Introducing Spell, a model to generate 3D worlds. A new era for 3D. ✨ (Thread - Link Below)

Spell can generate entire 3D scenes or “Worlds” from an image in just a few minutes. The worlds are consistent with the initial image input and are represented as a volume that can be rendered using Gaussian Splatting (or other methods, like NeRFs).

We are launching Spell at an early stage, with limited access and an intentionally high price. It is only meant for early adopters so we can better understand how you interact with the model and also to keep the GPU expense low during this phase. This is the first time we have built a model with this level of complexity, and we have learned so much while building it; there is also a lot more to do!

Access Spell: If you are interested in joining our research team, please reach out! We will continue to share more about it in the coming days. We can't wait to see what you can do with it! Learn more:

Who wants to transform into weird creatures? Play our Demo now on STEAM 👇

This is absolutely sick! Can I embed these on the web/mobile?

Yes! For example, you can embed this:

This is really wild! examples are looking great 🔥

Looking forward to trying this out!

Bold move on this feature. Would be fun to see how it integrates with your 3D capabilities.

Let's go!!!!!!

Wow, amazing! ✨👏✨