Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

GPT-6 Astra + LTX-2.5 = web video interface Your website is an immersive experience now Every click changes one property of the world: scene, lighting, clothing, or cast The world-video model becomes the transition surface Full GitHub build 🧵👇

AmirMušić

81,929 subscribers

270,393 Aufrufe • vor 5 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing Buzzy 3D Director Console, powered by GPT-6 Astra. Let GPT-6 turn your words into fully interactive 3D world, and then to stunning video on Buzzy. >Build complex 3D characters & scenes with simple prompts >Control cameras, characters, lighting, and environments easily >Direct and refine every detail with simple prompts Experience OpenAI's strongest model on Buzzy!

Introducing Buzzy 3D Director Console, powered by GPT-6 Astra. Let GPT-6 turn your words into fully interactive 3D world, and then to stunning video on Buzzy. >Build complex 3D characters & scenes with simple prompts >Control cameras, characters, lighting, and environments easily >Direct and refine every detail with simple prompts Experience OpenAI's strongest model on Buzzy!

Buzzy Now

1,560,002 Aufrufe • vor 3 Tagen

Dreaming of launching a clothing brand? GPT-6 Astra: >builds the website >generates model shots and logos with Higgsfield >deploys the finished store to Shopify Now all you need is the idea.

Higgsfield AI 🧩

13,408 Aufrufe • vor 3 Tagen

Cinema Studio is live. AI video has a control problem. You get a stunning shot, but never THE shot. 3D fixes that. Build the scene → set the camera → record the POV → render with AI. Built for VFX, previs, and game studios. Powered by GPT-6 Astra + Seedance 2.5.

Cinema Studio is live. AI video has a control problem. You get a stunning shot, but never THE shot. 3D fixes that. Build the scene → set the camera → record the POV → render with AI. Built for VFX, previs, and game studios. Powered by GPT-6 Astra + Seedance 2.5.

Customuse

217,198 Aufrufe • vor 1 Tag

Computer-use has come a long ways.. This video was entirely recorded, edited, and polished by astra gpt-6 in Codex. The world is not ready for billions of agents needing billions of powerful computers. Until now.

Computer-use has come a long ways.. This video was entirely recorded, edited, and polished by astra gpt-6 in Codex. The world is not ready for billions of agents needing billions of powerful computers. Until now.

Nick Vasilescu

18,361 Aufrufe • vor 1 Tag

We release Cosmos Policy 💫: a state-of-the-art robot policy built on a video diffusion model backbone. - policy + world model + value function — in 1 model - no architectural changes to the base video model - SOTA in LIBERO (98.5%), RoboCasa (67.1%), & ALOHA tasks (93.6%) 🧵👇

We release Cosmos Policy 💫: a state-of-the-art robot policy built on a video diffusion model backbone. - policy + world model + value function — in 1 model - no architectural changes to the base video model - SOTA in LIBERO (98.5%), RoboCasa (67.1%), & ALOHA tasks (93.6%) 🧵👇

Moo Jin Kim

150,032 Aufrufe • vor 7 Monaten

Runway Co-Founder & Co-CEO Anastasis Germanidis breaks down Solaris, an interface world model that generates interactive applications pixel by pixel: "Solaris is what we call an interface world model." "It's an interactive video model that essentially renders an interface for you." "The difference is that it's all generated pixel by pixel by a video model." "Unlike traditional interfaces where you write some code, you write some HTML or CSS, and then that renders pixels, you're now rendering pixels directly." "By doing that you get a ton more flexibility." "You can kind of leverage everything that the video model can do and create any kind of application on top of it."

Runway Co-Founder & Co-CEO Anastasis Germanidis breaks down Solaris, an interface world model that generates interactive applications pixel by pixel: "Solaris is what we call an interface world model." "It's an interactive video model that essentially renders an interface for you." "The difference is that it's all generated pixel by pixel by a video model." "Unlike traditional interfaces where you write some code, you write some HTML or CSS, and then that renders pixels, you're now rendering pixels directly." "By doing that you get a ton more flexibility." "You can kind of leverage everything that the video model can do and create any kind of application on top of it."

etn.

17,203 Aufrufe • vor 9 Tagen

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

Rahul

353,259 Aufrufe • vor 4 Tagen

GPT-6 Astra is now on TapNow Creative OS. From a still idea to a moving scene, helping you bring visual concepts to life as video. Start with a reference. Make it move. Click the link below for more details.

GPT-6 Astra is now on TapNow Creative OS. From a still idea to a moving scene, helping you bring visual concepts to life as video. Start with a reference. Make it move. Click the link below for more details.

