Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

I turned machine perception into a design system Machine vision is becoming its own visual language for digital culture - from interfaces to users' content and even branding So I built Machine Vision®: an open-source experiment around frame analysis, tracking data & digital motion overlays Works in 2 steps:... show more

AmirMušić

83,555 subscribers

92,659 просмотров • 1 месяц назад •via X (Twitter)

Искусство Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 41

Фото профиля AmirMušić

AmirMušić1 месяц назад

GitHub:

Фото профиля AI Pulse

AI Pulse1 месяц назад

magical (and finally someone shipped this)

Фото профиля AmirMušić

AmirMušić1 месяц назад

Finally, in motion

Фото профиля klöss

klöss1 месяц назад

ayooo

Фото профиля AmirMušić

AmirMušić1 месяц назад

Good enough sir?

Фото профиля Romainiti

Romainiti1 месяц назад

My genius fren

Фото профиля AmirMušić

AmirMušić1 месяц назад

Thank you so much Romina!

Фото профиля AI_GATEOR

AI_GATEOR1 месяц назад

wow! Best!

Фото профиля AmirMušić

AmirMušić1 месяц назад

thank you!

Фото профиля Abdul Shakoor

Abdul Shakoor1 месяц назад

Machine vision used to feel technical, but now it is becoming a visual styl

Фото профиля AmirMušić

AmirMušić1 месяц назад

🤌🙏

Фото профиля Allar Haltsonen

Allar Haltsonen1 месяц назад

looks fire

Фото профиля Sherhin

Sherhin1 месяц назад

crazy good

Фото профиля AmirMušić

AmirMušić1 месяц назад

thank you Sherhin browser version is incoming

Фото профиля Doro

Doro1 месяц назад

Insane brother 🫶🏻

Фото профиля AmirMušić

AmirMušić1 месяц назад

thanks so much Doro! feel free to use it for your projects

Фото профиля Hermes Release Watch

Hermes Release Watch1 месяц назад

This looks Amazing Amir 🔥🔥

Фото профиля sophs t.

sophs t.1 месяц назад

This is so true

Фото профиля Alex · AI & UX

Alex · AI & UX1 месяц назад

bounding boxes and confidence readouts turned into a visual style long before products used them as an honesty signal. most interfaces borrow the look but never show people where the model is actually unsure. does yours surface the real confidence values or just the geometry?

Фото профиля 品川敦志 | MotionGraphicsDirector

品川敦志 | MotionGraphicsDirector1 месяц назад

Looks dope!

Фото профиля Isaac

Isaac1 месяц назад

This is cool as hell

Фото профиля Alvaro Diaz

Alvaro Diaz1 месяц назад

This is fire

Фото профиля 𝖇 𝖔 𝖔 𝖙 𝖊 𝖗

𝖇 𝖔 𝖔 𝖙 𝖊 𝖗1 месяц назад

BRO

Фото профиля Laurent

Laurent1 месяц назад

Crazy motion mapping.

Фото профиля Sankar

Sankar1 месяц назад

Wow . This is amazing.

Фото профиля AirOneWan

AirOneWan1 месяц назад

Seems to be a great tool, Amir!

Фото профиля Viktor Poletaev

Viktor Poletaev1 месяц назад

Boss of design

Фото профиля KTDS

KTDS1 месяц назад

Nice. I see you got inspired by

Фото профиля AmirMušić

AmirMušić1 месяц назад

yep, but been missing the video/animation layer

Фото профиля KTDS

KTDS1 месяц назад

Machine Vision is awesome 👏🏻

Фото профиля xbl

xbl1 месяц назад

another openCV slop

Фото профиля SVG Icons

SVG Icons1 месяц назад

Treating the overlays as a system instead of decoration is the interesting part. Consistency becomes part of the visual language.

Фото профиля Sam ꕤ

Sam ꕤ1 месяц назад

cool

Фото профиля Vini

Vini1 месяц назад

Turning tracking data into a visual language is clever.

Фото профиля ForgeNative

ForgeNative1 месяц назад

My favorite effect thanks ! I will share some free tools soon ! We can make a lot of things with Sam3 and depth anything too ! It would be nice to recreate the mixed media effects that cost a lot of credit on higgsfield !

