Spell by Spline

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).

**Spell by Spline** is an advanced AI model designed to generate fully immersive 3D worlds from a single image in just minutes. It creates consistent, multi-view 3D scenes using techniques like Gaussian Splatting or NeRFs, offering realistic rendering across diverse categories such as environments, characters, and objects. The model excels in maintaining physical consistency, simulating material properties, and handling camera interactions with precision. Trained on a blend of real-world and synthetic data, Spell produces outputs in the form of videos, image sequences, or volumes, with potential for mesh conversion. While still evolving, Spell represents a groundbreaking step in AI-driven 3D graphics, promising enhanced quality and interactivity in the future.