---
title: SenseNova-U1-8B-MoT-Interleaved
canonical_url: "https://www.modelscope.cn/models/SenseNova/SenseNova-U1-8B-MoT-Interleaved"
md_url: "https://www.modelscope.cn/models/SenseNova/SenseNova-U1-8B-MoT-Interleaved.md"
repository: SenseNova/SenseNova-U1-8B-MoT-Interleaved
last_updated: 2026-06-12
license: apache-2.0
pipeline_tag: any-to-any
tasks:
  - any-to-any
model_type:
  - neo_chat
architectures:
  - NEOChatModel
parameters: 17.6B
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 100
stars: 0
tags:
  - multimodal
  - text-to-image
  - image-to-text
  - image-editing
  - interleaved-generation
  - custom_code
---

# SenseNova-U1-8B-MoT-Interleaved

> SenseNova-U1-8B-MoT-Interleaved - SenseNova 在 ModelScope 开源的模型。SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

SenseNova/SenseNova-U1-8B-MoT-Interleaved 是 ModelScope 魔搭社区上的 17.6B 参数any-to-any模型，采用 apache-2.0 许可。

- **Repository**: SenseNova/SenseNova-U1-8B-MoT-Interleaved
- **License**: apache-2.0
- **Tasks**: any-to-any
- **Parameters**: 17.6B
- **Tags**: multimodal, text-to-image, image-to-text, image-editing, interleaved-generation, custom_code
- **Downloads**: 100
- **Stars**: 0
- **Last updated**: 2026-06-12

Source: https://www.modelscope.cn/models/SenseNova/SenseNova-U1-8B-MoT-Interleaved

---

# SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

<p align="center">
  <strong>English</strong> | <a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/blob/main/README_CN.md">简体中文</a>
</p>

<p align="center">
  <a href="https://arxiv.org/abs/2605.12500"><img src="https://img.shields.io/badge/arXiv-2605.12500-b31b1b.svg" alt="arXiv"></a>
  <a href="https://github.com/OpenSenseNova/SenseNova-U1/tree/main" target="_blank"><img src="https://img.shields.io/badge/SenseNova_U1-Code-100000?style=flat-square&logo=github&logoColor=white" alt="SenseNova-U1" /></a>
  <a href="https://huggingface.co/collections/sensenova/sensenova-u1"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Model-yellow" alt="HuggingFace Model"></a>
  <a href="https://modelscope.cn/collections/SenseNova/SenseNova-U1"><img src="https://img.shields.io/badge/%F0%9F%A4%96%20ModelScope-模型-purple" alt="ModelScope-模型"></a>
  <a href="https://unify.light-ai.top/"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20SenseNova_U1-Demo-Green" alt="SenseNova-U1 Demo"></a>
  <a href="./LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License"></a>
  <a href="https://discord.com/invite/BuTXPHmQub"><img src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
</p>

<p align="center">
  <img src="docs/assets/teaser.webp" alt="SenseNova-U1" width="900">
</p>

<p align="center">
  <img src="docs/assets/teaser_2.webp" alt="visualization" width="900">
</p>

## 📣 Updated News
- `[2026.06.11]` Release [SenseNova-U1-8B-MoT-Interleaved 📖](https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved), specially optimized for interleaved image-text generation, with notably improved narrative coherence, character and style consistency, and text-image alignment in multi-page content such as picture books, story books, multi-page PPTs, and illustrated tutorials.

<details>
<summary>✨ Click to expand older news</summary>

- `[2026.05.15]` Release [SenseNova-U1-8B-MoT-Infographic 📊](https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Infographic), for improved infographic generation. See [U1 Infographic Model](docs/u1_infographic_model.md) for details, and [✨ Infographic Showcases ](docs/u1_infographic_showcases.md) for 100 generated examples.

- `[2026.05.10]` Release [🔥SenseNova-U1 Technical Report🔥](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/pdf/SenseNOVA_U1.pdf) and the weights for [SenseNova-U1-A3B-MoT-SFT](https://huggingface.co/sensenova/SenseNova-U1-A3B-MoT-SFT) & [SenseNova-U1-A3B-MoT](https://huggingface.co/sensenova/SenseNova-U1-A3B-MoT).

- `[2026.05.08]` Add **GGUF quantized checkpoints** and **layer-offload VRAM modes** for low-VRAM single-GPU inference. See [Memory-efficient inference](#-memory-efficient-inference-gguf--vram-modes). GGUF weights for `SenseNova-U1-8B-MoT-Merger` are available at [🤗 smthem/SenseNova-U1-8B-MoT-Merger-gguf](https://huggingface.co/smthem/SenseNova-U1-8B-MoT-Merger-gguf) — many thanks to [@smthem](https://github.com/smthem) for contributing the quantized weights.

