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。

Letting Michael keep improvising sounds expensive. At $0.003 per generated second, Vivix W1 at least makes the video part more manageable. That's why his switch from “pick two” to “pick three” lands: a real-time interactive video model needs to afford the next unscripted moment while generating quickly and maintaining... show more

Alamin

105,761 subscribers

41,013 次观看 • 5 天前 •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

$0.003 per second for video generation, without compromising on speed or visual quality? The supplied comparisons put Vivix W1 alongside leading models on visual quality. It also delivers eight seconds of video in roughly eight seconds. But the bigger story is that W1 is a real-time interactive video model. Every extra minute of interaction means more video to generate and pay for. Making generation this affordable could make interactive stories and live visuals practical to run, not just impressive demos. Live visuals are what I’m most curious about. Generating quickly is one thing; reacting at the right moment is what would make them feel live. Vivix.AI already offers real-time generation through the API; the browser playground currently produces finished clips. A closer look at what could power those live visuals 👇

$0.003 per second for video generation, without compromising on speed or visual quality? The supplied comparisons put Vivix W1 alongside leading models on visual quality. It also delivers eight seconds of video in roughly eight seconds. But the bigger story is that W1 is a real-time interactive video model. Every extra minute of interaction means more video to generate and pay for. Making generation this affordable could make interactive stories and live visuals practical to run, not just impressive demos. Live visuals are what I’m most curious about. Generating quickly is one thing; reacting at the right moment is what would make them feel live. Vivix.AI already offers real-time generation through the API; the browser playground currently produces finished clips. A closer look at what could power those live visuals 👇

Kalsoom (ghotai )

71,646 次观看 • 4 天前

I can already see the tree I'd ski into. If this perspective became interactive, I'd need cheap attempts more than a heroic opening shot. Vivix W1's $0.003/sec would make another eight generated seconds $0.024, with fast generation and comparable quality. That's a useful starting point for a real-time interactive video model you can actually spend time learning to use. The real-time capability is on its API; the run I'd like to try is still a possibility.

I can already see the tree I'd ski into. If this perspective became interactive, I'd need cheap attempts more than a heroic opening shot. Vivix W1's $0.003/sec would make another eight generated seconds $0.024, with fast generation and comparable quality. That's a useful starting point for a real-time interactive video model you can actually spend time learning to use. The real-time capability is on its API; the run I'd like to try is still a possibility.

Maria

24,201 次观看 • 4 天前

$0.003/sec changes the economics of running real-time AI video. I’ve been testing Vivix W1, and that number is hard to ignore. The comparison shows visual quality on par with the models alongside W1. About a second of generation time per second of footage, too. But W1 isn’t just another video generator. It’s built for real-time interactive video, where the model keeps generating as the experience moves forward. Every second of that experience adds to the generation bill. At $0.003/sec, you can actually start thinking about a story that keeps going as viewers make choices. Vivix.AI already supports real-time generation through the API. The browser playground currently uses offline generation, with real-time browser tools coming soon. Continuous video is one thing. Giving viewers meaningful control is another. If I change my mind halfway through a story, how much can it actually change with me? That’s the interesting challenge. The next plot twist could be yours 👇

$0.003/sec changes the economics of running real-time AI video. I’ve been testing Vivix W1, and that number is hard to ignore. The comparison shows visual quality on par with the models alongside W1. About a second of generation time per second of footage, too. But W1 isn’t just another video generator. It’s built for real-time interactive video, where the model keeps generating as the experience moves forward. Every second of that experience adds to the generation bill. At $0.003/sec, you can actually start thinking about a story that keeps going as viewers make choices. Vivix.AI already supports real-time generation through the API. The browser playground currently uses offline generation, with real-time browser tools coming soon. Continuous video is one thing. Giving viewers meaningful control is another. If I change my mind halfway through a story, how much can it actually change with me? That’s the interesting challenge. The next plot twist could be yours 👇

AI StackLab

222,340 次观看 • 5 天前

Same perfume concept. Four video models. The difference becomes obvious once the scene starts changing. Vivix W1 keeps the subject and product feeling coherent as the studio transitions into the storm. For me, that matters more than how dramatic the storm looks. An eight-second version costs $0.024 to generate. Waiting for it takes roughly eight seconds. This comparison only shows a finished clip. W1 is built for real-time interactive video, not just one-shot generation. Vivix.AI already offers that real-time capability through the API. At $0.003/sec, that also makes experimenting with interactive video workflows a lot more accessible. Letting a viewer influence how a scene unfolds would mean paying for generation throughout the interaction. Worth watching the comparison closely. The model behind the studio-to-storm transition 👇

