Search papers, labs, and topics across Lattice.
Visko Orbis 1.0 is a real-time interactive long-video generation model that allows users to modify prompts during the video creation process, with changes reflected instantly. It supports various input types, including text-to-video and image-to-video, while maintaining coherence across long sequences through a bounded multi-scale memory system. In comparative evaluations, it outperformed existing systems in overall preference and temporal stability, achieving 4K video generation at 24 FPS with minimal quality loss.
Users can alter video prompts on-the-fly, enabling a seamless interactive experience in long-form video generation.
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.
