实时交互式长视频生成，支持随时改提示并即时更新。
Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation
- 采用分块流式生成与多尺度记忆机制，保持长时间生成一致性。
- 24帧/秒流畅输出4K视频，支持跨场景持续生成不漂移。
- 适合需要动态调整内容的创作者、直播或实时交互应用。
我们提出 Visko Orbis 1.0，一种支持实时交互的长视频生成系统。用户可在生成过程中任意修改提示词，更改立即可见。该模型支持长文本到视频、图像到视频及视频续写，支持多语言提示与生成中切换。通过有界多尺度记忆机制，有效维持角色、场景与风格在分块生成中的连续性，实现小时级生成无明显质量或色彩漂移。基于蒸馏的分块流式生成器与流式超分模块，结合优化的GPU服务引擎，可实现实时4K视频生成，帧率24 FPS。在长视频综合评测中，Visko Orbis 1.0 在整体偏好度与时间稳定性上均优于现有实时交互视频生成系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。