---
title: LynnReal-Onmi-beta-0.1
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/LynnReal-Onmi-beta-0.1"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/LynnReal-Onmi-beta-0.1.md"
repository: AI-ModelScope/LynnReal-Onmi-beta-0.1
last_updated: 2026-09-23
license: other
parameters: 240.6B
tensor_type:
- U8
- BF16
- I8
- F8_E4M3
- F16
- F32
library_name:
- safetensors
- diffusers
- pytorch
frameworks:
- pytorch
downloads: 190
stars: 2
tags:
- "arxiv:2609.15863"
---
# LynnReal-Onmi-beta-0.1
> LynnReal-Onmi-beta-0.1 - AI-ModelScope 在 ModelScope 开源的模型。LynnReal-Omni · Standard four-step + Flash three-step 🎬
AI-ModelScope/LynnReal-Onmi-beta-0.1 是 ModelScope 魔搭社区上的 240.6B 参数机器学习模型，采用 other 许可。
- **Repository**: AI-ModelScope/LynnReal-Onmi-beta-0.1
- **License**: other
- **Parameters**: 240.6B
- **Tags**: arxiv:2609.15863
- **Downloads**: 190
- **Stars**: 2
- **Last updated**: 2026-09-23
Source: https://www.modelscope.cn/models/AI-ModelScope/LynnReal-Onmi-beta-0.1
---
# LynnReal-Omni · Standard four-step + Flash three-step 🎬
**One model for text-to-video, image-to-video, body- and hand-pose control, omni-reference
generation, video editing, frame-by-frame repair and streaming long video — generated with four
denoiser forwards per clip.**
**⚡🔥 The Flash three-step variant now runs in ComfyUI too: a five-second 1344×768 clip with
native stereo audio in ~8.4 s on a single H100 — see [ComfyUI](#comfyui--start-here)!**
[Code](https://github.com/LynnReal-AI/LynnReal-Omni) · [Paper](https://arxiv.org/abs/2609.15863) · [YouTube demo](https://www.youtube.com/watch?v=P5Bl2mriEmk) · [Bilibili demo](https://www.bilibili.com/video/BV12vYB6BEjc/)
## Recommended models for limited VRAM
For limited VRAM, we strongly recommend **Standard Lite** when preserving Standard quality, or
**Flash Lite** for the smallest model footprint and fastest generation. Choose the matching Lite
checkpoint and `*_lite.json` ComfyUI workflow:
| Priority | Workflow | DiT checkpoint |
| --- | --- | --- |
| Preserve Standard quality | `*_4step_lite.json`, **4 steps** | Standard Lite BF16 (**37.6 GiB**) or INT8 (**20.4 GiB**) |
| Minimize memory and generate quickly | `*_flash_3_step_lite.json`, **3 steps** | Flash Lite INT8 (**16.7 GiB**), with the Light VAE |
Keep the shipped step count for each Lite model. These are DiT file sizes, not total runtime VRAM;
the text encoder, VAEs and intermediate tensors also require memory.
🆕 Latest updates
*Newest first — the full history is in [CHANGELOG.md](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/CHANGELOG.md).*
- **2026-09-19 · Standard Lite — exact four-step BF16 and INT8 checkpoints.** The optional
BF16 checkpoint is **37.6 GiB instead of 61.7 GiB**, and the INT8 checkpoint is **20.4 GiB
instead of 44.5 GiB**. With the current node pack and the five `*_4step_lite.json` workflows,
every sampler state and denoiser output from all four steps is bit-identical to the original
checkpoint for t2v, i2v, r2v, pose2v and v2v (`max |Δ| = 0`, seed `970000`). **Keep Standard
Lite at 4 steps; other step counts are not validated.**
- **2026-09-19 · Flash Lite — the same three-step model in 16.7 GiB instead of 37.0 GiB.**
[`lynnreal_omni_flash_int8_lite.safetensors`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/models/diffusion_models)
is an optional Flash checkpoint whose adaLN step table stores the exact modulation vectors the
three-step schedule visits: **−55% on disk, −20.4 GiB of VRAM**, same speed, and the same frames
as the original Flash at the same seed. Open one of the new `*_lite.json` workflows — no flags.
**Keep Flash Lite at 3 steps; other step counts are not validated.**
- **2026-09-18 · ComfyUI node pack fix — Flash no longer crashes on DynamicVRAM machines.**
`RuntimeError: aimdo memory compile error` (torch ≥ 2.8 with a cu13x build, e.g. an RTX 5090)
is fixed. 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 needed.
- **2026-09-17 · Flash three-step in the ComfyUI bundle.** Three Flash workflows (text → video,
first frame → video, references → video), the Light VAE loader and the INT8 switch node:
5 s at 1344×768 warm in ≈8.4 s on one H100 80 GB.
- **2026-09-16 · Standard four-step ComfyUI port.** Five workflows (t2v, i2v, r2v, pose2v, v2v)
with their demo inputs: 5 s at 1344×768 warm in ≈50 s on one H100 80 GB.