Same perfume concept. Four video models. The difference becomes obvious once the scene starts changing. Vivix W1 keeps the subject and product feeling coherent as the studio transitions into the storm. For me, that matters more than how dramatic the storm looks. An eight-second version costs $0.024 to generate. Waiting for it takes roughly eight seconds. This comparison only shows a finished clip. W1 is built for real-time interactive video, not just one-shot generation. Vivix.AI already offers that real-time capability through the API. At $0.003/sec, that also makes experimenting with interactive video workflows a lot more accessible. Letting a viewer influence how a scene unfolds would mean paying for generation throughout the interaction. Worth watching the comparison closely. The model behind the studio-to-storm transition 👇

Liam | AI Tools & News

42,351 次观看 • 5 天前

AI video is hitting the same wall AI agents hit a year ago: The tech works. The economics don't. That's why Vivix.AI caught my attention. Their new real-time interactive video model, W1, generates video for just $0.003/sec while staying surprisingly fast and competitive on quality. To put that in perspective: At the supplied rates, an equal-length Seedance 2.5 clip costs about 77 times as much as a W1 clip. But the interesting part isn't cheaper clips. It's what happens when video becomes cheap enough to run continuously. Interactive stories. Live AI-generated experiences. Visuals that respond in real time. Those products only work if generation costs stay low. W1 still has room to improve on cinematic fidelity and complex scenes, but making real-time video economically viable feels like a much bigger milestone than most people realise. Here’s the W1 rate I’d use in a project estimate:

AI video is hitting the same wall AI agents hit a year ago: The tech works. The economics don't. That's why Vivix.AI caught my attention. Their new real-time interactive video model, W1, generates video for just $0.003/sec while staying surprisingly fast and competitive on quality. To put that in perspective: At the supplied rates, an equal-length Seedance 2.5 clip costs about 77 times as much as a W1 clip. But the interesting part isn't cheaper clips. It's what happens when video becomes cheap enough to run continuously. Interactive stories. Live AI-generated experiences. Visuals that respond in real time. Those products only work if generation costs stay low. W1 still has room to improve on cinematic fidelity and complex scenes, but making real-time video economically viable feels like a much bigger milestone than most people realise. Here’s the W1 rate I’d use in a project estimate:

Bishal Nandi

30,268 次观看 • 3 天前

An hour of live AI video generation now costs $10.80 At $0.003 a second, Vivix W1 generates a full minute for just 18 cents. That price matters because of what W1 is. It's a real-time interactive video model. Through the API, it keeps generating video while the experience is happening, and you can shape what comes next. With a normal clip generator, you pay once and you're done. Real-time interactive video keeps generating as you use it. Every second generated is another second you pay for. At higher per-second rates, that bill can grow quickly. It's hard to ship an interactive product when every user session costs a fortune. With W1, the math starts to look workable. And they didn't buy that price by cutting quality or speed. In Vivix’s supplied tests, eight-second videos averaged 7.7 seconds to generate from text and 8.4 seconds with one reference image. In the side-by-side comparisons, W1 holds its own against Seedance 2.5, Kling 3.0, and H3 Max on the same prompts. An exploding taxi, a skyline shot, a robot serving drinks on a plane. It's not perfect yet: • Cinematic fidelity still has gaps • Complex motion and dense scenes still need work • Full-scale training is still underway, so this is an early checkpoint How to try it: • Real-time generation is live through the API today • The browser playground does offline generation for now. Submit a prompt and you get a finished clip. Real-time browser tools are coming soon My take: I've seen a lot of interactive video demos that would cost a fortune to run in production. This looks priced for something you could actually ship. Once a minute of live video generation costs 18 cents, interactive stories, games, and characters could become an everyday medium instead of a tech demo. What I want to see next from Vivix.AI: better complex motion. Improve that and the use cases open up fast. Put your project’s runtime into the equation 👇

