smooth, precise, bi-manual coordinated sensorimotor control.

Generalist

279,190 views • 1 year ago

Today, we're introducing Bulbul V4 Flash, our latest text to speech model built for natural, expressive speech across Indian languages. Flash brings frontier-quality speech into a smaller, more efficient model, preserving the subtle details that make voices sound natural while making speech generation significantly faster. See details in our blog:

Today, we're introducing Bulbul V4 Flash, our latest text to speech model built for natural, expressive speech across Indian languages. Flash brings frontier-quality speech into a smaller, more efficient model, preserving the subtle details that make voices sound natural while making speech generation significantly faster. See details in our blog:

Sarvam

161,705 views • 28 days ago

open beta is live the first step towards domination weaponize the trenches on Solana

open beta is live the first step towards domination weaponize the trenches on Solana

xFractal

348,427 views • 1 year ago

Introducing Mocha - the app builder for the 99%. Not another mockup builder. Not another Supabase wrapper. Today we're also launching Spotlight 👇

Introducing Mocha - the app builder for the 99%. Not another mockup builder. Not another Supabase wrapper. Today we're also launching Spotlight 👇

Nicholas Charriere

526,837 views • 1 year ago

A heartwarming video you shouldn’t miss today. Guru’s blessings, the first step towards victory.

A heartwarming video you shouldn’t miss today. Guru’s blessings, the first step towards victory.

Anu Satheesh 🇮🇳🚩

25,534 views • 8 months ago