# LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows

arXiv: https://arxiv.org/abs/2609.15863 · HTML: https://mlsanity.com/paper/2609.15863/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 28 of 28)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://mlsanity.com/paper/2509.24695/) (2025)
- [Learning Few-Step Diffusion Models by Trajectory Distribution Matching](https://mlsanity.com/paper/2503.06674/) (2025)
- [VMBench: A Benchmark for Perception-Aligned Video Motion Generation](https://mlsanity.com/paper/2503.10076/) (2025)
- [WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation](https://mlsanity.com/paper/2605.25874/) (2026)
- [MultiShotMaster: A Controllable Multi-Shot Video Generation Framework](https://mlsanity.com/paper/2512.03041/) (2025)
- [PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation](https://mlsanity.com/paper/2512.24551/) (2025)
- [Code World Model: Coding Agent as World Brain](https://mlsanity.com/paper/2608.25927/) (2026)
- [Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation](https://mlsanity.com/paper/2604.03118/) (2026)
- [GenClaw: Code-Driven Agentic Image Generation](https://mlsanity.com/paper/2605.30248/) (2026)
- [MOSS Transcribe Diarize Technical Report](https://mlsanity.com/paper/2601.01554/) (2026)

## Built on by (most cited first, 1 of 1)

- [ROWBench: Do Video Models Render What the Program Specifies?](https://mlsanity.com/paper/2610.02205/) (2026)

## Abstract (arXiv)

Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guaranteed success, and long-horizon scenes drift in appearance, interactions, and temporal coherence. Agentic visual creation provides explicit references, editable 3D scenes, or executable game states for stable control, but does not by itself guarantee high object or character fidelity. Combining the two can enable stable, high-quality generation. To realize this combination, we present LynnReal-Omni, a native multimodal video generation framework built on a 32B shared multimodal diffusion transformer that unifies text-to-video, image-conditioned generation, reference-guided generation, structural control, editing, degraded video restoration, and long-video generation. It accepts heterogeneous visual inputs, including appearance references, editable 3D renders, and game recordings, allowing agents to compose visual conditions within a unified model. We also train a dedicated 27B Flash shared multimodal diffusion transformer for real-time rendering. We build a systematic data pipeline for video cleaning, subject association, multimodal annotation, and aligned control construction, yielding a curated corpus of multi-shot audiovisual segments, and introduce MSAVP, a 100-prompt, 20-metric evaluation design that separates instruction following, generating plausibility, visual quality, temporal behavior, and audio coordination. LynnReal-Omni-Flash further reduces inference cost through model and decoding acceleration, including a lightweight VAE decoder; on one H100, warm generation and decoding of a 22-frame 540p video take 843 ms with LynnReal-Omni and 377 ms with Flash. These results provide a foundation for real-time streaming video generation, making LynnReal-Omni a unified, controllable, and efficient basis for agentic visual creation.