An hour of live AI video generation now costs $10.80 At $0.003 a second, Vivix W1 generates a full minute for just 18 cents. That price matters because of what W1 is. It's a real-time interactive video model. Through the API, it keeps generating video while the experience is happening, and you can shape what comes next. With a normal clip generator, you pay once and you're done. Real-time interactive video keeps generating as you use it. Every second generated is another second you pay for. At higher per-second rates, that bill can grow quickly. It's hard to ship an interactive product when every user session costs a fortune. With W1, the math starts to look workable. And they didn't buy that price by cutting quality or speed. In Vivix’s supplied tests, eight-second videos averaged 7.7 seconds to generate from text and 8.4 seconds with one reference image. In the side-by-side comparisons, W1 holds its own against Seedance 2.5, Kling 3.0, and H3 Max on the same prompts. An exploding taxi, a skyline shot, a robot serving drinks on a plane. It's not perfect yet: • Cinematic fidelity still has gaps • Complex motion and dense scenes still need work • Full-scale training is still underway, so this is an early checkpoint How to try it: • Real-time generation is live through the API today • The browser playground does offline generation for now. Submit a prompt and you get a finished clip. Real-time browser tools are coming soon My take: I've seen a lot of interactive video demos that would cost a fortune to run in production. This looks priced for something you could actually ship. Once a minute of live video generation costs 18 cents, interactive stories, games, and characters could become an everyday medium instead of a tech demo. What I want to see next from Vivix.AI: better complex motion. Improve that and the use cases open up fast. Put your project’s runtime into the equation 👇

Raja Chichulkar

18,899 次观看 • 5 天前

I guess this is why the Second Amendment exists. This video from the active shooter incident at the In-N-Out in Twin Falls, Idaho yesterday appears to show a civilian armed with a handgun engaging the gunman. Witnesses reported seeing a man with an AR-style rifle come out of the drive-thru area, and then a separate individual with a pistol began returning fire on him. The shooter is now confirmed dead by police, with three total fatalities and at least two injured. This is the kind of real-time response the right to keep and bear arms is meant to enable.

I guess this is why the Second Amendment exists. This video from the active shooter incident at the In-N-Out in Twin Falls, Idaho yesterday appears to show a civilian armed with a handgun engaging the gunman. Witnesses reported seeing a man with an AR-style rifle come out of the drive-thru area, and then a separate individual with a pistol began returning fire on him. The shooter is now confirmed dead by police, with three total fatalities and at least two injured. This is the kind of real-time response the right to keep and bear arms is meant to enable.

ChaosLensX

16,006 次观看 • 2 个月前

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

113,347 次观看 • 3 个月前

A CARNIVAL GAG LIKE THIS IS THREE TIMED EVENTS, NOT ONE Bank-a-ball booth, plush prizes hanging overhead. She throws from behind camera, the ball bounces off the board and misses. Right as it lands, a guy in a cap pops up from behind the stand trying to catch it. She laughs, fixes her skirt, leans down for the next ball. None of it happened - not the booth, not the throw, not the guy who popped up at exactly the wrong moment. - Three moving things have to land on the same beat The ball needs its own arc, bounce, and miss off the board. Her throw needs the weight shift and follow-through of an actual pitch, not a mimed one. And the guy behind the stand has to time his entire pop-up to the second the ball lands, or the joke reads as staged instead of caught. None of the three gets generated with the other two in mind by default - getting all three to agree on one beat is the actual trick. Landing three unrelated timings on the same beat, on command, is the same process the article below turns into a business - across five different characters, every time.

A CARNIVAL GAG LIKE THIS IS THREE TIMED EVENTS, NOT ONE Bank-a-ball booth, plush prizes hanging overhead. She throws from behind camera, the ball bounces off the board and misses. Right as it lands, a guy in a cap pops up from behind the stand trying to catch it. She laughs, fixes her skirt, leans down for the next ball. None of it happened - not the booth, not the throw, not the guy who popped up at exactly the wrong moment. - Three moving things have to land on the same beat The ball needs its own arc, bounce, and miss off the board. Her throw needs the weight shift and follow-through of an actual pitch, not a mimed one. And the guy behind the stand has to time his entire pop-up to the second the ball lands, or the joke reads as staged instead of caught. None of the three gets generated with the other two in mind by default - getting all three to agree on one beat is the actual trick. Landing three unrelated timings on the same beat, on command, is the same process the article below turns into a business - across five different characters, every time.

capONE 💎

131,978 次观看 • 1 个月前

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Akshay 🚀

31,249 次观看 • 8 个月前

$THIS IS F**KING GOLD he highlighted half a sentence. the other half is the whole answer. $700 TO $65,000+ that range sits in the same google snippet at 0:13. the highlight stops at $4,000 to $7,000 per million views. the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads a legal requirement, not a youtube preference so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hooks says $630/day. and to be fair: the setup works. the images render, the shorts export,the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.$

THIS IS F**KING GOLD he highlighted half a sentence. the other half is the whole answer. $700 TO $65,000+ that range sits in the same google snippet at 0:13. the highlight stops at $4,000 to $7,000 per million views. the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads a legal requirement, not a youtube preference so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hooks says $630/day. and to be fair: the setup works. the images render, the shorts export,the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.

