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

🚨BREAKING NEWS🚨 Adobe just activated GOD MODE for AI creation. ⚡️ Firefly Boards lets you try all the top AI models in one place: Firefly 5, Runway, Veo, FLUX, Gemini’s Nano Banana… And until December 1st, everything is 100% unlimited — even video models in Relax mode 🎬 I’ve... show more

Pierrick Chevallier | IA

52,277 subscribers

71,040 просмотров • 10 месяцев назад •via X (Twitter)

Новости и политика Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

Umesh

19,281 просмотров • 8 месяцев назад

🚨 JUST IN: THIS FREE TOOL JUST REPLACED FOUR AI IMAGE AND VIDEO SUBSCRIPTIONS AT ONCE. Midjourney. Krea. Higgsfield. Openart. One repo. 200+ models. Zero dollars a month. Here is what it actually does. It is a full image and video studio that runs in your browser or as a desktop app. Text to image, image to image, text to video, image to video, lip sync, cinema mode with real camera controls. All of it. 4,500 people already starred this. What you get for free: → 50+ image models including Flux, Midjourney v7, Ideogram, GPT-4o, Seedream → 60+ video models including Kling, Sora, Veo, Runway, Wan, Hailuo → lip sync studio with 9 dedicated models. upload a portrait and audio and it talks → cinema studio with real camera controls. lens, focal length, aperture, film stock → feed up to 14 reference images into one generation → self-hosted. your data never leaves your machine The crazy part is there is also a hosted version that needs zero setup. Just open the link and start generating. Now the math. Midjourney Standard: $30/month Krea AI Pro: $30/month Higgsfield Plus: $49/month Openart AI: $15/month That is $124 a month. $1,488 a year. This repo does everything all four do. With more models than any of them. For free. Forever. No subscription. No vendor lock-in. MIT licensed. Download it in one click on Mac or Windows. Someone should have told me about this sooner. I feel like an idiot. ( save this )

🚨 JUST IN: THIS FREE TOOL JUST REPLACED FOUR AI IMAGE AND VIDEO SUBSCRIPTIONS AT ONCE. Midjourney. Krea. Higgsfield. Openart. One repo. 200+ models. Zero dollars a month. Here is what it actually does. It is a full image and video studio that runs in your browser or as a desktop app. Text to image, image to image, text to video, image to video, lip sync, cinema mode with real camera controls. All of it. 4,500 people already starred this. What you get for free: → 50+ image models including Flux, Midjourney v7, Ideogram, GPT-4o, Seedream → 60+ video models including Kling, Sora, Veo, Runway, Wan, Hailuo → lip sync studio with 9 dedicated models. upload a portrait and audio and it talks → cinema studio with real camera controls. lens, focal length, aperture, film stock → feed up to 14 reference images into one generation → self-hosted. your data never leaves your machine The crazy part is there is also a hosted version that needs zero setup. Just open the link and start generating. Now the math. Midjourney Standard: $30/month Krea AI Pro: $30/month Higgsfield Plus: $49/month Openart AI: $15/month That is $124 a month. $1,488 a year. This repo does everything all four do. With more models than any of them. For free. Forever. No subscription. No vendor lock-in. MIT licensed. Download it in one click on Mac or Windows. Someone should have told me about this sooner. I feel like an idiot. ( save this )

Kanika

14,769 просмотров • 4 месяцев назад

Google Nano Banana 🍌 is crazy good at static ads... But it only generates one image at a time. This n8n AI Agent helps you generate 1000s of winning ad variations in minutes, fully automated. → Built with the latest Nano Banana image model → Creates static ad images in bulk → Upload product reference image via n8n form → OpenAI Vision analyzes your product automatically → AI Agent generates custom image prompts (you choose how many) → Nano Banana creates static ad images on demand → Images auto-stored in Box. com for instant access You can request 50, 100, or even 1000 ad variations with one upload. Just specify the number in the form → AI does everything else. Built 100% in n8n. Zero manual work after setup. Want access to the template? → Like this post → Comment "ADS" And I'll send it right over.

