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.

1/ Manufacturing inspection often comes down to small visual differences that are easy to miss at scale. In this demo, HudsonGraeme walks through a full Sertn workflow: video upload → auto-labeling → model training → inference on copper-coloured thread sections.

Inference Labs

38,102 subscribers

13,816 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A student asked me to "nerd snipe" this gradient effect. At first I was quite puzzled 🤔 CSS? SVG? Shaders? A quick inspection revealed the secret! Basic demo and full lesson video in thread.

A student asked me to "nerd snipe" this gradient effect. At first I was quite puzzled 🤔 CSS? SVG? Shaders? A quick inspection revealed the secret! Basic demo and full lesson video in thread.

Carl 💥 Creative Coding Club

103,280 views • 11 months ago

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: 📰 Paper: 🎥 Demo: #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA

🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: 📰 Paper: 🎥 Demo: #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA

Yukang Chen

59,615 views • 3 months ago

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

NVIDIA AI

31,412 views • 1 month ago

We all run into it at some point: We are zooming in on a small area of our model, but Blender doesn't want to go any further. Well, fortunately there's 5 easy solutions for this, as shown in this video. #blender3d #blender #b3d

We all run into it at some point: We are zooming in on a small area of our model, but Blender doesn't want to go any further. Well, fortunately there's 5 easy solutions for this, as shown in this video. #blender3d #blender #b3d

Jan van den Hemel

24,231 views • 1 year ago

Here's my visual demo for everything I've been in up to 2024! I'm gonna start updating this yearly, I'm so thankful for everyone that gave me a shot :) Here's to a bajillion more✨ I can only upload 2 minutes here but the full post is up on YouTube!

Here's my visual demo for everything I've been in up to 2024! I'm gonna start updating this yearly, I'm so thankful for everyone that gave me a shot :) Here's to a bajillion more✨ I can only upload 2 minutes here but the full post is up on YouTube!

Jake Walters | Home Studio | Funny British Guy

22,514 views • 1 year ago

Important concept to understand as we head into in-season training and competition. Had to revive this one as we head into fall sports. Amazing video by Travis Dresch breaking down the “why” when it comes to training different performance qualities for athletes. The weight room is an educational setting. A 2 min demo can give student-athletes visual on why we do what we do. There’s not one right way to train, but smarter ways to train throughout the year. #BuildingStrongerHumans

Important concept to understand as we head into in-season training and competition. Had to revive this one as we head into fall sports. Amazing video by Travis Dresch breaking down the “why” when it comes to training different performance qualities for athletes. The weight room is an educational setting. A 2 min demo can give student-athletes visual on why we do what we do. There’s not one right way to train, but smarter ways to train throughout the year. #BuildingStrongerHumans

Darren Hansen

15,768 views • 1 year ago

In this clip, Caleb Lang walks through how hitters can use pre-AB routines to create clarity, confidence, and consistency in the box. From controlling breathing to locking in a simple plan, the focus is on training the mental and cognitive side of hitting — helping players slow the game down and compete pitch to pitch. This is a preview from the "Efficient Paths to Scoring Runs" full-length Barnstormers Clinic video, now available to ABCA members in the ABCA Video Library!. ABCA members can watch the full breakdown at Not a member yet? This is the type of game-ready, process-driven education that’s available year-round through ABCA membership!

In this clip, Caleb Lang walks through how hitters can use pre-AB routines to create clarity, confidence, and consistency in the box. From controlling breathing to locking in a simple plan, the focus is on training the mental and cognitive side of hitting — helping players slow the game down and compete pitch to pitch. This is a preview from the "Efficient Paths to Scoring Runs" full-length Barnstormers Clinic video, now available to ABCA members in the ABCA Video Library!. ABCA members can watch the full breakdown at Not a member yet? This is the type of game-ready, process-driven education that’s available year-round through ABCA membership!