Mayor.

363,468 次观看 • 1 个月前

$he highlighted half a sentence. the other half is the whole answer. "$500 TO $40,000+" that range sits in the same google snippet at 0:13. the highlight stops at "$2,000 to $5,000 per million views." the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads — a legal requirement, not a youtube preference — so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hook says $453/day. and to be fair: the setup works. the images render, the shorts export, the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.$

he highlighted half a sentence. the other half is the whole answer. "$500 TO $40,000+" that range sits in the same google snippet at 0:13. the highlight stops at "$2,000 to $5,000 per million views." the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads — a legal requirement, not a youtube preference — so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hook says $453/day. and to be fair: the setup works. the images render, the shorts export, the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.

riVeN

47,587 次观看 • 1 个月前

A routine anti-poaching patrol. A tiny calf spotted alone in the Tsavo bush. Two pilots watching from the air for nearly two hours, hoping his family would return. They never did. Today, Arthi turns two. In this video from the month of his rescue, he was still finding his feet at the Nursery – getting used to his Keepers, his new herd, and the safety of knowing where his next meal would come from. Now he's an easygoing, independent young bull who enjoys doing his own thing but appreciates the company of gentle friends. He prefers play-wrestling with Taroha and Olomunyak over rougher characters like Pardamat – and that calm, confident nature has made him a favourite among the Nursery herd. His rescue led to another life saved that day. Two for the price of one. Happy birthday, Arthi. Adopt Arthi:

A routine anti-poaching patrol. A tiny calf spotted alone in the Tsavo bush. Two pilots watching from the air for nearly two hours, hoping his family would return. They never did. Today, Arthi turns two. In this video from the month of his rescue, he was still finding his feet at the Nursery – getting used to his Keepers, his new herd, and the safety of knowing where his next meal would come from. Now he's an easygoing, independent young bull who enjoys doing his own thing but appreciates the company of gentle friends. He prefers play-wrestling with Taroha and Olomunyak over rougher characters like Pardamat – and that calm, confident nature has made him a favourite among the Nursery herd. His rescue led to another life saved that day. Two for the price of one. Happy birthday, Arthi. Adopt Arthi:

Sheldrick Wildlife Trust

13,570 次观看 • 2 个月前

This week is already so hot. 🔥 Massive release from Decart : Lucy 2.0 a World Editing Model running at 1080p, 30FPS in realtime. This is truly exciting, the era of real-time generative reality is here. We are moving from watching AI video to living inside AI video. A breakthrough model capable of transforming the visual world in real-time. Moving beyond offline rendering, Lucy 2.0 delivers high-fidelity 1080p video generation with near-zero latency. Lucy 2.0 literally "redraws" the entire world pixel-by-pixel, while you are watching it. e.g. If you want to be an anime character, it doesn't just put a mask on you. It turns your skin into anime skin, your hair into anime hair, and the lighting in your room into anime lighting. Lucy 2.0 is also trained to stop the generated video from slowly falling apart over time, so the same stream can run much longer without faces and details drifting. So why is this a "Massive Deal"? Traditional AI video-generation model takes a prompt, you wait 10–20 minutes, and the computer "bakes" a video for you. You couldn't touch it or change it while it was happening. But Lucy 2.0 works like a mirror. It happens in real-time (30 frames per second). There is no waiting. You move your hand, the AI character moves its hand instantly. The craziest part isn't the visuals; it's the physics. Usually, AI hallucinations are glitchy—hands merge into faces, walls melt. Lucy 2.0 understands how the world works without being told. It knows that if you take off a helmet, there is hair underneath. It knows that if you splash water, droplets fly. It learned "physics" just by watching millions of videos. The physical behavior you see emerges from learned visual dynamics, not from engineered geometry or explicit physics engines. Their official technical report explicitly states that the model does not use traditional 3D engines, depth maps, or wireframes. It is a "pure diffusion model."