Google Nano Banana 🍌 is crazy good at static ads... But it only generates one image at a time. This n8n AI Agent helps you generate 1000s of winning ad variations in minutes, fully automated. → Built with the latest Nano Banana image model → Creates static ad images in bulk → Upload product reference image via n8n form → OpenAI Vision analyzes your product automatically → AI Agent generates custom image prompts (you choose how many) → Nano Banana creates static ad images on demand → Images auto-stored in Box. com for instant access You can request 50, 100, or even 1000 ad variations with one upload. Just specify the number in the form → AI does everything else. Built 100% in n8n. Zero manual work after setup. Want access to the template? → Like this post → Comment "ADS" And I'll send it right over.

Mike Futia

209,875 просмотров • 1 год назад

✨ Every time the video models get better, the try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shoot

✨ Every time the video models get better, the try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shoot

@levelsio

334,317 просмотров • 1 год назад

☀️Very proud of the team for training 5.6! A few of my highlights: - Great front-end aesthetics. E.g., I asked Sol to make a new blog for 5.6 with a celestial theme. - Much better CUA - Can work for much longer and is less lazy But it's not all great: - The writing quality has improved, but it's still bad in artifacts - Too many options with models/reasoning/fast mode/Cerebras/multi-agent We'll fix the above. What else should we improve? PS: belated post as there are so many other good models to train.

☀️Very proud of the team for training 5.6! A few of my highlights: - Great front-end aesthetics. E.g., I asked Sol to make a new blog for 5.6 with a celestial theme. - Much better CUA - Can work for much longer and is less lazy But it's not all great: - The writing quality has improved, but it's still bad in artifacts - Too many options with models/reasoning/fast mode/Cerebras/multi-agent We'll fix the above. What else should we improve? PS: belated post as there are so many other good models to train.

Yann Dubois

37,058 просмотров • 2 месяцев назад

Google Nano Banana Pro 🍌 is crazy good at static ads... But it only generates one image at a time. This n8n AI Agent generates 100s of ad variations in minutes, fully automated. All inside n8n + Nano Banana Pro. Perfect for DTC brands & agencies who need massive creative volume to test and beat ad fatigue. Let's be honest: Manual ad creation takes forever. You're generating one image at a time, tweaking prompts, downloading files, trying different angles. And by the time you have enough variations to test, you've wasted hours. This n8n automation solves it: → Upload ONE product reference image via n8n form → OpenAI Vision analyzes your product automatically → AI generates custom image prompts (you choose quantity: 50, 100, 1000+) → Nano Banana Pro creates all variations in parallel → 4K studio-quality output with perfect text rendering → Images auto-stored in Box for instant access No manual prompting. No one-by-one generation. No wasted hours. What you get: → Hundreds of ad variations from one upload → Different angles, backgrounds, compositions automatically → 4K resolution with perfect text adherence → Production-ready static ads for testing at scale Built 100% in n8n. Want the complete n8n template? > Comment "NANO" > Like this post And I'll send it over (must be following so I can DM)

Google Nano Banana Pro 🍌 is crazy good at static ads... But it only generates one image at a time. This n8n AI Agent generates 100s of ad variations in minutes, fully automated. All inside n8n + Nano Banana Pro. Perfect for DTC brands & agencies who need massive creative volume to test and beat ad fatigue. Let's be honest: Manual ad creation takes forever. You're generating one image at a time, tweaking prompts, downloading files, trying different angles. And by the time you have enough variations to test, you've wasted hours. This n8n automation solves it: → Upload ONE product reference image via n8n form → OpenAI Vision analyzes your product automatically → AI generates custom image prompts (you choose quantity: 50, 100, 1000+) → Nano Banana Pro creates all variations in parallel → 4K studio-quality output with perfect text rendering → Images auto-stored in Box for instant access No manual prompting. No one-by-one generation. No wasted hours. What you get: → Hundreds of ad variations from one upload → Different angles, backgrounds, compositions automatically → 4K resolution with perfect text adherence → Production-ready static ads for testing at scale Built 100% in n8n. Want the complete n8n template? > Comment "NANO" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

