Загрузка видео...

Не удалось загрузить видео

На главную

Big Odyssey news! We’re unveiling Explorer, a generative world model. Explorer transforms text or an image into a realized, detailed 3D world. I'm also incredibly excited that Edwin Catmull, the legendary Pixar founder, is joining our board & investing. Read on for more...

102,831 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

Ed co-founded Pixar with the belief that the story must shape the technology—not the reverse. They took the hard road, pioneering new technologies to enable stories thought impossible. In Pixar's case, they pioneered computer graphics. For us, it's generative world models.

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

World models, alongside language, image, & video, are now a key AI frontier, but the least explored. Imagine worlds that build themselves, that feel indistinguishable from reality, where new stories can be created & remixed, and where human & machine intelligence can interact.

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

Enter Explorer—our first generative world model, and the start of this epic journey. Explorer is an image-to-world model that transforms an image into a detailed 3D world. Explorer is particularly tuned for photorealistic worlds, with this proving a key strength.

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

Our world is constantly in motion, and Explorer’s worlds should be no different. Although earlier in research, generative world motion, all in 3D, holds super exciting promise to enable artists to generate and manipulate motion in new and more realistic ways.

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

A world generated with Explorer (like in this video) is output as a gaussian splat. Many of the top vision researchers in the world have turned their attention towards splats, and it's easy to see why. Splats can represent 3D scenes with almost imperceptibly real detail.

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

Representing worlds as splats also means artists can natively edit them in a growing list of creative tools. Unreal, Houdini, Blender, Maya, 3D Studio Max, After Effects, & more now support splats. Artists with early Explorer access have used these tools for incredible things!

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

Generative world models could accelerate the creation of film & gaming-compatible worlds. To test this, we visited @GardenStudiosHQ. We beamed Explorer-generated worlds onto a SOTA virtual production stage, used for film. The conclusion: they worked & looked incredible!

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

We're now opening up access to Explorer more broadly. If you're eager to explore generative world models with us, and to collaborate closely, we want to hear from you ASAP. Head over to our site to apply, and we'll be in touch.

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

Explorer is our starting point, and one we're really, really proud of. Generative world models have a long road ahead, but the promise is vast. A brand new medium is being created as we speak! Let's together pioneer generative world models and what they enable you to create 🫡

Фото профиля Oliver Cameron
Oliver Cameron1 год назад

I still can't quite believe we have the opportunity to partner with and learn from Ed Catmull. We're beyond excited ❤️ You can learn a whole lot more about Explorer, generative world models, and our partnership with Ed here.

Фото профиля Cook For Love is here 👨‍🍳✨
Cook For Love is here 👨‍🍳✨1 год назад

🌟 Available now on Nintendo Switch! ✨ Embark on a heartfelt journey across generations in Tell Me Your Story! 🌎 Discover treasured memories, solve cozy puzzles, and dive into a beautiful world of family stories. Perfect for those who love exploring life’s moments in a relaxing game. 🎮✨ #IndieGames #NintendoSwitch #TellMeYourStory #CozyGames #PuzzleAdventure

Похожие видео

🚀 Announcing Echo — our new frontier model for 3D world generation. Echo turns a simple text prompt or image into a fully explorable, 3D-consistent world. Instead of disconnected views, the result is a single, coherent spatial representation you can move through freely. This is part of a bigger shift in AI: from generating pixels and tokens to generating spaces. Echo predicts a geometry-grounded 3D scene at metric scale, meaning every novel view, depth map, and interaction comes from the same underlying world — not independent hallucinations. Once generated, the world is interactive in real time. You control the camera, explore from any angle, and render instantly — even on low-end hardware, directly in the browser. High-quality 3D world exploration is no longer gated by expensive equipment. Under the hood, Echo infers a physically grounded 3D representation and converts it into a renderable format. For our web demo, we use 3D Gaussian Splatting (3DGS) for fast, GPU-friendly rendering — but the representation itself is flexible and can be easily adapted. Why this matters: consistent 3D worlds unlock real workflows — digital twins, 3D design, game environments, robotics simulation, and more. From a single photo or a line of text, Echo builds worlds that are reliable, editable, and spatially faithful. Echo also enables scene editing and restyling. Change materials, remove or add objects, explore design variations — all while preserving global 3D consistency. Editing no longer breaks the world. This is only the beginning. Echo is the foundation for future world models with dynamics, physical reasoning, and richer interaction — environments that don’t just look right, but behave right. Explore the generated worlds on our website and sign up for the closed beta. The era of spatial intelligence starts here. 🌍 #Echo #WorldModels #SpatialAI #3DFoundationModels Check it out:

SpAItial AI

176,524 просмотров • 8 месяцев назад