- `[2026.05.06]` Release [SenseNova-U1-8B-MoT-LoRA-8step-V1.0](https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-LoRAs/blob/main/SenseNova-U1-8B-MoT-LoRA-8step-V1.0.safetensors). Please see the [example script](docs/base_vs_distill.md#run-base-and-distilled-model).

- `[2026.04.30]` Release the preview version of the 8-step inference model [SenseNova-U1-8B-MoT-8step-preview](https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-8step-preview). In most cases, the image generation quality of this model closely matches that of the base model (see [comparison and existing issues](docs/base_vs_distill.md)). To test this model, you can use the [inference scripts](examples/README.md), but with the following parameters: ```--cfg_scale 1.0 --num_steps 8``` .

- `[2026.04.27]` Initial release of the weights for [SenseNova-U1-8B-MoT-SFT](https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-SFT) and [SenseNova-U1-8B-MoT](https://huggingface.co/sensenova/SenseNova-U1-8B-MoT).

- `[2026.04.27]` Initial release of the [inference code](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/examples/README.md) for SenseNova-U1.  

</details>

## 🌟 Overview

🚀 **SenseNova U1** is a new series of native multimodal models that unifies multimodal understanding, reasoning, and generation within a monolithic architecture. 
It marks a fundamental paradigm shift in multimodal AI: **from modality integration to true unification**. Rather than relying on adapters to translate between modalities, SenseNova U1 models think-and-act across language and vision natively.

Unifying visual understanding and generation in an end-to-end architecture from pixel to word opens tremendous possibilities, enabling highly efficient and strong understanding, generation, and interleaved reasoning in a natively multimodal manner.

<p align="center">
  <img src="docs/assets/teaser_1.webp" alt="radar plot" width="900">
</p>

## 🎨 Interleaved Showcases

Side-by-side comparison between the base **SenseNova-U1-8B-MoT** and **SenseNova-U1-8B-MoT-Interleaved** on interleaved image-text generation. With interleaved-specific optimization, the new model delivers stronger narrative coherence, character and style consistency, and text-image alignment across multi-page outputs.

<details open>
<summary>📖 Illustrated Tutorial</summary>

<table>
  <tr>
    <th align="center" width="50%">SenseNova-U1-8B-MoT</th>
    <th align="center" width="50%">SenseNova-U1-8B-MoT-Interleaved</th>
  </tr>
  <tr>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/教程_case1_8bmot_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/教程_case1_8bmot_隐藏think.webp"></a></td>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/教程_case1_interleaved_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/教程_case1_interleaved_隐藏think.webp"></a></td>
  </tr>
  <tr>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/教程_case2_8bmot_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/教程_case2_8bmot_隐藏think.webp"></a></td>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/教程_case2_interleaved_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/教程_case2_interleaved_隐藏think.webp"></a></td>
  </tr>
</table>

</details>

<details open>
<summary>📚 Story Book</summary>

<table>
  <tr>
    <th align="center" width="50%">SenseNova-U1-8B-MoT</th>
    <th align="center" width="50%">SenseNova-U1-8B-MoT-Interleaved</th>
  </tr>
  <tr>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/故事_case1_8bmot_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/故事_case1_8bmot_隐藏think.webp"></a></td>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/故事_case1_interleaved_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/故事_case1_interleaved_隐藏think.webp"></a></td>
  </tr>
  <tr>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/故事_case2_8bmot_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/故事_case2_8bmot_隐藏think.webp"></a></td>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/故事_case2_interleaved_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/故事_case2_interleaved_隐藏think.webp"></a></td>
  </tr>
</table>

</details>

<details open>
<summary>🎨 Drawing</summary>

<table>
  <tr>
    <th align="center" width="50%">SenseNova-U1-8B-MoT</th>
    <th align="center" width="50%">SenseNova-U1-8B-MoT-Interleaved</th>
  </tr>
  <tr>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/画画_case1_8bmot_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/画画_case1_8bmot_隐藏think.webp"></a></td>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/画画_case1_interleaved_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/画画_case1_interleaved_隐藏think.webp"></a></td>
  </tr>
</table>

</details>

<details open>
<summary>📑 Presentation / PPT</summary>

**Single-page PPT** — base vs Interleaved:

<table>
  <tr>
    <th align="center" width="50%">SenseNova-U1-8B-MoT</th>
    <th align="center" width="50%">SenseNova-U1-8B-MoT-Interleaved</th>
  </tr>
  <tr>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/PPT_单页case2_8bmot_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/PPT_单页case2_8bmot_隐藏think.webp"></a></td>
    <td align="center" valign="top"><a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/PPT_单页case2_interleaved_隐藏think.webp"><img width="100%" src="docs/assets/showcases/interleave/PPT_单页case2_interleaved_隐藏think.webp"></a></td>
  </tr>
</table>

