Spell is an AI model to generate full 3D scenes or “Worlds” from an image, in just a few minutes. The worlds are consistent with the initial image input and are rendered as a volume that can be rendered using Gaussian Splatting (or NeRFs).
Oh looks like someone hunted this for us!
For anyone interested. This has been a massive endeavor in terms of research and development.
Spell is a special model because it has a deeper understanding of the 3d space. Which means that it can approximate physical behaviors.
We wrote more about it here: https://blog.spline.design/intro...
I can already see how Spell by Spline could be used in educational settings to teach 3D design and world-building. It makes the process so accessible and engaging for students.
Great job simplifying such a complex process 😀
Today I learned making a 3D toggle micro interaction! The Spline tutorials are very easy to follow.” “...I'm looking forward to trying out more of their tutorials.
Turning a single image into a full 3D world is such an interesting concept! The fact that it keeps the scene consistent with the original image is impressive—feels like it could be super useful for creative projects or visualizations.
Wow this level of...I guess you could call it 'World Generation' is unbelievable...
What a tool to be able to extrapolate an idea of the 360 degree environment.
Top work Alejandro, best of luck today!!!
Congratulations on the release of Spell by Spline! The ability to generate 3D worlds from images is a fascinating development. How does Spell ensure consistency in style and detail between the initial image and the generated 3D scene?
Spline