InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model

TL;DR

InSpatio-WorldFM is an open-source, low-latency, real-time spatial intelligence model that generates independent frames with multi-view consistency, transforming diffusion models into efficient scene generators.

Contribution

It introduces a novel frame-based paradigm with explicit 3D anchors and a progressive training pipeline for real-time spatial scene generation.

Findings

Achieves strong multi-view consistency across viewpoints.

Supports interactive exploration on consumer-grade GPUs.

Transforms pretrained diffusion models into real-time scene generators.

Abstract

We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation.