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。

Cool new work on real-time video generation with motion control. MotionStream enables sub-second latency streaming on a single GPU. You can also control what parts of an image do & don't move, like the video below. 👏 to Xun Huang, Joonghyuk Shin, and team!

Justine Moore

165,850 subscribers

21,780 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

MotionStream Real-Time Video Generation with Interactive Motion Controls model runs in real time on a single NVIDIA H100 GPU (29 FPS, 0.4s Latency)

MotionStream Real-Time Video Generation with Interactive Motion Controls model runs in real time on a single NVIDIA H100 GPU (29 FPS, 0.4s Latency)

AK

22,304 次观看 • 8 个月前

New AI video model MotionStream lets you control motion in real time. This is a glimpse at what all video models will allow you to do in the future.

New AI video model MotionStream lets you control motion in real time. This is a glimpse at what all video models will allow you to do in the future.

Dan Scalco

28,162 次观看 • 8 个月前

A single image. Cinematic motion. Turn wallpapers into living visuals with Motion Control on BudgetPixel AI. Drop in a reference → control the movement → get a premium ad-grade video in seconds.

A single image. Cinematic motion. Turn wallpapers into living visuals with Motion Control on BudgetPixel AI. Drop in a reference → control the movement → get a premium ad-grade video in seconds.

BudgetPixel AI

204,084 次观看 • 5 个月前

Take the drawings on the fridge to the silver screen. With video generation in the Google Gemini on #Pixel10 Pro you can upload an image and transform it with motion and sound based on the scene you describe:¹

Take the drawings on the fridge to the silver screen. With video generation in the Google Gemini on #Pixel10 Pro you can upload an image and transform it with motion and sound based on the scene you describe:¹

Made by Google

27,780 次观看 • 9 个月前

What if you could talk to your microscope? Honoured to present our work PertzLab on real-time image processing and smart microscopy! Video shows micro-manager control using #OmegaAgent by Loïc A. Royer 💻🔬⚗️

What if you could talk to your microscope? Honoured to present our work PertzLab on real-time image processing and smart microscopy! Video shows micro-manager control using #OmegaAgent by Loïc A. Royer 💻🔬⚗️

Lucien Hinderling

14,600 次观看 • 2 年前

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

Stability AI

181,441 次观看 • 1 年前

The new Krea 3D feature is insanely good. You can turn an image into a 3D model to move & rotate in space - and it guides real-time scene generation. Watch me move this couch around a living room ⬇️

The new Krea 3D feature is insanely good. You can turn an image into a 3D model to move & rotate in space - and it guides real-time scene generation. Watch me move this couch around a living room ⬇️

Justine Moore

32,708 次观看 • 1 年前

You can now turn any image on X into a video. Long press on an image that you like and select Make Video with Grok.

You can now turn any image on X into a video. Long press on an image that you like and select Make Video with Grok.

Chaitu

993,765 次观看 • 11 个月前

Nikola Jokic on what it takes to close a game like that in OT 🎙️ "Don't get too high, don't get too low. Just try to control what you can control." "Just believe in your team and in yourself."

Nikola Jokic on what it takes to close a game like that in OT 🎙️ "Don't get too high, don't get too low. Just try to control what you can control." "Just believe in your team and in yourself."

DNVR Nuggets

41,043 次观看 • 6 个月前

introducing Generative Sliders. now you can control the intensity, complexity, and movement of any image you generate with Krea 2. what new controls would you like to see? 👇

introducing Generative Sliders. now you can control the intensity, complexity, and movement of any image you generate with Krea 2. what new controls would you like to see? 👇

Krea

25,246 次观看 • 29 天前

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

Hao AI Lab

78,660 次观看 • 11 个月前

We may have cracked motion control in AI video. I've been testing the new Kling AI tool, and it's shockingly good. It can handle complex movements I've never gotten another video-to-video model to do - like this gymnastics clip. It can also do lip sync and camera movement 👇

We may have cracked motion control in AI video. I've been testing the new Kling AI tool, and it's shockingly good. It can handle complex movements I've never gotten another video-to-video model to do - like this gymnastics clip. It can also do lip sync and camera movement 👇

Justine Moore

350,825 次观看 • 6 个月前

Today, we're introducing Muse Image and Muse Video! 🖌️ Muse Image is an agentic image generation model with strong integrations with coding, search, and self-refinement! Muse Video is an early preview of our video generation efforts with strong audio and video generation abilities! Details below! 🧵👇

Today, we're introducing Muse Image and Muse Video! 🖌️ Muse Image is an agentic image generation model with strong integrations with coding, search, and self-refinement! Muse Video is an early preview of our video generation efforts with strong audio and video generation abilities! Details below! 🧵👇

Matt Deitke

51,442 次观看 • 3 天前

New on Higgsfield AI, Kling Motion Control. Change your video and keep the motion perfectly with any images you have! This was using some of my art pieces. It’s so easy.

New on Higgsfield AI, Kling Motion Control. Change your video and keep the motion perfectly with any images you have! This was using some of my art pieces. It’s so easy.

Ana Herrera

13,029 次观看 • 6 个月前

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵

Google DeepMind

1,480,967 次观看 • 10 个月前

Hurts to Brown for the second time today CHIvsPHI on Prime Video Also streaming on NFL+

Hurts to Brown for the second time today CHIvsPHI on Prime Video Also streaming on NFL+

NFL

578,089 次观看 • 7 个月前

We’ve just added image-to-video with Veo 3 inside LTX Studio. Start from an image, guide motion with a prompt, and get cinematic results with better consistency and control. Now live for Pro users.

We’ve just added image-to-video with Veo 3 inside LTX Studio. Start from an image, guide motion with a prompt, and get cinematic results with better consistency and control. Now live for Pro users.

LTX Studio

1,536,293 次观看 • 11 个月前

Gen-3 Alpha Image to Video now supports using an image as either the first or last frame of your video generation. This feature can be used on its own or combined with a text prompt for additional guidance. All examples below demonstrate using an image as the last frame. (1/5)

Gen-3 Alpha Image to Video now supports using an image as either the first or last frame of your video generation. This feature can be used on its own or combined with a text prompt for additional guidance. All examples below demonstrate using an image as the last frame. (1/5)

Runway

143,494 次观看 • 1 年前

Imagine directing a character’s movement as easily as uploading a reference video. Creating lifelike character motion usually takes expensive mocap studios. That’s exactly what Kling 3.0 Motion Control on Pollo AI enables: ⤵️

Imagine directing a character’s movement as easily as uploading a reference video. Creating lifelike character motion usually takes expensive mocap studios. That’s exactly what Kling 3.0 Motion Control on Pollo AI enables: ⤵️

Arpita Trisha

21,598 次观看 • 4 个月前