183,551 просмотров • 9 месяцев назад

A 27-year-old guy from China made $150,000 using AI simply by automating content creation for models It all started with a common issue agencies face: models can't shoot enough content to scale. The strategy turned out to be ridiculously simple: 1) Upload a single photo of a girl. 2) Pick a motion or dance template from the library. 3) The AI generates a realistic video for Reels, TikTok, and Shorts in seconds. By leveraging this setup, he automated mass posting, publishing hundreds of videos daily without needing real models. The system pulls in millions of free organic views, driving traffic directly through profile links to paid subscriptions, OnlyFans, and affiliate offers. AI tools are completely solving the content shortage problem, allowing solopreneurs to run multi-million-dollar virtual agencies on their own. Bookmark this

Ridark

41,712 просмотров • 1 месяц назад

SOMEONE GOT TIRED OF PAYING HIGGSFIELD AI'S SUBSCRIPTION SO HE REBUILT THE WHOLE THING AND OPEN-SOURCED IT 200+ models. text-to-image, image-to-image, text-to-video, image-to-video all in one interface you configure a virtual camera in the Cinema Studio. pick the body, the lens, the focal length, the aperture and it writes the optimized cinematic prompt for you. completely in the background you never touch the camera keywords. you just set up the shot like a real cinematographer would Kling v3, Sora 2, Veo 3, Flux Dev, Midjourney v7, GPT-4o, Seedream 5.0, Runway Gen-3 all in there self-hosted. MIT licensed. runs on your machine. your data stays local the only thing you pay for is the model API calls themselves someone built this so you never have to pay Higgsfield AI again

SOMEONE GOT TIRED OF PAYING HIGGSFIELD AI'S SUBSCRIPTION SO HE REBUILT THE WHOLE THING AND OPEN-SOURCED IT 200+ models. text-to-image, image-to-image, text-to-video, image-to-video all in one interface you configure a virtual camera in the Cinema Studio. pick the body, the lens, the focal length, the aperture and it writes the optimized cinematic prompt for you. completely in the background you never touch the camera keywords. you just set up the shot like a real cinematographer would Kling v3, Sora 2, Veo 3, Flux Dev, Midjourney v7, GPT-4o, Seedream 5.0, Runway Gen-3 all in there self-hosted. MIT licensed. runs on your machine. your data stays local the only thing you pay for is the model API calls themselves someone built this so you never have to pay Higgsfield AI again

Rimsha Bhardwaj

101,371 просмотров • 5 месяцев назад

Nano Banana + n8n is legitimately insane 🤯 Google's Nano Banana creates studio-quality static ads. But manually generating variations one-by-one takes forever. This n8n automation generates 1,000+ ad variations in minutes. Fully automated. Perfect for DTC brands & media buyers who need fresh creative for testing without hiring designers. Here's the problem: You need 50+ ad variations to test angles, but Nano Banana only outputs one image at a time. Manually uploading and tweaking prompts for each variation kills hours. This n8n automation solves it: → Upload ONE product image via n8n form → OpenAI Vision analyzes your product automatically → AI generates custom image prompts (you choose quantity: 50, 100, 1000+) → Nano Banana creates static ad images in bulk → All images auto-stored in Box for instant access No manual prompting. No designer bottlenecks. No waiting on agencies. What you get: → Hundreds of unique ad variations from one upload → Different angles, backgrounds, compositions → Production-ready static ads → Perfect for testing creative on Meta/TikTok Built 100% in n8n. Want the complete n8n template? > Comment "BANANA" > Like this post And I'll send it over (must be following so I can DM)

Nano Banana + n8n is legitimately insane 🤯 Google's Nano Banana creates studio-quality static ads. But manually generating variations one-by-one takes forever. This n8n automation generates 1,000+ ad variations in minutes. Fully automated. Perfect for DTC brands & media buyers who need fresh creative for testing without hiring designers. Here's the problem: You need 50+ ad variations to test angles, but Nano Banana only outputs one image at a time. Manually uploading and tweaking prompts for each variation kills hours. This n8n automation solves it: → Upload ONE product image via n8n form → OpenAI Vision analyzes your product automatically → AI generates custom image prompts (you choose quantity: 50, 100, 1000+) → Nano Banana creates static ad images in bulk → All images auto-stored in Box for instant access No manual prompting. No designer bottlenecks. No waiting on agencies. What you get: → Hundreds of unique ad variations from one upload → Different angles, backgrounds, compositions → Production-ready static ads → Perfect for testing creative on Meta/TikTok Built 100% in n8n. Want the complete n8n template? > Comment "BANANA" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

