---
language:
  - en
  - zh
base_model_relation: quantized
tags:
  - image-generation
  - multimodal
  - qwen
  - quantized
  - nunchaku
  - comfyui
library_name: diffusers
pipeline_tag: text-to-image
base_model: Qwen/Qwen-Image-2512
license: apache-2.0
---

<!-- QF-LICENSE-BLOCK:START -->
## License & Attribution

These are **quantized derivative weights** of [`Qwen/Qwen-Image-2512`](https://huggingface.co/Qwen/Qwen-Image-2512) (**Qwen-Image-2512**).

- **Modifications:** the original weights were quantized (e.g. W4A4 / FP4 / INT4 / FP8) and
  repackaged for the QuantFunc inference engine — a "modification" under Apache-2.0 §4(b).
- **License:** Apache License 2.0 (inherited from the base model), included as [`LICENSE`](./LICENSE). Upstream copyright and attribution notices are retained.
- This repository is **not affiliated with or endorsed by** the upstream model authors.

> **Disclaimer:** "Nunchaku" / "SVDQuant" name the *quantization method/format* (the open-source SVDQuant work by MIT HAN Lab, Apache-2.0). This repository is an independent re-quantization and is **not affiliated with, sponsored by, or endorsed by MIT HAN Lab or the Nunchaku project**. Official Nunchaku releases are under the `nunchaku-ai` / `nunchaku-tech` namespaces.
<!-- QF-LICENSE-BLOCK:END -->

# QuantFunc

<div align="center" style="margin-top: 50px;">
  <img src="assets/logo.webp" width="300" alt="Logo">
</div>

<p align="center">
  🤗 <a href="https://huggingface.co/QuantFunc">Hugging Face</a> &nbsp;|&nbsp;
  🤖 <a href="https://www.modelscope.cn/profile/QuantFunc">ModelScope</a> &nbsp;|&nbsp;
  💻 <a href="https://github.com/RealJonathanYip/ComfyUI-QuantFunc">GitHub</a> &nbsp;|&nbsp;
  💬 <a href="#wechat">WeChat (微信)</a> &nbsp;|&nbsp;
  🎮 <a href="https://discord.gg/jCp9TpFWcn">Discord</a>
</p>

> ⚡ **Qwen-Image-2512 — SVDQ (Nunchaku) pre-quantized text-to-image.** **2x–11x faster** with the QuantFunc plugin; 100% Nunchaku-ComfyUI compatible.

Offline-quantized **Qwen-Image-2512** text-to-image checkpoints in **best-quality / balanced / ultimate-speed** variants (INT4 & FP4), ready to drop straight into ComfyUI.

**Powered by the [QuantFunc ComfyUI plugin](https://github.com/RealJonathanYip/ComfyUI-QuantFunc) — the fastest diffusion inference engine:**

- 🚀 **2x–11x speedup** over standard BF16/FP16 Python pipelines (pre-exported → even faster loading).
- ⚙️ **Native C++/CUDA** (`libquantfunc.so` / `quantfunc.dll`) with **zero Python model dependencies**.
- 🧩 **Dual engine** (SVDQ offline + Lighting runtime 4-bit), **zero-cost LoRA stacking**, reference-image editing & inpainting.
- 🟢 **Full GPU coverage** — RTX 20/30/40/50 · A100/H100/H200/B100/B200/GB300 · RTX 6000 Ada / PRO Blackwell (CUDA 12 & 13); native **FP4** on Blackwell.

👉 **Install the plugin:** **https://github.com/RealJonathanYip/ComfyUI-QuantFunc**

## Introduction

We are excited to share our latest model series based on <strong>nunchaku + qwen-image-2512</strong> quantization. These models are carefully optimized to maintain high-quality output while significantly improving inference speed and efficiency. <strong>All models are 100% compatible with the nunchaku-comfyui && lora plugin</strong> and can be used directly in ComfyUI.

## Gallery

<div align="center">

<table>
  <tr>
    <td align="center"><img src="assets/ComfyUI_00006_.png" alt="Result 6" style="max-width: 300px;"></td>
    <td align="center"><img src="assets/ComfyUI_00010_.png" alt="Result 3" style="max-width: 300px;"></td>
  </tr>
  <tr>
    <td align="center"><img src="assets/ComfyUI_00019_.png" alt="Result 1" style="max-width: 300px;"></td>
    <td align="center"><img src="assets/ComfyUI_00051_.png" alt="Result 2" style="max-width: 300px;"></td>
  </tr>
  <tr>
    <td align="center"><img src="assets/ComfyUI_00040_.png" alt="Result 4" style="max-width: 300px;"></td>
    <td align="center"><img src="assets/ComfyUI_00048_.png" alt="Result 5" style="max-width: 300px;"></td>
  </tr>
</table>

</div>

## Model Checkpoints

| Name | low_rank | Notes |
|:---|:---:|:---|
| nunchaku_qwen_image_2512_best_quality_fp4 | 256 | Best quality model, suitable for scenarios with extremely high quality requirements |
| nunchaku_qwen_image_2512_best_quality_int4 | 256 | Best quality model, suitable for scenarios with extremely high quality requirements |
| nunchaku_qwen_image_2512_ultimate_speed_int4 | 32 | Ultimate speed model, prioritizing inference speed |
| nunchaku_qwen_image_2512_ultimate_speed_fp4 | 32 | Ultimate speed model, prioritizing inference speed |
| nunchaku_qwen_image_2512_balance_int4 | 128 | Balanced model, achieving the best balance between quality and speed |
| nunchaku_qwen_image_2512_balance_fp4 | 128 | Balanced model, achieving the best balance between quality and speed |

## 4 steps workflow

Here’s a <a href="https://huggingface.co/QuantFunc/Nunchaku-Qwen-Image-2512/tree/main">workflow</a> example of integrating 4-step LoRA in ComfyUI. If you don’t need 4-step LoRA, simply remove the LoRA node.
<img src="assets/workflow_image.png" alt="work flow" style="max-width: 800px;">

## Coming Soon

If you encounter any issues during use, feel free to join our community for feedback:
- Join our [Discord server](https://discord.gg/jCp9TpFWcn)
- Scan the QR code below to join our WeChat group

We will add support for build in lora and qwen-image-edit-2511 in approximately one month.

<div align="center" id="wechat">
  <img src="https://raw.githubusercontent.com/RealJonathanYip/ComfyUI-QuantFunc/main/assets/WeChat.jpg" alt="WeChat Group" style="max-width: 300px;">
</div>