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。

This is literally magic 🤯 FMA-Net is a new AI method for video deblurring! It uses complex motion representation learning for spatio-temporally-variant restoration with kernels that are aware of motion trajectories. More info below ⬇️⬇️

Alex Carlier

8,596 subscribers

144,268 次观看 • 2 年前 •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

DINOv2 by Meta AI is the first method for training computer vision models that uses self-supervised learning to achieve results matching or exceeding industry standards. More details and a demo ⬇️

DINOv2 by Meta AI is the first method for training computer vision models that uses self-supervised learning to achieve results matching or exceeding industry standards. More details and a demo ⬇️

AI at Meta

96,119 次观看 • 3 年前

Jeff Nippard was right Training Calves in the Lower half Range of Motion is way more effective for growth. Reference Link below ⬇️

Jeff Nippard was right Training Calves in the Lower half Range of Motion is way more effective for growth. Reference Link below ⬇️

Anand Nagu

20,525 次观看 • 4 个月前

A new era of AI video is here. Kling 3.0 and Kling 3.0 Motion Control are officially available for everyone now! With native 1080p cinematic output, it is built for advertising, brand storytelling, and professional film production.

Taylor Brown | AI Specialist 🤖

178,274 次观看 • 5 个月前

PatchFusion was just released. Compared to ZoeDepth, it predicts depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️

PatchFusion was just released. Compared to ZoeDepth, it predicts depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️

Alex Carlier

92,067 次观看 • 2 年前

Replace a person from a video with any character using a single picture 🤯 This new paper from Alibaba is called MIMO: Controllable Character Video Synthesis withSpatial Decomposed Modeling More below ⬇️⬇️

Replace a person from a video with any character using a single picture 🤯 This new paper from Alibaba is called MIMO: Controllable Character Video Synthesis withSpatial Decomposed Modeling More below ⬇️⬇️

Alex Carlier

14,113 次观看 • 1 年前

Gemini Omni's motion control is f*cking cracked i just figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)

Gemini Omni's motion control is f*cking cracked i just figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)

Miko

59,856 次观看 • 1 个月前

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

Jialu Li

35,060 次观看 • 1 年前

ok, this is crazy. LumaLabs AI just unveiled Ray 2, a new AI video model, the motion and camera work are incredible. Here are 15 Raw clips with prompts👇:

ok, this is crazy. LumaLabs AI just unveiled Ray 2, a new AI video model, the motion and camera work are incredible. Here are 15 Raw clips with prompts👇:

el.cine

138,593 次观看 • 1 年前

New motion video for a real estate client currently working on it. Also, this is my first edit using this Mac 🔥.

New motion video for a real estate client currently working on it. Also, this is my first edit using this Mac 🔥.

Aftermagics

22,029 次观看 • 7 个月前

🚨BREAKING: Kling 2.5 Turbo just made AI video look like Hollywood. Type a prompt → get cinematic shots with smooth motion. This is the new gold standard for AI content creation 👇

🚨BREAKING: Kling 2.5 Turbo just made AI video look like Hollywood. Type a prompt → get cinematic shots with smooth motion. This is the new gold standard for AI content creation 👇

The AI Colony

81,532 次观看 • 11 个月前

Some of my favorite parts of the new Interfere product pages. Every asset is fully built in code. The animations are built with Motion, except for the dot matrix, which is uses a canvas. Had a ton of fun working on these with Paul Faivret.

Some of my favorite parts of the new Interfere product pages. Every asset is fully built in code. The animations are built with Motion, except for the dot matrix, which is uses a canvas. Had a ton of fun working on these with Paul Faivret.

Jakub Krehel

23,849 次观看 • 1 个月前

Choombaz this is just for you‼️ Higgsfield. ai 🧩 Kling Motion Control⚡🎬 lets you transfer motion like a director — fast, clean, and ridiculously fun. 3 easy viral examples below 👇 1⃣ rebecca |Face dance 2⃣ Faye Valentine | Tiktok dance 3⃣ Himiko | Dame un grrrr stop posting dancing cats make something awesome🤯with Higgsfield🧩 Kling motion Control

Choombaz this is just for you‼️ Higgsfield. ai 🧩 Kling Motion Control⚡🎬 lets you transfer motion like a director — fast, clean, and ridiculously fun. 3 easy viral examples below 👇 1⃣ rebecca |Face dance 2⃣ Faye Valentine | Tiktok dance 3⃣ Himiko | Dame un grrrr stop posting dancing cats make something awesome🤯with Higgsfield🧩 Kling motion Control