This week is already so hot. 🔥 Massive release from Decart : Lucy 2.0 a World Editing Model running at 1080p, 30FPS in realtime. This is truly exciting, the era of real-time generative reality is here. We are moving from watching AI video to living inside AI video. A breakthrough model capable of transforming the visual world in real-time. Moving beyond offline rendering, Lucy 2.0 delivers high-fidelity 1080p video generation with near-zero latency. Lucy 2.0 literally "redraws" the entire world pixel-by-pixel, while you are watching it. e.g. If you want to be an anime character, it doesn't just put a mask on you. It turns your skin into anime skin, your hair into anime hair, and the lighting in your room into anime lighting. Lucy 2.0 is also trained to stop the generated video from slowly falling apart over time, so the same stream can run much longer without faces and details drifting. So why is this a "Massive Deal"? Traditional AI video-generation model takes a prompt, you wait 10–20 minutes, and the computer "bakes" a video for you. You couldn't touch it or change it while it was happening. But Lucy 2.0 works like a mirror. It happens in real-time (30 frames per second). There is no waiting. You move your hand, the AI character moves its hand instantly. The craziest part isn't the visuals; it's the physics. Usually, AI hallucinations are glitchy—hands merge into faces, walls melt. Lucy 2.0 understands how the world works without being told. It knows that if you take off a helmet, there is hair underneath. It knows that if you splash water, droplets fly. It learned "physics" just by watching millions of videos. The physical behavior you see emerges from learned visual dynamics, not from engineered geometry or explicit physics engines. Their official technical report explicitly states that the model does not use traditional 3D engines, depth maps, or wireframes. It is a "pure diffusion model."

Rohan Paul

12,761 次观看 • 8 个月前

Last week we introduced Kenji to the button that initiates a video call to an emergency contact. Because he already knows to push buttons, he only needed to learn that it was a paw push not a nose push, and the cue "FaceTime". Today he had his second training session and we moved the button into the living room where it will be used, and he immediately went and pushed it when cued. Then we started to add distance. We did a few runs from within the living room, then a few from the kitchen, and finally a few from the back porch. He did it every single time. Young dogs learn very quickly. We kept the session short and just did a few repetitions at the furthest distance. It's tempting to go further away or into a different room, but it's better to leave that for the next session. Overtraining can take the fun out of it for the dog. Yes, they need to get lots of repetitions in for a behavior to become precise and reliable, but we want to keep it enjoyable and not increase difficulty too quickly. If he's already done several repetitions from a distance and then we ask him to do it from a room further away, then we run the risk of him losing interest in the activity and becoming more interested in some of the distractions he passes along the way. Like his bone and a toy box. When training a new skill, the dog needs lots of wins. It's far better for us to end the session where we did, rather than move to the bedroom and have him decide to stop and check out his bone on his way to the button. In a day or so we will do another session with him doing it once from the living room, a couple of fast repetitions from the back porch with exciting rewards, and then increase the difficulty while he's highly motivated. The session after that we will probably hook it up and introduce the sounds that it makes. He's doing awesome at this. It's not surprising. We know that there's more in his giant noggin than just marshmallows. Even if he's still hoping that button let's him video chat with Pizza Hut. 🎥 Kenji being awesome #Rottweiler #PuppyTraining #KenjiChaos

Last week we introduced Kenji to the button that initiates a video call to an emergency contact. Because he already knows to push buttons, he only needed to learn that it was a paw push not a nose push, and the cue "FaceTime". Today he had his second training session and we moved the button into the living room where it will be used, and he immediately went and pushed it when cued. Then we started to add distance. We did a few runs from within the living room, then a few from the kitchen, and finally a few from the back porch. He did it every single time. Young dogs learn very quickly. We kept the session short and just did a few repetitions at the furthest distance. It's tempting to go further away or into a different room, but it's better to leave that for the next session. Overtraining can take the fun out of it for the dog. Yes, they need to get lots of repetitions in for a behavior to become precise and reliable, but we want to keep it enjoyable and not increase difficulty too quickly. If he's already done several repetitions from a distance and then we ask him to do it from a room further away, then we run the risk of him losing interest in the activity and becoming more interested in some of the distractions he passes along the way. Like his bone and a toy box. When training a new skill, the dog needs lots of wins. It's far better for us to end the session where we did, rather than move to the bedroom and have him decide to stop and check out his bone on his way to the button. In a day or so we will do another session with him doing it once from the living room, a couple of fast repetitions from the back porch with exciting rewards, and then increase the difficulty while he's highly motivated. The session after that we will probably hook it up and introduce the sounds that it makes. He's doing awesome at this. It's not surprising. We know that there's more in his giant noggin than just marshmallows. Even if he's still hoping that button let's him video chat with Pizza Hut. 🎥 Kenji being awesome #Rottweiler #PuppyTraining #KenjiChaos