ABCA

20,564 views • 8 months ago

Global media keep reporting “dozens dying over flour crumbs” in Gaza — always with “according to testimonies” in small print. Meanwhile, local restaurants are busy promoting themselves🍰☕️. Here’s a thread on one — they even made a full video showing how to find it. 1/🧵

Global media keep reporting “dozens dying over flour crumbs” in Gaza — always with “according to testimonies” in small print. Meanwhile, local restaurants are busy promoting themselves🍰☕️. Here’s a thread on one — they even made a full video showing how to find it. 1/🧵

GAZAWOOD - the PALLYWOOD saga

82,615 views • 1 year ago

I sat down with Silas Alberti, Head of Research Cognition, to chat about the intersection of RL and inference -- from training frontier coding models to running inference at scale. Watch till the end for bonus doggo! :o 0:00 — Intros 1:04 — What's hardest to get right in an RL run 3:39 — How Cognition started using Modal 4:03 — What to weigh when buying inference 4:58 — The latency/throughput Pareto frontier 7:14 — DFlash reveal (!!) 8:44 — Why faster runtime matters 9:56 — Memory-bound vs. compute-bound 10:57 — Tree-based speculation 14:20 — Hot take: RL and inference optimization converging 15:28 — Online training of the speculator 16:22 — "Auto inference" 17:27 — Agents competing on optimization problems 18:27 — What inference providers still get wrong

I sat down with Silas Alberti, Head of Research Cognition, to chat about the intersection of RL and inference -- from training frontier coding models to running inference at scale. Watch till the end for bonus doggo! :o 0:00 — Intros 1:04 — What's hardest to get right in an RL run 3:39 — How Cognition started using Modal 4:03 — What to weigh when buying inference 4:58 — The latency/throughput Pareto frontier 7:14 — DFlash reveal (!!) 8:44 — Why faster runtime matters 9:56 — Memory-bound vs. compute-bound 10:57 — Tree-based speculation 14:20 — Hot take: RL and inference optimization converging 15:28 — Online training of the speculator 16:22 — "Auto inference" 17:27 — Agents competing on optimization problems 18:27 — What inference providers still get wrong

gongy

80,477 views • 1 month ago

Journalist Vidya Senthamizhan made a documentary on sexual harassment in buses . It was in 2021 and I was also part of it . This was a asia ville and I am going to upload parts of the video in this thread. The video is in Tamil but there are English subtitles . Part 1

Journalist Vidya Senthamizhan made a documentary on sexual harassment in buses . It was in 2021 and I was also part of it . This was a asia ville and I am going to upload parts of the video in this thread. The video is in Tamil but there are English subtitles . Part 1

Shalin Maria Lawrence

19,651 views • 7 months ago

Epic pays up to 8% cashback in $XRP on every booking. Not a stablecoin, not points, $XRP sent directly to your wallet after every hotel and flight. A lot of people have asked why $XRP specifically. The answer comes down to who Epic was built for and where the value should actually go. Adrian Baschuk walks through the full reasoning in this video.

Epic pays up to 8% cashback in $XRP on every booking. Not a stablecoin, not points, $XRP sent directly to your wallet after every hotel and flight. A lot of people have asked why $XRP specifically. The answer comes down to who Epic was built for and where the value should actually go. Adrian Baschuk walks through the full reasoning in this video.

EPIC Travel

55,641 views • 1 month ago

We at Oprah Daily want to be a force in the movement that is flipping the script on the Big M. Half of the human population goes through this seismic hormonal shift, yet women are still fumbling through menopuase alone. That ends here. A THREAD:

We at Oprah Daily want to be a force in the movement that is flipping the script on the Big M. Half of the human population goes through this seismic hormonal shift, yet women are still fumbling through menopuase alone. That ends here. A THREAD:

Oprah Daily

23,804 views • 3 years ago

🧵 Climate misconception number 1. How can 0.042% carbon dioxide in the atmosphere have an effect on climate? This video explains how a small % compostion can have a big effect. Sources are in the thread. Let me know which misconception to cover next? #ClimateBrawl

🧵 Climate misconception number 1. How can 0.042% carbon dioxide in the atmosphere have an effect on climate? This video explains how a small % compostion can have a big effect. Sources are in the thread. Let me know which misconception to cover next? #ClimateBrawl

BONUS🌍

202,927 views • 2 years ago

We knew from day one that unlocking constellation-scale manufacturing would be more than just a hardware challenge. That's why we built Octopus — our proprietary operating system, developed in-house to handle the many complexities of rapidly scaling satellite manufacturing. Octopus provides an end-to-end source of truth, from first customer conversation to orbit, enabling streamlined traceability that ensures speed never comes at the expense of quality. Octopus is built on Palantir's Foundry and AIP platforms, which provide the underlying infrastructure to rapidly prototype and deploy custom applications across the entire company. By building Octopus on Palantir, we have unified scheduling, procurement, receiving, inspection, inventory management, and production into a single integrated workflow — enabling predictable and secure, constellation-scale production. Hear from Apex CEO, Ian Cinnamon, and the rest of the team on how Apex's partnership with Palantir is unlocking rate production at Factory One, and laying the foundation for the next generation of satellite manufacturing.