- **2026-09-15 · Initial beta.** Diffusers-format weights, the ComfyUI bundle, demo videos and
the paper link.
## Demo
*Compressed preview (≈10 MB, 960×540, audio included). Full-quality demo: [YouTube](https://www.youtube.com/watch?v=P5Bl2mriEmk) · [Bilibili](https://www.bilibili.com/video/BV12vYB6BEjc/) · [paper](https://arxiv.org/abs/2609.15863).*
## ComfyUI 🧩 — start here
The ComfyUI port runs these checkpoints out of the box, with no launcher flags — **Standard
four-step and Flash three-step**. Everything it needs is in this repository: the workflows, the
small custom node pack and the model files, all in ComfyUI format under
[`comfyui/models/`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/models).
1. Copy [`comfyui/custom_nodes/ComfyUI-LynnReal`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/custom_nodes/ComfyUI-LynnReal) into `ComfyUI/custom_nodes/`.
2. Copy the workflows below into `ComfyUI/user/default/workflows/`.
3. Copy the model files under `comfyui/models/` into the matching `ComfyUI/models/` folders
(see the table further down for what each file is).
4. Open a workflow and press **Run**. On one H100 at 1344×768, a warm five-second video takes
**≈50 s with the Standard 4-step model and ≈8.4 s with Flash**.
| Task | Workflow | Node pack | Demo input |
|---|---|---|---|
| Text → video + audio | [`t2v_lynnreal_4step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/t2v_lynnreal_4step.json) | — | — |
| First frame → video | [`i2v_lynnreal_4step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/i2v_lynnreal_4step.json) | — | `transparent_rgb_gaming_mouse.png` |
| Reference images → video | [`r2v_lynnreal_4step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/r2v_lynnreal_4step.json) | — | `red_superboy_on_city_roof.png`, `mecha_dragon_lightning.png` |
| Pose control clip → video | [`pose2v_lynnreal_4step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/pose2v_lynnreal_4step.json) | required | `pose_boxing_first.png`, `pose_boxing_control.mp4` |
| Video continuation | [`v2v_lynnreal_4step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/v2v_lynnreal_4step.json) | — | `snowboard.mp4` |
| **⚡ Flash** text → video + audio | [`t2v_lynnreal_flash_3_step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/t2v_lynnreal_flash_3_step.json) | required | — |
| **⚡ Flash** first frame → video | [`ti2v_lynnreal_flash_3_step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/ti2v_lynnreal_flash_3_step.json) | required | `beauty_first_frame.png` |
| **⚡ Flash** references → video | [`ref2v_lynnreal_flash_3_step.json`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/workflows/ref2v_lynnreal_flash_3_step.json) | required | `beauty_reference_a.png`, `beauty_reference_b.png` |
The five Standard tasks also have matching `*_4step_lite.json` workflows. They require the current
node pack and preserve the same BF16/INT8 switch while selecting the two Standard Lite checkpoints.
The demo inputs sit next to the workflows under `comfyui/input/`.
[`comfyui/README.md`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/README.md)
documents every file each task loads, the optional INT8 switch and the VRAM behaviour; the
workflows are also in the [GitHub repository](https://github.com/LynnReal-AI/LynnReal-Omni/tree/main/comfyui).
### ⚡🔥 Flash three-step is live, and it is fast!
The three Flash workflows run the W8A8 Flash DiT at its trained **three** steps with the Light
A lighter variant of the same checkpoint, [`lynnreal_omni_flash_int8_lite.safetensors`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/models/diffusion_models), cuts the weight file to **16.7 GiB from 37.0 GiB (−55%, −20.4 GiB of VRAM)** at the same speed and the same
frames at the same seed; load it with the `*_lite.json` workflows.
VAE! On **one H100 80 GB** at 1344×768, warm — model already loaded, the way a session runs —
with 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** —
three denoiser steps and both decoders included — on a **single** GPU. `generate` is the
Generate-wall convention used throughout this project (first denoiser forward to decoded frames);
`click-to-video` is what you actually wait for, prompt encoding and muxing included. Repeat runs
agree to ±0.02 s!
Weights:
[`comfyui/models/diffusion_models/lynnreal_omni_flash_int8.safetensors`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/models/diffusion_models/lynnreal_omni_flash_int8.safetensors)
and
[`comfyui/models/vae/lynnreal_omni_light_vae_fp16.safetensors`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/models/vae/lynnreal_omni_light_vae_fp16.safetensors).
> [!WARNING]
> Videos longer than 11 seconds are not usable in the ComfyUI Flash path yet — the accelerated
> path for long clips is still being fixed.
Nothing is assumed about the card it lands on: the node pack picks the fastest attention it can
find and verifies it numerically (FlashAttention-3 → FA2 → cuDNN SDPA → native), falls back to
ComfyUI's own block math when a fused kernel is unavailable, and tunes the INT8 GEMMs for the GPU
it actually runs on!