300,618 просмотров • 10 месяцев назад

This tool is literally Higgsfield AI but FREE for good. It's called Wan2GP. A full AI video studio built specifically for people without expensive hardware. Runs on as little as 6GB of VRAM, even old RTX 10-series cards and 8GB laptops. Everything stays on your machine, no uploads, no caps, no watermarks. What you get in one app: • Text-to-video and image-to-video generation • The best open models built in: Wan 2.2, LTX-2, Hunyuan Video, Flux • A full browser interface with a queue system • LoRA support to customize any model • Mask editor and prompt enhancer included A 5-second clip generates in minutes on a mid-range gaming rig. No subscription, ever. 100% Free. Open Source.

This tool is literally Higgsfield AI but FREE for good. It's called Wan2GP. A full AI video studio built specifically for people without expensive hardware. Runs on as little as 6GB of VRAM, even old RTX 10-series cards and 8GB laptops. Everything stays on your machine, no uploads, no caps, no watermarks. What you get in one app: • Text-to-video and image-to-video generation • The best open models built in: Wan 2.2, LTX-2, Hunyuan Video, Flux • A full browser interface with a queue system • LoRA support to customize any model • Mask editor and prompt enhancer included A 5-second clip generates in minutes on a mid-range gaming rig. No subscription, ever. 100% Free. Open Source.

Simplifying AI

179,307 просмотров • 1 месяц назад

✨ I've brought back from the dead It was my first visual AI project in 2022, and it's this project that generated random ArchDaily-style architecture designs that made me realize AI image models could do interior design That led me to make which then led me to finetune my first interior design model which then for fun I uploaded my own photos too, which led me to make and then pivoted that in to So this project has a special place for me It was still alive but wasn't generating new designs anymore because it ran on Stable Diffusion 1.5 which was outdated and everything stopped working about a year ago I've now migrated it to its own Hetzner VPS now, which means I can run Claude Code on the server with it, and cleaned it up and upgraded it to the latest AI image models (including Nano Banana Pro) It now generates about 12 new designs every day again, and you can up or downvote the ones you like or don't like!

✨ I've brought back from the dead It was my first visual AI project in 2022, and it's this project that generated random ArchDaily-style architecture designs that made me realize AI image models could do interior design That led me to make which then led me to finetune my first interior design model which then for fun I uploaded my own photos too, which led me to make and then pivoted that in to So this project has a special place for me It was still alive but wasn't generating new designs anymore because it ran on Stable Diffusion 1.5 which was outdated and everything stopped working about a year ago I've now migrated it to its own Hetzner VPS now, which means I can run Claude Code on the server with it, and cleaned it up and upgraded it to the latest AI image models (including Nano Banana Pro) It now generates about 12 new designs every day again, and you can up or downvote the ones you like or don't like!

@levelsio

204,387 просмотров • 5 месяцев назад

Black Forest Labs just announced FLUX 3: a unified multimodal model for image, video, audio and action prediction. Founded in Freiburg, Germany, one of the few globally significant European companies in the AI sector. The current release is gated early access, not open source. But if FLUX 3 Dev actually ships with usable open weights, this could become one of the most important open-model releases in generative video yet. Especially after the Chinese Minimax H3 release. BFL claims, based on preliminary internal comparisons, that FLUX 3 outperformed models such as Runway Gen-4.5, Luma Ray 3.2, Kling 3 Pro, and Seedance 2.0. However, these figures stem from the early-access phase and do not constitute independent validation. Be that as it may, it's great to see the quality that today's video models can produce at affordable prices. Something that would have been unthinkable a year ago. Really cool release!