We knew from day one that unlocking constellation-scale manufacturing would be more than just a hardware challenge. That's why we built Octopus — our proprietary operating system, developed in-house to handle the many complexities of rapidly scaling satellite manufacturing. Octopus provides an end-to-end source of truth, from first customer conversation to orbit, enabling streamlined traceability that ensures speed never comes at the expense of quality. Octopus is built on Palantir's Foundry and AIP platforms, which provide the underlying infrastructure to rapidly prototype and deploy custom applications across the entire company. By building Octopus on Palantir, we have unified scheduling, procurement, receiving, inspection, inventory management, and production into a single integrated workflow — enabling predictable and secure, constellation-scale production. Hear from Apex CEO, Ian Cinnamon, and the rest of the team on how Apex's partnership with Palantir is unlocking rate production at Factory One, and laying the foundation for the next generation of satellite manufacturing.

Apex - Satellite Platforms 🛰

33,843 views • 6 months ago

We've released the code for LegoGPT. This autoregressive model generates physically stable and buildable designs from text prompts, by integrating physics laws and assembly constraints into LLM training and inference. This work is led by PhD students Ava Pun, Kangle Deng, Ruixuan Liu, and in collaboration with CMU faculty Changliu Liu and Deva Ramanan. LegoGPT is a small first step towards the ultimate goal of generative manufacturing of physical objects. Our implementation is limited to 20x20x20 dimensions, 21 object categories, and simple brick types, but we are working on scaling it up! Code: Website: Demo:

We've released the code for LegoGPT. This autoregressive model generates physically stable and buildable designs from text prompts, by integrating physics laws and assembly constraints into LLM training and inference. This work is led by PhD students Ava Pun, Kangle Deng, Ruixuan Liu, and in collaboration with CMU faculty Changliu Liu and Deva Ramanan. LegoGPT is a small first step towards the ultimate goal of generative manufacturing of physical objects. Our implementation is limited to 20x20x20 dimensions, 21 object categories, and simple brick types, but we are working on scaling it up! Code: Website: Demo:

Jun-Yan Zhu

38,730 views • 1 year ago

Lightchain AI – Decentralized Inference Demo 🍂🥧 + Blockchain Rewards In this video, we showcase how Lightchain AI’s decentralized inference engine (AIVM + PoI + Federated Learning) runs a real-world prompt “What is the best way to make pumpkin pie for thanksgiving dinner?” 💰 Blockchain Rewards in Action This demo doesn’t just show inference — it shows how inference providers are rewarded for their work. The provider that processed this prompt was automatically rewarded on the Lightchain testnet. 🍁 Why It Matters Unlike centralized AI, Lightchain AI distributes inference across a global network of participants. Nodes earn blockchain rewards for providing compute, ensuring a trustless, transparent, and economically sustainable ecosystem. With pay-to-prompt mechanics and DAO governance, Lightchain AI creates a fair AI economy for all. 🌐 Learn more at-

Lightchain AI – Decentralized Inference Demo 🍂🥧 + Blockchain Rewards In this video, we showcase how Lightchain AI’s decentralized inference engine (AIVM + PoI + Federated Learning) runs a real-world prompt “What is the best way to make pumpkin pie for thanksgiving dinner?” 💰 Blockchain Rewards in Action This demo doesn’t just show inference — it shows how inference providers are rewarded for their work. The provider that processed this prompt was automatically rewarded on the Lightchain testnet. 🍁 Why It Matters Unlike centralized AI, Lightchain AI distributes inference across a global network of participants. Nodes earn blockchain rewards for providing compute, ensuring a trustless, transparent, and economically sustainable ecosystem. With pay-to-prompt mechanics and DAO governance, Lightchain AI creates a fair AI economy for all. 🌐 Learn more at-

Lightchain AI

18,665 views • 1 year ago

Wandering through the corridors of a dream I never want to wake up from. POV: You took a wrong turn at the Milky Way and ended up in paradise🤯 If you Want to create a video like this full workflow link 👇 I Created this video using Midjourney V7 + Veo 3.1 on TapNow #tapnow #taptv #createinpublic

Wandering through the corridors of a dream I never want to wake up from. POV: You took a wrong turn at the Milky Way and ended up in paradise🤯 If you Want to create a video like this full workflow link 👇 I Created this video using Midjourney V7 + Veo 3.1 on TapNow #tapnow #taptv #createinpublic

Yaseen Khan Gul

83,681 views • 6 months ago