> [!WARNING]
> **The ComfyUI port is experimental and under active construction 🚧** — it runs the same
> checkpoints and schedules, but the pipeline around them is ComfyUI's. Same-seed output is not
> comparable between the two engines: compare quality, not pixel identity. The Flash three-step
> checkpoint and its Light VAE are already here, with the three workflows above; videos longer
> than 11 seconds are not usable in that path yet.
## What the model does
LynnReal-Omni connects controllable visual workflows through one shared multimodal diffusion
transformer (32B, following the MiniMax H3 architecture). A native packing layout distinguishes
appearance references, frame-aligned controls and causal history, so a single checkpoint covers:
| Generate | Control | Edit & repair |
|---|---|---|
| Text-to-video and first-frame conditioning | Single- and multiple-subject references | Instruction-guided image editing |
| Video continuation | Body- and hand-pose control | Video appearance editing |
| Speech and video generation | Game- and mesh-video rendering | General frame-by-frame video repair |
Long video is generated in chunks that condition on the preceding context and emit 17 new frames
per step, with a fixed head-overlap interface that bounds continuation memory. This release also
contains the **Standard DiT in ComfyUI format** ([`comfyui/models/`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/models)),
including an optional W8A8 INT8 checkpoint built from the same weights.
On a single H100, warm generation and decoding of a 22-frame 540p clip takes 843 ms with the
Standard model and 377 ms with Flash, using the original scripts; Flash, a 27B three-step variant
with a lightweight VAE decoder, is the path toward real-time streaming.
## Files in this repository
| File | Size | Where it goes (ComfyUI) |
|---|---|---|
| `comfyui/models/diffusion_models/lynnreal_omni_standard_bf16.safetensors` | 61.7 GiB | `models/diffusion_models/` |
| `comfyui/models/diffusion_models/lynnreal_omni_standard_bf16_lite.safetensors` | **37.6 GiB** | `models/diffusion_models/` (optional Standard Lite) |
| `comfyui/models/diffusion_models/lynnreal_omni_standard_int8.safetensors` | 44.5 GiB | `models/diffusion_models/` (optional, INT8 switch) |
| `comfyui/models/diffusion_models/lynnreal_omni_standard_int8_lite.safetensors` | **20.4 GiB** | `models/diffusion_models/` (optional Standard Lite) |
| `comfyui/models/diffusion_models/lynnreal_omni_flash_int8.safetensors` | 37.0 GiB | `models/diffusion_models/` (Flash workflows) |
| `comfyui/models/diffusion_models/lynnreal_omni_flash_int8_lite.safetensors` | **16.7 GiB** | `models/diffusion_models/` (Flash workflows, optional — `*_lite.json`) |
| `comfyui/models/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors` | 14.6 GiB | `models/text_encoders/` |
| `comfyui/models/vae/minimax_h3_video_vae_fp16.safetensors` | 4.9 GiB | `models/vae/` |
| `comfyui/models/vae/lynnreal_omni_light_vae_fp16.safetensors` | 3.6 GiB | `models/vae/` (Flash workflows) |
| `comfyui/models/vae/minimax_h3_audio_vae_fp32.safetensors` | 577 MiB | `models/vae/` |
| `comfyui/models/embeddings/minimaxh3_art_is_explosion.safetensors` | 500 KiB | `models/embeddings/` |
| `assets/lynnreal-demo-preview.mp4` | 9.4 MiB | — (demo preview) |
The diffusers-format bundle (transformer shards, text encoder, VAE and schedulers) stays at the
repository root and is what the `script/sample/` launchers in the GitHub repository load.
## More
- **Setup, tasks and launchers (reference implementation):** [GitHub README](https://github.com/LynnReal-AI/LynnReal-Omni#quick-start)
- **ComfyUI bundle details:** [comfyui/README.md](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/README.md) · [end-to-end verification record](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/blob/main/comfyui/VERIFICATION.md)
- **Flash (three-step) weights:** [stdstu123/LynnReal-Onmi-flash-beta-0.1](https://huggingface.co/stdstu123/LynnReal-Onmi-flash-beta-0.1) · in ComfyUI format under [`comfyui/models/`](https://huggingface.co/stdstu123/LynnReal-Onmi-beta-0.1/tree/main/comfyui/models)
- **Lightweight VAE:** [stdstu123/LynnReal-Onmi-light-vae](https://huggingface.co/stdstu123/LynnReal-Onmi-light-vae)
This is an early beta: bugs, compatibility issues and inconsistent generation quality may remain.
We plan to release the training code, part of the training data and a more efficient DiT.
Issues and pull requests are welcome. 🙌
## Acknowledgments
We thank the MiniMax H3 team for the model that forms the foundation of LynnReal-Omni, and Qwen3-VL
for the multimodal encoder, tokenizer and processor implementation used for conditioning. Model
licenses and upstream attribution are retained in the bundle; see [LICENSE](LICENSE).