Team Servicerottie🇨🇦🐕‍🦺🦽

10,160 次观看 • 1 个月前

This guy cracked the code on AI virtual influencers using real-time face filters and now D2C brands pay him $2,000 per UGC video. He got tired of watching D2C brands burn $4,000 on a single creator who takes 2 weeks to deliver one angle, so he built a setup that runs hyperrealistic AI girls in real-time from his own webcam, generating viral content without actresses, studios, or makeup artists. His monthly revenue hit $89,000 last month from a network of 7 AI personas across TikTok and Instagram, while the average UGC creator caps at $6K juggling 4 brand deals. Here is the exact breakdown: → The hardware is the moat, but most people butcher the setup in the first frame. You need the face mesh locked at 60fps with zero artifacting → Persona comes first, and if you mess this up nothing saves it. Name, backstory, voice tone, niche before a single clip is shot → Face selection is not random. You A/B test features (eye spacing, jawline, hair contrast with face-framing highlights) because some faces convert better in 9:16 → You are picking who your audience trusts, not who looks cool. That is your targeting baked into bone structure → Real-time physics run before the script, and this is what kills the uncanny valley that destroys watch time in 2 seconds → The filter has to survive the strap of a tank top, the texture of a knit cardigan, the hair flick. → Batching is the move 96 percent skip: one performance, multiple personas, three platforms. → The system pushes 12 pieces of content before lunch, while traditional brands test 2 creators per week and wonder why their CPAs are stuck at $94 The economics are stupid: each video costs him $4 in compute, sells for $1,500 to $3,000, and takes 14 minutes to produce. That is a 37,500 percent margin, while UGC agencies pay creators $400 to $800 per clip and net $200 after revisions. One supplement brand generated 14 variants with 7 personas in 4 hours and found a winner in 36 hours without flying a creator to LA. They were previously paying $1,200 per UGC video and burning $6,000 per week on content that did not scale. Now they spend $210 for 14 variants and their CPA dropped from $89 to $27. The avatars hold real products. Warm window light on the persona, cold neon on the operator. Mouth shapes sync to consonants, not just vowels. Just a webcam, a tracked face, and the discipline to move enough that the filter never has a chance to break.

Shade

136,231 次观看 • 4 个月前

TIMED DIALOGUE IN A NIGHTCLUB. THREE WALLS FALL AT ONCE. Nightclub sketch, cut in two halves. Black-and-white first - a couple making out on a couch, someone laughing off-camera. Then color reveals the setup: guy walks up with a drink, delivers a line, she gives him a one-sentence answer that changes the picture, he pauses, then kisses her anyway. None of them exist. It's fully generated, both halves. - What used to be four problems is now one clip Character consistency across a cut - same two faces in B&W and in color. Two-person dialogue with alternating lip sync - three separate English lines, all on time, all matching mouth shapes. Nightclub lighting - low light, saturated color wash, moving sources - was the last hard lighting environment for AI video to render without collapsing into noise. And a kiss - two faces contacting without merging into each other, which has been one of the persistent tells. Any one of these has been solvable for maybe six months. All four in one sketch was still a demo-reel problem in early 2026. - The B&W cut is doing two jobs The editing choice isn't style. It's engineering. Splitting a 15-second sketch into two 5-7 second clips means the model only has to hold consistency inside each segment, not across the whole thing. Monochrome also hides small differences between the two generations - if the girl's face is 3% off between the halves, B&W flattens the delta. Color grading in the second half does the reverse job. Two seams, both hidden by the aesthetic. - The comic beat is the actual craft Generating a kiss is one problem. Generating a kiss that lands as a punchline is a different one. The half-second where he pauses, processes, and decides not to care - that timing has to be prompted specifically. The default output of every current model is a rushed sequence with no beats. Deadpan comic delivery out of AI video means the operator wrote the prompt the way a screenwriter would - pauses, reactions, holds, all specified frame by frame. - What it costs Two 5-7 second clips at $3-5 each with in-model audio. Locked character references for both actors so the faces match across the cut. Prompt structured as a mini-script with beat notation. Realistically 40-60 rerolls to land the timing on all three spoken lines and the kiss. Under $200 in compute. A weekend from concept to publish-ready. - What this actually opens Short-form comedy has been the one segment of content nobody was making with AI video yet, because you can't fake comic timing when your output has drift and glitches. That barrier just came down. Which means every sketch account, every meme page, every stand-up clip factory now has a pipeline that doesn't require booking actors, renting a location, or getting a laugh out of a live crew. That's a real shift in a market that produces billions of views a month.