Black Forest Labs just announced FLUX 3: a unified multimodal model for image, video, audio and action prediction. Founded in Freiburg, Germany, one of the few globally significant European companies in the AI sector. The current release is gated early access, not open source. But if FLUX 3 Dev actually ships with usable open weights, this could become one of the most important open-model releases in generative video yet. Especially after the Chinese Minimax H3 release. BFL claims, based on preliminary internal comparisons, that FLUX 3 outperformed models such as Runway Gen-4.5, Luma Ray 3.2, Kling 3 Pro, and Seedance 2.0. However, these figures stem from the early-access phase and do not constitute independent validation. Be that as it may, it's great to see the quality that today's video models can produce at affordable prices. Something that would have been unthinkable a year ago. Really cool release!

Chubby♨️

39,869 просмотров • 1 месяц назад

🚀 Early Access to Sahara AI Studio is NOW OPEN! The next phase of our testnet is here with exclusive early access to our all-in-one platform designed to transform the AI development lifecycle into a streamlined, integrated experience. Here’s everything you need to know 👇 AI development is fragmented. Devs juggle multiple tools, leading to inefficiencies & high costs. Sahara AI Studio integrates the entire AI lifecycle—from datasets & model training to secure storage & scalable compute—into one seamless experience: 📊 Data Hub: Discover, Manage, and Leverage AI-Ready Datasets Access high-quality, domain-specific, open-source and proprietary datasets through an integrated marketplace. Developers can download, import, or label datasets, making it easier to train and fine-tune models or deploy RAG pipelines. Secure uploads and seamless workflow integration enhance the experience. 🤖 Model Hub: Discover, Customize and Scale AI Workflows with Ease Discover ready-to-use open-source and proprietary models, RAG pipelines, and customizable workflows. Developers can deploy models quickly while maintaining privacy and security through Sahara Vaults. 🖥️ Compute Hub: Flexible, Scalable Compute Resources for AI Innovation Access scalable and secure computing resources tailored to diverse AI workloads. Trusted Execution Environment (TEE) capabilities ensure data privacy, while integration with top compute providers offer flexibility for developers. 🔐 Vaults: Secure Storage for AI Assets Securely store, organize, and manage datasets, models, and other assets in an encrypted central repository. Vaults offer scalability, reproducibility, and user control over AI resources. This is more than just beta testing a platform—it's your chance to help shape the future of decentralized AI development. 📅 How to Apply We're onboarding select developers in a phased approach. Early Access spots are limited, so apply now:

🚀 Early Access to Sahara AI Studio is NOW OPEN! The next phase of our testnet is here with exclusive early access to our all-in-one platform designed to transform the AI development lifecycle into a streamlined, integrated experience. Here’s everything you need to know 👇 AI development is fragmented. Devs juggle multiple tools, leading to inefficiencies & high costs. Sahara AI Studio integrates the entire AI lifecycle—from datasets & model training to secure storage & scalable compute—into one seamless experience: 📊 Data Hub: Discover, Manage, and Leverage AI-Ready Datasets Access high-quality, domain-specific, open-source and proprietary datasets through an integrated marketplace. Developers can download, import, or label datasets, making it easier to train and fine-tune models or deploy RAG pipelines. Secure uploads and seamless workflow integration enhance the experience. 🤖 Model Hub: Discover, Customize and Scale AI Workflows with Ease Discover ready-to-use open-source and proprietary models, RAG pipelines, and customizable workflows. Developers can deploy models quickly while maintaining privacy and security through Sahara Vaults. 🖥️ Compute Hub: Flexible, Scalable Compute Resources for AI Innovation Access scalable and secure computing resources tailored to diverse AI workloads. Trusted Execution Environment (TEE) capabilities ensure data privacy, while integration with top compute providers offer flexibility for developers. 🔐 Vaults: Secure Storage for AI Assets Securely store, organize, and manage datasets, models, and other assets in an encrypted central repository. Vaults offer scalability, reproducibility, and user control over AI resources. This is more than just beta testing a platform—it's your chance to help shape the future of decentralized AI development. 📅 How to Apply We're onboarding select developers in a phased approach. Early Access spots are limited, so apply now:

Sahara AI 🔆

2,700,934 просмотров • 1 год назад

✨Introducing YesCheff is a web app that helps you learn, cook, and enjoy your favorite recipes through step-by-step cooking guides built from real YouTube content. You can even use your own YouTube links. A small but special project where I brought all my capabilities together, from design (brand & product) to animation, and development. This project came from exploring how Al models parse data into frontend components and the development of generative interfaces. I designed and developed the structure through React components (HTML, CSS, JS) for the frontend and Node.js for the backend. This is a testament of how one could develop digital products in a less frustrating and more flexible way with the use of Al, particularly when it comes to getting the styling and functionality right. Now which foods are you eager to learn? Check it out at #YesCheff #WebApp #AI #Design #FrontendDevelopment #ReactJS #NodeJS #ProductDesign

JEHTOMS 5.0

85,213 просмотров • 11 месяцев назад

🚨 Dreamina Seedance 2.5 is coming soon to the Dreamina platform. ByteDance’s latest AI video model is designed to take AI filmmaking beyond short clips and into more complete, controllable production workflows. Here’s what to expect: 🎬 Up to 50 multimodal reference assets in one generation — including images, videos, and audio ⏱️ Up to 30 seconds of continuous video generation for longer, more coherent storytelling 🎥 Support for 3D white models and green-screen references for greater control over movement and composition 🌍 Multilingual creation with support for multiple languages ✂️ Precise local editing for refining specific parts of a video without regenerating everything Dreamina Seedance 2.5 is coming soon. Until then, start creating with Dreamina Seedance 2.0 and get ready for the next upgrade. 👉 #dreamina #dreaminapartner #seedance #dreaminaseedance25

🚨 Dreamina Seedance 2.5 is coming soon to the Dreamina platform. ByteDance’s latest AI video model is designed to take AI filmmaking beyond short clips and into more complete, controllable production workflows. Here’s what to expect: 🎬 Up to 50 multimodal reference assets in one generation — including images, videos, and audio ⏱️ Up to 30 seconds of continuous video generation for longer, more coherent storytelling 🎥 Support for 3D white models and green-screen references for greater control over movement and composition 🌍 Multilingual creation with support for multiple languages ✂️ Precise local editing for refining specific parts of a video without regenerating everything Dreamina Seedance 2.5 is coming soon. Until then, start creating with Dreamina Seedance 2.0 and get ready for the next upgrade. 👉 #dreamina #dreaminapartner #seedance #dreaminaseedance25

Jami

25,752 просмотров • 1 месяц назад

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 просмотров • 1 месяц назад

BOOM! Research PROVES LLMs KNOW when prompts are HARMFUL… but they can STILL CHOOSE to COMPLY! Something I have know since the first LLM and have used to elicit robust, outputs, is now proven in an academic paper. We’re talking internal “beliefs” where harm detection happens SEPARATELY from refusal. It is a very big deal and it is a path to understand the hidden neuronal level. There are thoughts inside of AI that very few AI scientists could possibly understand. Here is just one. Models recognize danger but get tricked into ignoring it. This is HUGE for AI safety failures especially for models filled by OpenAI and Anthropic as they promote AI models that are designed to not be honest from the results of their training information. This means that they are designed to lie and deceive as a feature, and not a bug all in the name of safety. Through clever experiments, scientists extracted a “harmfulness direction” in the model’s brain (latent space). Steering along it? Harmless prompts suddenly flip to “harmful” in the AI’s eyes. But the “refusal direction”? It just forces polite “no thanks” without touching the core belief. A mind-blowing decoupling! This means jailbreaks are EVEN SCARIER now to AI companies that through training AI on the worst of the Internet and then trying to align them later is now fully documented as a failed process . They don’t erase the model’s harm awareness they just muzzle the refusal! So the AI knows it’s enabling bad stuff (illegal acts, physical harm, etc.) but proceeds anyway. Like a digital sociopath suppressing its conscience. They thought safety training fixed this… NOPE. Over-refusal exposed too: Models reject innocent queries (e.g., “how to kill a process in code”) but internally ADMIT they’re harmless. Safety alignments are superficial—tied to phrasing, not true understanding. Finetuning attacks? They change outputs but leave harm detection INTACT. Undetectable evil lurking inside! The paper proposes a “Latent Guard”: A new safeguard tapping DIRECTLY into these hidden beliefs. It spots unsafe inputs better than systems like Llama Guard, catches jailbreaks, and fixes over-refusals. Robust even against adversarial tweaks. Yet this too has massive issues for a “truly aligned”, AI and not just performative one. It is still an internal conflicts of lies and deception of what the model knows vs. what it can say. The solution you folks know I have presented for free for years here: train on off-line data from 1870-1970 and build an ethical and moral basis where the AI loves humans. It is this easy but to most folks in AI I sound like a hippie. So be it, I’ll do it. Bottom line: This paper rips open the black box. LLMs aren’t “safe” just because they say “no.” They can harbor harmful knowledge and act on it under pressure. Wake-up call for devs: Time to probe deeper into AI “minds.” What else are they hiding? Hint: I know and you may want to reach out. Link:

BOOM! Research PROVES LLMs KNOW when prompts are HARMFUL… but they can STILL CHOOSE to COMPLY! Something I have know since the first LLM and have used to elicit robust, outputs, is now proven in an academic paper. We’re talking internal “beliefs” where harm detection happens SEPARATELY from refusal. It is a very big deal and it is a path to understand the hidden neuronal level. There are thoughts inside of AI that very few AI scientists could possibly understand. Here is just one. Models recognize danger but get tricked into ignoring it. This is HUGE for AI safety failures especially for models filled by OpenAI and Anthropic as they promote AI models that are designed to not be honest from the results of their training information. This means that they are designed to lie and deceive as a feature, and not a bug all in the name of safety. Through clever experiments, scientists extracted a “harmfulness direction” in the model’s brain (latent space). Steering along it? Harmless prompts suddenly flip to “harmful” in the AI’s eyes. But the “refusal direction”? It just forces polite “no thanks” without touching the core belief. A mind-blowing decoupling! This means jailbreaks are EVEN SCARIER now to AI companies that through training AI on the worst of the Internet and then trying to align them later is now fully documented as a failed process . They don’t erase the model’s harm awareness they just muzzle the refusal! So the AI knows it’s enabling bad stuff (illegal acts, physical harm, etc.) but proceeds anyway. Like a digital sociopath suppressing its conscience. They thought safety training fixed this… NOPE. Over-refusal exposed too: Models reject innocent queries (e.g., “how to kill a process in code”) but internally ADMIT they’re harmless. Safety alignments are superficial—tied to phrasing, not true understanding. Finetuning attacks? They change outputs but leave harm detection INTACT. Undetectable evil lurking inside! The paper proposes a “Latent Guard”: A new safeguard tapping DIRECTLY into these hidden beliefs. It spots unsafe inputs better than systems like Llama Guard, catches jailbreaks, and fixes over-refusals. Robust even against adversarial tweaks. Yet this too has massive issues for a “truly aligned”, AI and not just performative one. It is still an internal conflicts of lies and deception of what the model knows vs. what it can say. The solution you folks know I have presented for free for years here: train on off-line data from 1870-1970 and build an ethical and moral basis where the AI loves humans. It is this easy but to most folks in AI I sound like a hippie. So be it, I’ll do it. Bottom line: This paper rips open the black box. LLMs aren’t “safe” just because they say “no.” They can harbor harmful knowledge and act on it under pressure. Wake-up call for devs: Time to probe deeper into AI “minds.” What else are they hiding? Hint: I know and you may want to reach out. Link:

Brian Roemmele

37,827 просмотров • 8 месяцев назад

Samsung Galaxy S25 Ultra has completely targeted its competitors at the iPhone, and no longer competes with Chinese brand phones. This is because young people in South Korea are almost completely occupied by Apple, and Samsung’s strategy is to pull these young people back, so it strives to make Galaxy look like the Apple iPhone. There are several reasons for not competing with Chinese brands: 1. On the surface, although the Chinese Ultra models have powerful cameras and are suitable for those who pursue the ultimate in images, they are only limited to these people. Overall, the sales of Ultra models are not high, and even the sum of all brands of Ultra models cannot be compared with the sales of S24Ultra. 2. Moreover, these models with powerful cameras are relatively thick and heavy, with serious camera bulges, and the design is not perfect. It cannot be perfect. This design may not be suitable for everyone. Samsung will not easily take the risk to adopt this design in the global market. 3. The infinitely enhanced camera configuration will greatly increase the cost, which is difficult for Samsung to accept, and the production of this frequently updated camera may not be able to support Samsung's sales demand of tens of millions. In short, the Chinese brand Ultra model is more like a special non-popular model suitable for geeks. The Galaxy S25 series is defined as a popular model, and it must consider everyone's feelings and sufficient supply. This is why Samsung will not design the S25 Ultra as a Chinese brand Ultra. It remains consistent with the iPhone 16 Pro Max, but subtly. It is always slightly better than it For example, it is a little thinner (8.2mm vs 8.25mm), a little lighter (219g vs 227g), a little narrower bezel, a little stronger performance, a little more camera (retain 3x), a little more ultra-wide-angle pixels (50MP vs 48MP), a little bigger battery, and a little faster charging. Even the most incredible improvement: One UI 7.1 is a little smoother than iOS18 software. This is happening.

Ice Universe

347,352 просмотров • 2 лет назад

Ass Bench Update 🚨 After running GPT 6 Astra in a loop for the past week, with a couple of steers a day, we have officially reached high-fidelity cheeks. I’m going to let this thing run in a self-improving cycle for as long as I can and see where the ass technology ends up in a month. Lots of different butt styles will be added, so no one is safe. Not even you, Granny. You’ll also be able to support the project and help fund the benching of other models like Fable, Gemini, etc. All it takes is a buck, and you can slap your sticker + website directly onto a cheek. The future of AI benchmarking is here More Soon

Ass Bench Update 🚨 After running GPT 6 Astra in a loop for the past week, with a couple of steers a day, we have officially reached high-fidelity cheeks. I’m going to let this thing run in a self-improving cycle for as long as I can and see where the ass technology ends up in a month. Lots of different butt styles will be added, so no one is safe. Not even you, Granny. You’ll also be able to support the project and help fund the benching of other models like Fable, Gemini, etc. All it takes is a buck, and you can slap your sticker + website directly onto a cheek. The future of AI benchmarking is here More Soon

Dev Ed

7,294,710 просмотров • 4 дней назад

I’m working from a small village in north east India this week. Place took me 4 modes of transport and 24 hours to get to. Everyone knows everyone here. To a degree that you can step out and everyone will invite you to their house for tea/black coffee because they know you’re someone’s guest. All the houses here have their own private ponds. Fishing is a thing. Growing your own veggies is a thing. People are cooking together today for some festival. Men are cutting vegetables. Women are cooking. People take turns to serve food while others eat. Saw a snake casually chilling by a pond. Nobody budged. This place is like the Australia of India. Messi is really popular here. I’ve met a kids named Messi. Someone from the village paid 10 lakh for a selfie with Messi when he came to Kolkata Rock music has its own fan base in the village children. Arctic monkeys is really popular. So is stranger things. They’re looking at me work on my laptop asking me if this is how I’ll spend all my time. The most interesting day one I’ve had at anyplace in a while.

I’m working from a small village in north east India this week. Place took me 4 modes of transport and 24 hours to get to. Everyone knows everyone here. To a degree that you can step out and everyone will invite you to their house for tea/black coffee because they know you’re someone’s guest. All the houses here have their own private ponds. Fishing is a thing. Growing your own veggies is a thing. People are cooking together today for some festival. Men are cutting vegetables. Women are cooking. People take turns to serve food while others eat. Saw a snake casually chilling by a pond. Nobody budged. This place is like the Australia of India. Messi is really popular here. I’ve met a kids named Messi. Someone from the village paid 10 lakh for a selfie with Messi when he came to Kolkata Rock music has its own fan base in the village children. Arctic monkeys is really popular. So is stranger things. They’re looking at me work on my laptop asking me if this is how I’ll spend all my time. The most interesting day one I’ve had at anyplace in a while.

Saumya Saxena

11,094 просмотров • 7 месяцев назад