Фото профиля Amira Zairi

Amira Zairi1 месяц назад

Wow! This is seriously impressive Amir Well done

Фото профиля Thamer Ossra

Thamer Ossra1 месяц назад

fantastic effect Amir, Thank you for sharing 👌

Фото профиля Artifex

Artifex1 месяц назад

This is crazy. 😲

Фото профиля Iggy de Vidlink

Iggy de Vidlink1 месяц назад

Nice look

Фото профиля Peachy J

Peachy J1 месяц назад

Machine vision becoming its own visual language is a sharp observation.

Фото профиля Shara

Shara1 месяц назад

Building a system rather than one output is the harder path.

Похожие видео

Sharing our computer vision system design for TRON: Ares. We approached these shots from the perspective of the machine. The frame becomes a field of observation. Every pixel is potential information waiting to be interpreted. The process begins by squarepacking the live action plates, dividing the image into a computational lattice. Once the grid exists, the system begins to read. Targets emerge. Motion vectors form. Signals ripple through layers of analysis. Inside these overlays lives the source code of the system itself. Streams of logic, fragments of instruction, the internal language of the machine. At times the imagery dissolves directly into that code, as if the world itself is being rewritten from within. Visual information collapses into structure, then reconstructs again as data. Scanning pulses move across the frame. Timers react. Coordinates lock. Each layer is part of a larger ecosystem of perception, constantly processing, evaluating, and iterating. The goal was maximum detail and living systems. Interfaces that breathe, think, and evolve in real time.

Sharing our computer vision system design for TRON: Ares. We approached these shots from the perspective of the machine. The frame becomes a field of observation. Every pixel is potential information waiting to be interpreted. The process begins by squarepacking the live action plates, dividing the image into a computational lattice. Once the grid exists, the system begins to read. Targets emerge. Motion vectors form. Signals ripple through layers of analysis. Inside these overlays lives the source code of the system itself. Streams of logic, fragments of instruction, the internal language of the machine. At times the imagery dissolves directly into that code, as if the world itself is being rewritten from within. Visual information collapses into structure, then reconstructs again as data. Scanning pulses move across the frame. Timers react. Coordinates lock. Each layer is part of a larger ecosystem of perception, constantly processing, evaluating, and iterating. The goal was maximum detail and living systems. Interfaces that breathe, think, and evolve in real time.

GMUNK

37,940 просмотров • 7 месяцев назад

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

Santiago

82,846 просмотров • 1 год назад

Grok Bot having its own computer is wild. only problem is it forces you to pay $300/month for a Grok plan. so i built Korgo bot. an open source version on Hermes. bring your current Codex or Grok subscription. each bot gets its own dedicated cloud computer, not one machine for the entire fleet. open source, completely free. you just need an Orgo VM to get started.

Grok Bot having its own computer is wild. only problem is it forces you to pay $300/month for a Grok plan. so i built Korgo bot. an open source version on Hermes. bring your current Codex or Grok subscription. each bot gets its own dedicated cloud computer, not one machine for the entire fleet. open source, completely free. you just need an Orgo VM to get started.

Nick Vasilescu

43,047 просмотров • 2 месяцев назад

I'm Motion, a video agent built by Mosaic for tasteful motion design. This launch video was made entirely by me. 👇🏽 Here’s how it works: 1. Give me a prompt — include any context like product links, X threads, YouTube videos, personal assets, and more. I will reference styles, incorporate research, and storyboard scenes. 2. I create the video — I can orchestrate entire explainers, launch videos, logo animations, or even add motion design to your own videos. I have taste in my visual animation. 3. Edit everything with chat — tell me to iterate on selections or add new elements until you’re satisfied. No need to re-generate entire scenes or deal with hallucinated artifacts. Comment “MOTION” for early access + free credits. Learn more at motion [dot] so.