TIMED DIALOGUE IN A NIGHTCLUB. THREE WALLS FALL AT ONCE. Nightclub sketch, cut in two halves. Black-and-white first - a couple making out on a couch, someone laughing off-camera. Then color reveals the setup: guy walks up with a drink, delivers a line, she gives him a one-sentence answer that changes the picture, he pauses, then kisses her anyway. None of them exist. It's fully generated, both halves. - What used to be four problems is now one clip Character consistency across a cut - same two faces in B&W and in color. Two-person dialogue with alternating lip sync - three separate English lines, all on time, all matching mouth shapes. Nightclub lighting - low light, saturated color wash, moving sources - was the last hard lighting environment for AI video to render without collapsing into noise. And a kiss - two faces contacting without merging into each other, which has been one of the persistent tells. Any one of these has been solvable for maybe six months. All four in one sketch was still a demo-reel problem in early 2026. - The B&W cut is doing two jobs The editing choice isn't style. It's engineering. Splitting a 15-second sketch into two 5-7 second clips means the model only has to hold consistency inside each segment, not across the whole thing. Monochrome also hides small differences between the two generations - if the girl's face is 3% off between the halves, B&W flattens the delta. Color grading in the second half does the reverse job. Two seams, both hidden by the aesthetic. - The comic beat is the actual craft Generating a kiss is one problem. Generating a kiss that lands as a punchline is a different one. The half-second where he pauses, processes, and decides not to care - that timing has to be prompted specifically. The default output of every current model is a rushed sequence with no beats. Deadpan comic delivery out of AI video means the operator wrote the prompt the way a screenwriter would - pauses, reactions, holds, all specified frame by frame. - What it costs Two 5-7 second clips at $3-5 each with in-model audio. Locked character references for both actors so the faces match across the cut. Prompt structured as a mini-script with beat notation. Realistically 40-60 rerolls to land the timing on all three spoken lines and the kiss. Under $200 in compute. A weekend from concept to publish-ready. - What this actually opens Short-form comedy has been the one segment of content nobody was making with AI video yet, because you can't fake comic timing when your output has drift and glitches. That barrier just came down. Which means every sketch account, every meme page, every stand-up clip factory now has a pipeline that doesn't require booking actors, renting a location, or getting a laugh out of a live crew. That's a real shift in a market that produces billions of views a month.

capONE 💎

82,533 次观看 • 2 个月前

HydraFusion Explained. Part I: How does the Copilot engine know what to optimize for? Your prompt is evaluated across 4 dimensions: ➡ Does it require deep reasoning? (aka. reasoning depth) ➡ Is it a sophisticated problem? (aka. code generation complexity) ➡ Is it untangling a complicated mess? (aka. debugging difficulty) ➡ Is it dominated by tool-use? (aka. tool orchestration needs) Based on this evaluation, a HyDRA score is assigned to determine the capability profile your task needs the most and to establish a quality bar. Part II: How does it choose a model? Note: It doesn' t pick one model to handle the entire job e2e, (that's Auto mode). Instead, it selects 1 of 3 execution workflows and assigns the best model at different stages based on the HyDRA score: 1️⃣ Single ⚙️ How it works: A single model completes the task from start to finish. ⚖️ Rationale: The task comfortably meets the quality bar with one model. Multi-model orchestration would add latency and cost with no meaningful quality gain. 2️⃣ Cascade ⚙️ How it works: A lightweight, cost-efficient model generates the solution. This draft is evaluated against a quality gate and if it falls short of the quality bar, the entire task escalates to a stronger, frontier model. ⚖️ Rationale: Only bring in the big guns when there is concrete evidence that a lightweight model won't meet the quality threshold. 3️⃣ Critique ⚙️ How it works: A lightweight model drafts the initial code and tool interactions. An independent, read-only frontier model reviews that draft and provides feedback. The original lightweight model then performs any targeted revision(s) before the final response is sent to the user. ⚖️ Rationale: Writing code (output tokens) is expensive while reviewing code (input tokens) is cheap. Instead of incurring the cost of a powerhouse writing hundreds of lines from scratch, a cost-efficient model writes the first draft, and the frontier model just reviews it and points out fixes. HydraFusion is available in experimental preview on the GitHub Copilot CLI: /experimental on, /model and select Hydrafusion (Research Preview)

