Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation
Not on the map. Why?
Abstract (arXiv)
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. The generator is factorized causally in time, matching the causal structure of physical dynamics, and is aligned with a latent world-model reward for predictive consistency. Built on a distilled chunk-wise streaming generator and a streaming video upscaler, Visko Orbis 1.0 delivers 4K video generation at 24 FPS in real time, using an optimized GPU serving engine. In quantitative evaluations, Visko Orbis 1.0 achieves the best DOVER aesthetic and technical scores and the best VideoAlign visual and motion quality, and leads three physical-plausibility protocols (VideoPhy-2, Physics-IQ, and VBench-2.0 Physics); in long-form Arena comparisons, it obtains the highest overall-preference and temporal-stability ratings among all the state-of-the-art real-time interactive video generation systems.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 83 of its 97 references that are in the map. First posted on arXiv 29 Jul 2026.
Builds on
83 of 97 references.
References · 83
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
- 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
- 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
- 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
- 2023Consistency Modelscited by 1,778
- 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
38 more
- 2018Datasheets for Datasetscited by 1,371
- 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
- 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
- 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
- 2023One-step Diffusion with Distribution Matching Distillationcited by 978
- 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
- 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
- 2017Dense-Captioning Events in Videoscited by 789
- 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
- 2022On Distillation of Guided Diffusion Modelscited by 721
- 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
- 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
- 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
- 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
- 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 488
- 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 441
- 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
- 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 389
- 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 388
- 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
- 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 332
- 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
- 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 289
- 2025Improving Video Generation with Human Feedbackcited by 267
- 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioningcited by 263
- 2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 255
- 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
- 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 239
- 2025LongLive: Real-time Interactive Long Video Generationcited by 237
- 2022VRT: A Video Restoration Transformercited by 219
- 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
- 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 209
- 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 196
- 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 174
- 2022Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AIcited by 169
- 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
- 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 166
- 2018Frame-Recurrent Video Super-Resolutioncited by 160
50 most cited of 83 All 83 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025MotionStream: Real-Time Video Generation with Interactive Motion Controls
- 2025GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
- 2025Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
- 2023PEEKABOO: Interactive Video Generation via Masked-Diffusion
- 2025StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
- 2024Owl-1: Omni World Model for Consistent Long Video Generation
- 2026A Mechanistic View on Video Generation as World Models: State and Dynamics
- 2026minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models