🆉🆄🆄🅷🅻82

53,909 次观看 • 7 个月前

reminder that you can create an AI video for literally ANYTHING the prompt is everything.. this is a result of our new V2 prompting system:

reminder that you can create an AI video for literally ANYTHING the prompt is everything.. this is a result of our new V2 prompting system:

Miko

23,886 次观看 • 5 个月前

This video, a creation of motion graphics designer Tom Coben, is mind-blowing for multiple reasons: the terrifyingly good bowling robot and the fact that the entire video is completely computer-generated [read more:

This video, a creation of motion graphics designer Tom Coben, is mind-blowing for multiple reasons: the terrifyingly good bowling robot and the fact that the entire video is completely computer-generated [read more:

Massimo

560,087 次观看 • 3 年前

hey guys i need some help. this is my biggest insecurity so please be kind. first clip is from the morning, second is from nighttime. i’ve had a severe bloating problem for a long time. more info down below⬇️⬇️

hey guys i need some help. this is my biggest insecurity so please be kind. first clip is from the morning, second is from nighttime. i’ve had a severe bloating problem for a long time. more info down below⬇️⬇️

Griffin!🌸 🔜 Offkai

17,962 次观看 • 4 个月前

Kling 2.6 Motion Control is absolutely insane 🤯 Take any reference video and transfer the exact motion onto an AI character: full-body sync, facial expressions, hand gestures, everything. All with just a few clicks. Perfect for e-comm brands and agencies creating AI video ads that don't look like AI. Here's the problem: AI-generated video ads still look robotic. The movements are stiff, the expressions are flat. Your audience clocks it as AI instantly and keeps scrolling. Kling 2.6 Motion Control fixes it: → Start with any reference clip (stock footage, existing UGC, motion reference) → Upload to Kling → Map the exact movement onto any AI character → Full-body motion, hand gestures, facial expressions—all transferred → Generate up to 30 seconds of video No stiff AI movements, no uncanny valley, no instant "skip this ad" reaction. What this unlocks: - Use one winning UGC motion → swap in different AI creators - Pull reference clips from anywhere → generate branded variations - Create dynamic AI video ads with real human movement - Test multiple "creators" without filming anyone new I recorded a quick walkthrough showing how to do this step-by-step. Want access? > Comment "KLING" > Like this post And I'll send it over (must be following so I can DM)

Kling 2.6 Motion Control is absolutely insane 🤯 Take any reference video and transfer the exact motion onto an AI character: full-body sync, facial expressions, hand gestures, everything. All with just a few clicks. Perfect for e-comm brands and agencies creating AI video ads that don't look like AI. Here's the problem: AI-generated video ads still look robotic. The movements are stiff, the expressions are flat. Your audience clocks it as AI instantly and keeps scrolling. Kling 2.6 Motion Control fixes it: → Start with any reference clip (stock footage, existing UGC, motion reference) → Upload to Kling → Map the exact movement onto any AI character → Full-body motion, hand gestures, facial expressions—all transferred → Generate up to 30 seconds of video No stiff AI movements, no uncanny valley, no instant "skip this ad" reaction. What this unlocks: - Use one winning UGC motion → swap in different AI creators - Pull reference clips from anywhere → generate branded variations - Create dynamic AI video ads with real human movement - Test multiple "creators" without filming anyone new I recorded a quick walkthrough showing how to do this step-by-step. Want access? > Comment "KLING" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

25,179 次观看 • 6 个月前

New open-source library speeds up whole-body imitation learning. Train the policy below in under 20 minutes ⬇️ LocoMuJoCo2 brings biomechanics and humanoid robotics into one clean, high-speed benchmark. Built for researchers who want to train smarter and faster. What it offers ✅ 22K+ motion trajectories per humanoid model ✅ Supports both MuJoCo and MJX ✅ JAX-based PPO, GAIL, AMP, DeepMimic implementations ✅ Plug-and-play robot2robot retargeting pipeline Whether you’re building humanoids or studying human motion, this toolkit saves you weeks of setup. Github: Thank you, Firas Al-Hafez for sharing this great work!

New open-source library speeds up whole-body imitation learning. Train the policy below in under 20 minutes ⬇️ LocoMuJoCo2 brings biomechanics and humanoid robotics into one clean, high-speed benchmark. Built for researchers who want to train smarter and faster. What it offers ✅ 22K+ motion trajectories per humanoid model ✅ Supports both MuJoCo and MJX ✅ JAX-based PPO, GAIL, AMP, DeepMimic implementations ✅ Plug-and-play robot2robot retargeting pipeline Whether you’re building humanoids or studying human motion, this toolkit saves you weeks of setup. Github: Thank you, Firas Al-Hafez for sharing this great work!

Ilir Aliu

23,197 次观看 • 1 年前