# World Engine ## Overview \ The Worlds Engine leverages generative AI models tailored for 3D asset creation and procedural world-building within Unity and Unreal Engine. It generates terrains, structures, foliage, and environmental details while ensuring technical feasibility and aesthetic consistency. ## Model Type & Architecture * Multimodal Generative Models: The Worlds Engine uses a combination of 3D generative diffusion models and transformer-based architectures trained on large datasets of game environments. These models generate heightmaps, textures, meshes, and environmental objects that seamlessly integrate into Unity or Unreal. * Procedural Generation + LLM Integration: LLMs guide high-level thematic and narrative consistency. For example, a text prompt describing a “mystical forest” informs the generative model, which produces terrain, trees, and ruins aligned with that theme. * Reinforcement Learning for Aesthetic & Performance Optimization: RL is used to fine-tune world generation parameters, striking a balance between visual quality, game performance, and player navigation. The model iteratively refines generated worlds based on developer feedback and performance constraints. ## Underlying Tech * 3D Diffusion Models: State-of-the-art diffusion architectures adapted for 3D asset generation. * Text-to-World Pipelines: LLM-based prompt interpretation, guiding generative models with thematic constraints. * Integration with Unity/Unreal APIs: Specialized adapters ensure the generated assets are compatible, with automated optimization passes for polygon counts, texture sizes, and physics properties. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.altura.com/altura-documentation/altura-intelligence/world-engine.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.