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

Hugging Face Daily Papers Papers

Summary

LynnReal-Omni is a unified multimodal video diffusion framework that integrates agentic visual controls with high-fidelity generation and real-time acceleration for stable, controllable video creation.

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.
Original Article
View Cached Full Text

Cached at: 09/15/26, 10:40 AM

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

Source: https://huggingface.co/papers/2609.15863

Abstract

LynnReal-Omni is a unified multimodal video diffusion framework that integrates agentic visual controls with high-fidelity generation and real-time acceleration.

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 sharedmultimodal diffusion transformerthat unifiestext-to-video,image-conditioned generation,reference-guided generation,structural control, editing, degradedvideo restoration, andlong-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 sharedmultimodal diffusion transformerfor 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 introduceMSAVP, 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 lightweightVAE 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.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2609\.15863

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.15863 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.15863 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.15863 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

Hugging Face Daily Papers

CogOmniControl is a reasoning-driven framework for controllable video generation that uses a specialized vision-language model (CogVLM) trained on anime production data to infer creative intent from sparse conditions, then guides a diffusion-based generator via reinforcement learning, achieving state-of-the-art results on new benchmarks.