**Multi-page PPT** — a new capability unique to SenseNova-U1-8B-MoT-Interleaved (not supported by the base model):

<p align="center">
  <a href="https://huggingface.co/sensenova/SenseNova-U1-8B-MoT-Interleaved/resolve/main/docs/assets/showcases/interleave/PPT_多页case3_interleaved_隐藏think.webp"><img width="60%" src="docs/assets/showcases/interleave/PPT_多页case3_interleaved_隐藏think.webp"></a>
</p>

</details>


## 🛠️ Quick Start


### 🌐 Use with SenseNova-Studio

The fastest way to experience SenseNova-U1 is through **[SenseNova-Studio](https://unify.light-ai.top/)** — a 🆓 free online playground where you can try the model directly in your browser, no installation or GPU required.

> **Note:** To serve more users, U1-Fast has undergone step and CFG distillation, and is dedicated to infographic generation.


### 🦞 Use with SenseNova-Skills (OpenClaw)

The easiest way to integrate SenseNova-U1 into your own agent or application is through our companion repository **[SenseNova-Skills (OpenClaw) 🦞](https://github.com/OpenSenseNova/SenseNova-Skills)**, which ships SenseNova-U1 as a ready-to-use skill with a unified tool-calling interface.

> Refer to the [SenseNova-Skills README](https://github.com/OpenSenseNova/SenseNova-Skills) for installation and usage details.

<details>
<summary>✨ Some interesting cases produced through our Skills and Studio</summary>

<p align="center">
  <img src="docs/assets/showcases/t2i_infographic/u1-case2.webp" alt="Skill Cases">
</p>

</details>

### 🤗 Run with transformers (Default)

> **Setup:** Follow the [Installation Guide](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/installation.md) to clone the repo and install dependencies with [uv](https://github.com/astral-sh/uv).

<details open>
<summary>♻️ Interleaved Generation</summary>

```bash
python examples/interleave/inference.py --model_path sensenova/SenseNova-U1-8B-MoT-Interleaved --prompt "I want to learn how to cook tomato and egg stir-fry. Please give me a beginner-friendly illustrated tutorial." --resolution "16:9" --output_dir outputs/interleave/ --stem demo --profile
```
</details>

> See [`examples/README.md`](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/examples/README.md) for batched inference, JSONL format, prompt enhancement, resolution buckets, and full flag reference.

> See [`docs/gpu_mem_profiler.md`](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/gpu_mem_profiler.md) for GPU memory profiler.


### ⚡ Run with LightLLM + LightX2V (Recommended)

For production serving, we co-design a dedicated inference stack on top of **[LightLLM](https://github.com/ModelTC/lightllm)** (understanding) and **[LightX2V](https://github.com/ModelTC/lightx2v)** (generation). The two engines are disaggregated so that each path can use its own parallelism and resource budget, with a low-overhead transfer channel in between.

On a single node with `TP2 + CFG2`, this stack delivers roughly **~0.15 s/step** and **~9 s end-to-end** for a **2048×2048** image on H100 / H200, with a ~**2.4–3.2×** prefill speedup from our FA3-based hybrid-mask attention over the Triton baseline. Full per-GPU performance are reported in [`docs/inference_infra.md`](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/inference_infra.md).

An official docker image is provided for one-command deployment:

```bash
docker pull lightx2v/lightllm_lightx2v:20260407
```

> ⚙️ **Deployment guide (Docker, launch flags, modes, quantization, API test):** see [`docs/deployment.md`](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/deployment.md).
>
> 📖 **Full design and performance profiling:** see [`docs/inference_infra.md`](https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/inference_infra.md).

<!-- ## 🖊️ Citation

```bibtex
``` -->

## 🌐 Join the Community!

Join our growing community to share feedback, get support, and stay updated on the latest SenseNova-U1 developments — we'd love to hear from you!

<div align="center">
<table>
  <tr>
    <td align="center"><b><a href="https://discord.com/invite/BuTXPHmQub">Discord</a></b></td>
    <td align="center"><b>WeChat Group</b></td>
  </tr>
  <tr>
    <td align="center"><a href="https://discord.com/invite/BuTXPHmQub"><img src="docs/assets/discord_qr.webp" width="160"/></a></td>
    <td align="center"><img src="docs/assets/wechat_qr.webp" width="160"/></td>
  </tr>
</table>
</div>
## ⚖️ License

This project is released under the [Apache 2.0 License](./LICENSE).