TapNow

56,039 Aufrufe • vor 3 Tagen

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

ComfyUI

13,174 Aufrufe • vor 1 Monat

Elysium is live now!!🤩 🌿Link : I wanted to build the most beautiful 3D world on the #web. 6 months of hard work, dedication and many sleepless nights later, we are finally here! If this post reaches 1k likes, 👇🧵 Tools used: Three.js, #javascript

Elysium is live now!!🤩 🌿Link : I wanted to build the most beautiful 3D world on the #web. 6 months of hard work, dedication and many sleepless nights later, we are finally here! If this post reaches 1k likes, 👇🧵 Tools used: Three.js, #javascript

Ebenezer

79,094 Aufrufe • vor 3 Jahren

GPT-5.6 Sol just changed how I build websites with AI. In this full 10-minute video, I test Sol and Terra inside Codex to build a cinematic landing page from a video reference. I cover: → Which GPT-5.6 model to use → How I analyze a full website experience → How I recreate the layout, motion and interactions → Why better prompting matters more than one-shot results → How to avoid generic AI slop The model matters—but the way you guide it matters even more. Watch the full process below 👇 Want the free template and the exact prompt I used? They’re available exclusively in the description of the YouTube version:

GPT-5.6 Sol just changed how I build websites with AI. In this full 10-minute video, I test Sol and Terra inside Codex to build a cinematic landing page from a video reference. I cover: → Which GPT-5.6 model to use → How I analyze a full website experience → How I recreate the layout, motion and interactions → Why better prompting matters more than one-shot results → How to avoid generic AI slop The model matters—but the way you guide it matters even more. Watch the full process below 👇 Want the free template and the exact prompt I used? They’re available exclusively in the description of the YouTube version:

Sourasith

261,047 Aufrufe • vor 2 Monaten

There’s a strange thing about AI video: The moment generation becomes cheap, the cost of a bad creative decision becomes much more obvious. You can generate another clip. But should you? I’d rather build the scene first with GPT-6 Astra, establish the camera and character paths in the Viewport, manually bring the 3D scene into CapCut PC, render with Seedance 2.5, and then decide what actually deserves to stay in the final edit. Maybe the future isn’t about generating more. Maybe it’s about becoming better at choosing. #GPT6Astra #Seedance25 #CapCutPC #AIVideo

There’s a strange thing about AI video: The moment generation becomes cheap, the cost of a bad creative decision becomes much more obvious. You can generate another clip. But should you? I’d rather build the scene first with GPT-6 Astra, establish the camera and character paths in the Viewport, manually bring the 3D scene into CapCut PC, render with Seedance 2.5, and then decide what actually deserves to stay in the final edit. Maybe the future isn’t about generating more. Maybe it’s about becoming better at choosing. #GPT6Astra #Seedance25 #CapCutPC #AIVideo

Jessica AI

21,378 Aufrufe • vor 3 Tagen

There’s an interesting shift when you stop thinking about AI video as “text to video.” Because a film isn’t text becoming pixels. It’s an idea becoming a world, a world becoming movement, movement becoming footage, and footage becoming a story. GPT-6 Astra handles the spatial setup through the Viewport. I then manually bring the 3D scene into CapCut PC, use Seedance 2.5 to render it, and continue the creative process in CapCut PC with Edit Pilot. That feels much closer to a filmmaking pipeline. Maybe “AI filmmaking” is a better description than “AI video generation.” #GPT6Astra #AIVideo #CapCutPC #Seedance25

There’s an interesting shift when you stop thinking about AI video as “text to video.” Because a film isn’t text becoming pixels. It’s an idea becoming a world, a world becoming movement, movement becoming footage, and footage becoming a story. GPT-6 Astra handles the spatial setup through the Viewport. I then manually bring the 3D scene into CapCut PC, use Seedance 2.5 to render it, and continue the creative process in CapCut PC with Edit Pilot. That feels much closer to a filmmaking pipeline. Maybe “AI filmmaking” is a better description than “AI video generation.” #GPT6Astra #AIVideo #CapCutPC #Seedance25

Ryan Hayes

32,222 Aufrufe • vor 3 Tagen

I THINK THE INTERESTING SHIFT IN AI-POWERED FILM PRODUCTION ISN'T THAT "AI CAN NOW GENERATE VIDEO." WE ALREADY KNOW THAT. The key is that the workflow is starting to resemble the actual filmmaking process: Plan the scene → establish the movement → generate the footage → edit the sequence. GPT-6 Astra handles the spatial planning and visualization. Seedance 2.5 takes care of rendering once the scene is in CapCut PC. Then, CapCut PC processes the footage during post-production. The model is important, but the workflow could be even more so. #GPT6Astra #CapCutPC #Seedance25 #AIVideo

