Search papers, labs, and topics across Lattice.
The paper introduces AlayaRenderer-Flash, a real-time generative world renderer that enhances the original AlayaRenderer's performance from 0.56 FPS to 31.54 FPS, making it suitable for interactive applications. By reformulating the rendering process as a few-step autoregressive streaming model and employing lightweight distilled codecs, AlayaRenderer-Flash achieves significant improvements in inference cost while maintaining the essential rendering capabilities of its predecessor. Evaluations demonstrate that it effectively preserves scene structure and dynamics, enabling continuous rendering over unbounded input streams.
AlayaRenderer-Flash achieves real-time generative rendering at 30 FPS without sacrificing scene fidelity or control.
Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesizes RGB frames. Unlike models that generate frames from text/control-hints prompts, AlayaRenderer preserves scene structure without altering the underlying world dynamics. This demonstrates an alternative path toward interactive world modeling and user-controllable play. However, the original AlayaRenderer is too computationally expensive for real-time deployment. This technical report introduces AlayaRenderer-Flash, a real-time-oriented generative forward world renderer that pushes AlayaRenderer from 0.56 FPS to 31.54 FPS, reaching the speed of play. AlayaRenderer-Flash reformulates the original renderer as a few-step autoregressive streaming model and introduces lightweight distilled codecs for efficient latent encoding and frame reconstruction. It retains the teacher model's G-buffer and text-prompt interfaces while enabling continuous rendering over input streams of unbounded length. We evaluate AlayaRenderer-Flash on G-buffer streams across content preservation, temporal consistency, cross-window stability, prompt controllability, and runtime efficiency. Our results show that AlayaRenderer-Flash substantially reduces inference cost while preserving the core rendering capabilities of the teacher model. By integrating AlayaRenderer-Flash with a physics engine, we build a fully playable generative world running at 30 FPS.