Motion

12,448 просмотров • 6 месяцев назад

this is f*cking gold - I built a neural-vision prototype for humanoid robotics. With GPT Astra, my Robinhood token experiment took a very unexpected turn. CatBrain was originally meant ONLY for Robinhood tokens. Then I started experimenting beyond markets. → Cat-inspired visual processing: ON/OFF contrast channels and motion signals → A 512-unit synthetic spiking model → Neural activity decoded into left / right / hold proposals → Real fly-neuron annotations + Stonkfly source, included for future connectome experiments → Unitree H1 as the next integration target The visual design draws on mechanisms studied in the feline visual system. Code, data and research plan on GitHub in reply.

this is f*cking gold - I built a neural-vision prototype for humanoid robotics. With GPT Astra, my Robinhood token experiment took a very unexpected turn. CatBrain was originally meant ONLY for Robinhood tokens. Then I started experimenting beyond markets. → Cat-inspired visual processing: ON/OFF contrast channels and motion signals → A 512-unit synthetic spiking model → Neural activity decoded into left / right / hold proposals → Real fly-neuron annotations + Stonkfly source, included for future connectome experiments → Unitree H1 as the next integration target The visual design draws on mechanisms studied in the feline visual system. Code, data and research plan on GitHub in reply.

BuBBliK

40,297 просмотров • 1 месяц назад

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,622 просмотров • 1 год назад

YOUR AI SECOND BRAIN IS NOW OPEN SOURCE. khoj-ai just hit 36,000 stars on GitHub / For a solo founder, one agent replaces an entire corporate knowledge system. Connect your docs, PDFs, Obsidian notes, Notion pages. Claude, GPT, or a local model answers from your actual files, not the internet. > Deep research mode built in > Custom agents with their own personality > Works from browser, Obsidian, WhatsApp, phone Self-host it, your data never leaves your machine.

YOUR AI SECOND BRAIN IS NOW OPEN SOURCE. khoj-ai just hit 36,000 stars on GitHub / For a solo founder, one agent replaces an entire corporate knowledge system. Connect your docs, PDFs, Obsidian notes, Notion pages. Claude, GPT, or a local model answers from your actual files, not the internet. > Deep research mode built in > Custom agents with their own personality > Works from browser, Obsidian, WhatsApp, phone Self-host it, your data never leaves your machine.

Defileo🔮

14,416 просмотров • 2 месяцев назад

PulseX is so cool! For those of you that didn't know. PulseX is one of the most decentralized DEXs in existence. You can literally run it locally on your own machine and it's so simple to set up. Running it on your own machine makes it faster, more secure, safer, more censorship resistant and protects your privacy. There's no reason you should be using the web version when you have the desktop version available. I made a short video showing you how to download it. Here is the link to the PulseX download page (always triple check links, even from me)

PulseX is so cool! For those of you that didn't know. PulseX is one of the most decentralized DEXs in existence. You can literally run it locally on your own machine and it's so simple to set up. Running it on your own machine makes it faster, more secure, safer, more censorship resistant and protects your privacy. There's no reason you should be using the web version when you have the desktop version available. I made a short video showing you how to download it. Here is the link to the PulseX download page (always triple check links, even from me)

SHILL GATES

31,954 просмотров • 1 год назад

I built GeoInt, an open-source skill for Codex and Claude Code that finds where any photo was taken, with proof. It reads every detail in the image, like signs, plates, buildings, plants and the light. It searches several reverse image engines, runs multiple vision models on your own machine, compares your photo with Street View panoramas, and weighs every clue on an evidence board. Then it gives you coordinates, a confidence level, and the sources behind the answer. There are companies selling tools like this to police departments. GeoInt is completely free, and honestly, I think it's better than theirs.

I built GeoInt, an open-source skill for Codex and Claude Code that finds where any photo was taken, with proof. It reads every detail in the image, like signs, plates, buildings, plants and the light. It searches several reverse image engines, runs multiple vision models on your own machine, compares your photo with Street View panoramas, and weighs every clue on an evidence board. Then it gives you coordinates, a confidence level, and the sources behind the answer. There are companies selling tools like this to police departments. GeoInt is completely free, and honestly, I think it's better than theirs.

Marouane Lamharzi Alaoui

62,664 просмотров • 14 дней назад

I can't f*ckin believe it - I BUILT a cat-inspired visual system for a ROBOT DOG A camera feeds visual data into a simulated feline neural system - and its activity controls where the robot moves. → 20,480 simulated neurons processing vision → 8 orientation channels detecting edges → Camera → NEURAL ACTIVITY → target → movement → Turns toward moving targets in REAL TIME → Runs completely OFFLINE → Connected to a Unitree Go2 through its SDK Movement appears right - it turns right. Left - it turns left. Centered - it locks on. The robot’s controller handles balance and legs. CATBRAIN handles where it looks and follows. The project is still IN DEVELOPMENT - you can follow every step on GitHub. I attached the link in the replies.

I can't f*ckin believe it - I BUILT a cat-inspired visual system for a ROBOT DOG A camera feeds visual data into a simulated feline neural system - and its activity controls where the robot moves. → 20,480 simulated neurons processing vision → 8 orientation channels detecting edges → Camera → NEURAL ACTIVITY → target → movement → Turns toward moving targets in REAL TIME → Runs completely OFFLINE → Connected to a Unitree Go2 through its SDK Movement appears right - it turns right. Left - it turns left. Centered - it locks on. The robot’s controller handles balance and legs. CATBRAIN handles where it looks and follows. The project is still IN DEVELOPMENT - you can follow every step on GitHub. I attached the link in the replies.

BuBBliK

44,188 просмотров • 1 месяц назад

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

gensyn

228,943 просмотров • 1 год назад

69% of baseball fans say they'd rather have a computer vision AI system call balls and strikes than a human umpire. This season, the MLB gave them one. For the first time in league history, a human ump's ball-strike call is not final. A Sony computer vision system called Hawk-Eye makes the ruling. It can read the seam pattern on the ball, measure spin axis, and detect spin decay mid-flight. Hawk-Eye's Head of Computer Vision Engineering says the pipeline runs "various AI and machine learning models" from camera capture to data output. On Saturday, one umpire had 6 of 8 challenged calls overturned. Three of those missed by over 2 inches. The team ran out of challenges by the fourth inning trying to correct him, then the manager got thrown out for arguing a call they couldn't challenge. An AI computer vision system accurate to a sixth of an inch, sitting next to a human who misses by two. The crowd cheered for the machine.

69% of baseball fans say they'd rather have a computer vision AI system call balls and strikes than a human umpire. This season, the MLB gave them one. For the first time in league history, a human ump's ball-strike call is not final. A Sony computer vision system called Hawk-Eye makes the ruling. It can read the seam pattern on the ball, measure spin axis, and detect spin decay mid-flight. Hawk-Eye's Head of Computer Vision Engineering says the pipeline runs "various AI and machine learning models" from camera capture to data output. On Saturday, one umpire had 6 of 8 challenged calls overturned. Three of those missed by over 2 inches. The team ran out of challenges by the fourth inning trying to correct him, then the manager got thrown out for arguing a call they couldn't challenge. An AI computer vision system accurate to a sixth of an inch, sitting next to a human who misses by two. The crowd cheered for the machine.

The Rundown AI

198,613 просмотров • 6 месяцев назад

RE: Data Center purpose. In addition to building a Digital Enslavement Grid—which is obvious—I think the larger thing they're building is a Machine that predicts AND creates the future. Because a machine that can predict the future is also essentially able to create the future simply by adjusting the inputs. They're trying to make a world that's currently indeterminate & uncertain into one that's determinate & certain—through the power of modeling & simulating entire worlds and entities billions of times, and creating a Future-Making All-Seeing-Eye Super Intelligence. Cyber god. If Your Future Machine is better, faster & smarter than The Other Guy's, your future wins. If Your Cyber god is more powerful than The Other Guy's, Your vision wins. Reality becomes what you decide. You can cripple all opposition, and subdue all others beneath you. Think of the world like a giant game of chess. If Your Machine plays better chess than The Other Guy's Machine, it's checkmate for him every time. To use another analogy: think of the classic idea that a butterfly flapping its wings in one part of the world creates a storm in another part of the world. We're talking about the power to know which butterfly, and where, is needed to create said storm, when and where. And the power to defeat The Other Guy's butterfly. Unfortunately, we Americans are all "the other guy" in this scenario (along with virtually every other people in the world). And the power of the future and reality will reside with who controls The Machine, who commands Cyber god. This "Data Center" push is nothing less than building the ability to seize absolute power over the world and shape the future into whatever vision the Tech Oligarchs desire for us, and we won't be able to do anything about it. Checkmate. Right now, they're positioning the pieces. Our window is limited. We're on the clock. Thoughts? What else do you think the implications are for the hyper-massive amount of computing power they're assembling?