I THINK THE INTERESTING SHIFT IN AI-POWERED FILM PRODUCTION ISN'T THAT "AI CAN NOW GENERATE VIDEO." WE ALREADY KNOW THAT. The key is that the workflow is starting to resemble the actual filmmaking process: Plan the scene → establish the movement → generate the footage → edit the sequence. GPT-6 Astra handles the spatial planning and visualization. Seedance 2.5 takes care of rendering once the scene is in CapCut PC. Then, CapCut PC processes the footage during post-production. The model is important, but the workflow could be even more so. #GPT6Astra #CapCutPC #Seedance25 #AIVideo

Marco | IA

45,499 Aufrufe • vor 3 Tagen

The best AI video generator still can’t guarantee every detail will come out exactly right. Seedance 2.5 is already available on CapCut, and Seedance 2.5 1080p is now live. My workflow is AI Image batch generation → AI Video → CapCut PC timeline → AI Edit. If the character’s outfit, lighting, product detail or an unwanted object needs changing, I can target that part instead of regenerating the whole scene. Then AI Extend handles longer scenes, Edit Pilot handles batch changes, and the multi-track timeline finishes captions, voiceover, color and sound. That’s the kind of control I want from an AI video editor. #CapCutPC #AIVideoEditor #CapCutSeedance25 #Seedance251080p

The best AI video generator still can’t guarantee every detail will come out exactly right. Seedance 2.5 is already available on CapCut, and Seedance 2.5 1080p is now live. My workflow is AI Image batch generation → AI Video → CapCut PC timeline → AI Edit. If the character’s outfit, lighting, product detail or an unwanted object needs changing, I can target that part instead of regenerating the whole scene. Then AI Extend handles longer scenes, Edit Pilot handles batch changes, and the multi-track timeline finishes captions, voiceover, color and sound. That’s the kind of control I want from an AI video editor. #CapCutPC #AIVideoEditor #CapCutSeedance25 #Seedance251080p

Esha ❤️

36,787 Aufrufe • vor 24 Tagen

The hardest part of AI video might eventually become deciding what not to generate. When the scene, camera, character movement, and sequence are all intentional, generation becomes less about exploring random possibilities and more about executing a creative decision. That’s the workflow I see in GPT-6 Astra: Build the spatial scene in the Viewport → bring it into CapCut PC → render with Seedance 2.5 → edit the footage into the final sequence. AI gets the generation. The creator keeps the direction. #GPT6Astra #AIVideo #CapCutPC #Seedance25

The hardest part of AI video might eventually become deciding what not to generate. When the scene, camera, character movement, and sequence are all intentional, generation becomes less about exploring random possibilities and more about executing a creative decision. That’s the workflow I see in GPT-6 Astra: Build the spatial scene in the Viewport → bring it into CapCut PC → render with Seedance 2.5 → edit the footage into the final sequence. AI gets the generation. The creator keeps the direction. #GPT6Astra #AIVideo #CapCutPC #Seedance25

Nyama Quarter

109,943 Aufrufe • vor 3 Tagen

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,725 Aufrufe • vor 2 Jahren

One video, now made for every feed and format. Upload your existing video, choose your desired aspect ratio and watch our editing model, Aleph 2.0, fill in the rest of the scene as if you made it that way from the start. Try it on our desktop web app at the link below.

One video, now made for every feed and format. Upload your existing video, choose your desired aspect ratio and watch our editing model, Aleph 2.0, fill in the rest of the scene as if you made it that way from the start. Try it on our desktop web app at the link below.

Runway

21,968 Aufrufe • vor 3 Monaten

Episode 6 of our Dev Diary Series is NOW AVAILABLE! In this sixth episode we’ll learn the steps necessary to create an interconnected non-linear world to keep the player entertained for multiple hours. EP05: "The path of the Penitent One” Full video -

Episode 6 of our Dev Diary Series is NOW AVAILABLE! In this sixth episode we’ll learn the steps necessary to create an interconnected non-linear world to keep the player entertained for multiple hours. EP05: "The path of the Penitent One” Full video -

Blasphemous

41,482 Aufrufe • vor 2 Jahren

Camera control is no longer in the prompt Meet 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnific

Camera control is no longer in the prompt Meet 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnific

Magnific

610,355 Aufrufe • vor 1 Monat