Julia Muiruri

13,000 次观看 • 1 个月前

Charlie meets Erika - They met at the office. Erika was introduced to Charlie at that time and they talked for a moment about a job. Then they were set to meet again. Charlie says when he DM’d her to Urgently meet up it was partially for an interview but “partially for something else”. Sounds like that meeting at the office had Charlie crushing on Erika. When they met up for dinner…… 15 MINUTES into it he knew he was going to date her. Not hours but 15 minutes into it. Then they went on a second date because he had to see her again immediately and then took her to Hawaii the NEXT day. Josh and Sarah was there. Interesting Candace because you said he only dated her as a rebound and when you met her you believed she would only be a girlfriend. And that Erika basically wore him down over time claiming to be a Godly woman. That’s not how it sounds coming from Charlie. Sounds to me at the first meeting at the office he liked her. He took her to HAWAII the week after meeting her for dinner. They had already been dating and already gone on vacation to Hawaii before you met her. Why would you think she was only going to be a girlfriend? I think you’re fibbing again Candace. I don’t think Charlie was using Erika to make anyone jealous. Besides that wouldn’t be a Christian thing to do and I don’t see Charlie being that way. You on the other hand…..were you trying to make Charlie jealous with George and getting engaged so fast? Just asking questions. Seems suspicious to me. Super sweet video of Charlie and Erika about their meeting. He looks so young.

Charlie meets Erika - They met at the office. Erika was introduced to Charlie at that time and they talked for a moment about a job. Then they were set to meet again. Charlie says when he DM’d her to Urgently meet up it was partially for an interview but “partially for something else”. Sounds like that meeting at the office had Charlie crushing on Erika. When they met up for dinner…… 15 MINUTES into it he knew he was going to date her. Not hours but 15 minutes into it. Then they went on a second date because he had to see her again immediately and then took her to Hawaii the NEXT day. Josh and Sarah was there. Interesting Candace because you said he only dated her as a rebound and when you met her you believed she would only be a girlfriend. And that Erika basically wore him down over time claiming to be a Godly woman. That’s not how it sounds coming from Charlie. Sounds to me at the first meeting at the office he liked her. He took her to HAWAII the week after meeting her for dinner. They had already been dating and already gone on vacation to Hawaii before you met her. Why would you think she was only going to be a girlfriend? I think you’re fibbing again Candace. I don’t think Charlie was using Erika to make anyone jealous. Besides that wouldn’t be a Christian thing to do and I don’t see Charlie being that way. You on the other hand…..were you trying to make Charlie jealous with George and getting engaged so fast? Just asking questions. Seems suspicious to me. Super sweet video of Charlie and Erika about their meeting. He looks so young.

Raven Grace - Operative #22/92

43,469 次观看 • 3 个月前

We just ran one of the largest robot models that exists today, all without a local GPU. And it’s running real-time at <50 ms overhead. Scaling laws are becoming real for physical AI. Perceptron’s Isaac 0.5 is one of the largest open-source models, sitting at 36B total parameters. Perceptron AI joins other frontier robotics labs like Dyna Robotics and Generalist in showing the need to massively scale pre-training data, from a 1000s to millions of hours of video. Specifically, they show that the more egocentric video the model is trained on, the less teleop data that it needs to achieve the same loss. At Dreamscale Labs (YC F26) (YC F26), we’ve noticed an important truth here: data and training compute do not just scale in isolation. The model sizes must increase too, and GPT-6 Astra has given a glimpse into what a trillion-parameter robotics model could do. We’re building to serve that future - one that is not constrained by the bottlenecks of on-board compute, but rather, allowing large models to run fast over the cloud. Reach out if you’re interested in our work.

We just ran one of the largest robot models that exists today, all without a local GPU. And it’s running real-time at <50 ms overhead. Scaling laws are becoming real for physical AI. Perceptron’s Isaac 0.5 is one of the largest open-source models, sitting at 36B total parameters. Perceptron AI joins other frontier robotics labs like Dyna Robotics and Generalist in showing the need to massively scale pre-training data, from a 1000s to millions of hours of video. Specifically, they show that the more egocentric video the model is trained on, the less teleop data that it needs to achieve the same loss. At Dreamscale Labs (YC F26) (YC F26), we’ve noticed an important truth here: data and training compute do not just scale in isolation. The model sizes must increase too, and GPT-6 Astra has given a glimpse into what a trillion-parameter robotics model could do. We’re building to serve that future - one that is not constrained by the bottlenecks of on-board compute, but rather, allowing large models to run fast over the cloud. Reach out if you’re interested in our work.

Chris Yoo

13,503 次观看 • 13 天前