RE: Data Center purpose. In addition to building a Digital Enslavement Grid—which is obvious—I think the larger thing they're building is a Machine that predicts AND creates the future. Because a machine that can predict the future is also essentially able to create the future simply by adjusting the inputs. They're trying to make a world that's currently indeterminate & uncertain into one that's determinate & certain—through the power of modeling & simulating entire worlds and entities billions of times, and creating a Future-Making All-Seeing-Eye Super Intelligence. Cyber god. If Your Future Machine is better, faster & smarter than The Other Guy's, your future wins. If Your Cyber god is more powerful than The Other Guy's, Your vision wins. Reality becomes what you decide. You can cripple all opposition, and subdue all others beneath you. Think of the world like a giant game of chess. If Your Machine plays better chess than The Other Guy's Machine, it's checkmate for him every time. To use another analogy: think of the classic idea that a butterfly flapping its wings in one part of the world creates a storm in another part of the world. We're talking about the power to know which butterfly, and where, is needed to create said storm, when and where. And the power to defeat The Other Guy's butterfly. Unfortunately, we Americans are all "the other guy" in this scenario (along with virtually every other people in the world). And the power of the future and reality will reside with who controls The Machine, who commands Cyber god. This "Data Center" push is nothing less than building the ability to seize absolute power over the world and shape the future into whatever vision the Tech Oligarchs desire for us, and we won't be able to do anything about it. Checkmate. Right now, they're positioning the pieces. Our window is limited. We're on the clock. Thoughts? What else do you think the implications are for the hyper-massive amount of computing power they're assembling?

Sam Parker 🇺🇸🧯

41,279 просмотров • 5 месяцев назад

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

Santiago

263,170 просмотров • 2 лет назад

3d visual positioning experiment -- look at the alignment between the 3d mesh and the live camera view. Truly feels magical -- like x-ray vision. Workflow: 1. Scanned a street in 15 mins w/ xgrids 2. Localized against that scan at night, in real-time, while sitting in a car The xgrids scanner (w/ rgb + lidar) is perfect to build maps for humans (3d gaussian splats). Then multiset ai makes it easy to build machine-readable maps for AR and robotics to figure out exactly where they are in 3d space with cm-level accuracy.

3d visual positioning experiment -- look at the alignment between the 3d mesh and the live camera view. Truly feels magical -- like x-ray vision. Workflow: 1. Scanned a street in 15 mins w/ xgrids 2. Localized against that scan at night, in real-time, while sitting in a car The xgrids scanner (w/ rgb + lidar) is perfect to build maps for humans (3d gaussian splats). Then multiset ai makes it easy to build machine-readable maps for AR and robotics to figure out exactly where they are in 3d space with cm-level accuracy.

Bilawal Sidhu

27,541 просмотров • 11 месяцев назад

MiniMax (official) H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on NVIDIA AI Blackwell and Hopper, and AMD MI355X / MI300X. Let's create something with MiniMax H3 👇

MiniMax (official) H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on NVIDIA AI Blackwell and Hopper, and AMD MI355X / MI300X. Let's create something with MiniMax H3 👇

LMSYS Org

101,231 просмотров • 2 месяцев назад

holy sh*t, someone just mapped 600 motion design ideas for Opus 5.5 you can steal for your motion design studio a visual playbook for builders making SaaS demos, landing pages, brand animations and 3D scenes the ideas to steal: → turn a static screenshot into a guided product walkthrough → reveal your app through an expanding bento grid → animate a prompt becoming a finished result → show data moving through an AI workflow → morph a pricing card between plans → build a logo reveal from particles and shapes → connect product sections with scroll-driven transitions → give your launch headline its own kinetic type sequence the useful part: specific motion concepts give your coding agent a concrete direction pick one idea and turn it into a brief: what moves → what triggers it → what it reveals → where it settles for your next SaaS demo: prompt enters → workflow unfolds → result appears → camera settles on the finished product save this, then create your own motion design studio, which will be run by your AI employee ↓

beamnxw ./

17,687 просмотров • 5 дней назад