computer vision

Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation

arXiv:2607.26694

summary

Visko Orbis 1.0 is a live model that generates long videos in real time, letting users change prompts on the fly while preserving subject, scene, and style consistency across hour‑scale rollouts.

Abstract

We present Visko Orbis 1.0, a Live Model for real-time, interactive long-video generation. Users can change the prompt at any moment during generation, and the update becomes visible in real time. Visko Orbis 1.0 supports long-form text-to-video, image-to-video, and video continuation, with multilingual prompts and prompt switching while generation is in progress. A bounded multi-scale memory preserves subjects, scenes, and style across chunks, sustaining hour-scale rollouts without evident quality or color drift. Built on a distilled chunk-wise streaming generator and a streaming video upscaler, Visko Orbis 1.0 delivers real-time 4K video generation at 24 FPS using an optimized GPU serving engine. In long-form Arena comparisons, Visko Orbis 1.0 obtains the highest overall-preference and temporal-stability ratings among state-of-the-art real-time interactive video-generation systems.

Topics & keywords

#real-time video generation#interactive text-to-video#multilingual prompts#long-form video continuation#streaming generation memoryVisko Orbis 1.0chunk-wise streaming generatorbounded multi-scale memory4K 24 FPS video upscalerGPU serving engine