---
title: LynnReal-Onmi-flash-beta-0.1
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/LynnReal-Onmi-flash-beta-0.1"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/LynnReal-Onmi-flash-beta-0.1.md"
repository: AI-ModelScope/LynnReal-Onmi-flash-beta-0.1
last_updated: 2026-09-22
parameters: 64.1B
tensor_type:
  - BF16
  - F32
  - I8
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 84
stars: 1
tags:
  - "arxiv:2609.15863"
  - minimax-h3
  - int8
  - video-generation
---

# LynnReal-Onmi-flash-beta-0.1

> LynnReal-Onmi-flash-beta-0.1 - AI-ModelScope 在 ModelScope 开源的模型。Code: LynnReal-AI/LynnReal-Omni · Paper · HF Paper

- **Repository**: AI-ModelScope/LynnReal-Onmi-flash-beta-0.1
- **Parameters**: 64.1B
- **Tags**: arxiv:2609.15863, minimax-h3, int8, video-generation
- **Downloads**: 84
- **Stars**: 1
- **Last updated**: 2026-09-22

Source: https://www.modelscope.cn/models/AI-ModelScope/LynnReal-Onmi-flash-beta-0.1

---

# LynnReal Flash

Code: [LynnReal-AI/LynnReal-Omni](https://github.com/LynnReal-AI/LynnReal-Omni) · [Paper](https://arxiv.org/abs/2609.15863) · [HF Paper](https://huggingface.co/papers/2609.15863)

## 🆕 Latest updates

- **2026-09-18 · ComfyUI node pack fix** — the Flash three-step workflows no longer stop with
  `RuntimeError: aimdo memory compile error` on machines where comfy-aimdo's DynamicVRAM is active
  (a cu13x torch, e.g. an RTX 5090). Update
  [`comfyui/custom_nodes/ComfyUI-LynnReal`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/custom_nodes/ComfyUI-LynnReal)
  and re-run; no launcher flags are needed.
- **2026-09-17 · ComfyUI Flash workflows** — three-step t2v / ti2v / ref2v now ship in the
  [main bundle](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui), with
  the Light VAE loader and the INT8 switch node.

Full history: [CHANGELOG.md](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/CHANGELOG.md)
in the main repository.

A 42-block joint video/audio DiT with three denoiser evaluations. Supports
text-to-video and native first/last keyframes. Middle blocks use spatial
stride-two token selection with full-resolution residual restoration.

The complete transformer uses trained W8A8 projections: INT8 weights,
per-token INT8 activations, INT32 accumulation, and BF16 outputs. Sensitive
projections remain BF16. Packed weights and per-channel scales are stored
without requantization in indexed Hugging Face safetensors shards.

Load using the release `model.flash_int8.load_transformer` or the launchers
in `script/sample/flash/int8`. This custom packed format requires that loader;
a generic Diffusers `from_pretrained` does not install the INT8 operators.
Shared conditioning and codec components are included in this model bundle.
See LICENSE and NOTICE for upstream terms.

## ⚡🔥 ComfyUI — the fastest way to try it!

This checkpoint also runs in ComfyUI, at its trained three steps, from three workflows that ship
with the release: `t2v`, `ti2v` (one first frame) and `ref2v` (reference pictures), plus the
Light VAE and the node pack that implements the token selection! On a **single H100 80 GB** at
1344×768, warm, three measured runs per cell:

| Task | 5 s · generate | 5 s · click-to-video | 10 s · generate | 10 s · click-to-video |
| :--- | ---: | ---: | ---: | ---: |
| Text → video | **8.4 s** | 12.2 s | **22.0 s** | 29.1 s |
| First frame → video | **8.9 s** | 13.0 s | **23.1 s** | 30.1 s |
| References → video | **9.5 s** | 13.2 s | **24.2 s** | 31.1 s |

A five-second 1344×768 clip **with native stereo audio** in about **eight and a half seconds** on
one card: three denoiser steps and both decoders included. `generate` is the Generate-wall
convention (first denoiser forward to decoded frames), `click-to-video` is what you actually wait
for! Videos longer than 11 seconds are not usable in that path yet — the accelerated path for
long clips is still being fixed.

Everything it needs — workflows, node pack, weights and demo assets — is in
[🤗 stdstu123/LynnReal-Onmi-beta-0.1 · comfyui](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui).
The weights below are the original bundle the `script/sample/` launchers load.