---
title: Unipic3-DMD
canonical_url: "https://www.modelscope.cn/models/Skywork/Unipic3-DMD"
md_url: "https://www.modelscope.cn/models/Skywork/Unipic3-DMD.md"
repository: Skywork/Unipic3-DMD
last_updated: 2026-02-07
license: mit
pipeline_tag: any-to-any
tasks:
  - any-to-any
parameters: 8.4B
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 109
stars: 0
tags:
  - text-to-image
  - image-editing
  - image-understanding
  - vision-language
  - multimodal
  - unified-model
---

# Unipic3-DMD

> Unipic3-DMD - Skywork 在 ModelScope 开源的模型。🌌 Unipic3-DMD-Model(Distribution Matching Distillation)

Skywork/Unipic3-DMD 是 ModelScope 魔搭社区上的 8.4B 参数any-to-any模型，采用 mit 许可。

- **Repository**: Skywork/Unipic3-DMD
- **License**: mit
- **Tasks**: any-to-any
- **Parameters**: 8.4B
- **Tags**: text-to-image, image-editing, image-understanding, vision-language, multimodal, unified-model
- **Downloads**: 109
- **Stars**: 0
- **Last updated**: 2026-02-07

Source: https://www.modelscope.cn/models/Skywork/Unipic3-DMD

---

## 🌌 Unipic3-DMD-Model(Distribution Matching Distillation)
<div align="center">   
  <img src="skywork-logo.png" alt="Skywork Logo" width="500"> 
</div>

<p align="center">
  <a href="https://github.com/SkyworkAI/UniPic">
    <img src="https://img.shields.io/badge/GitHub-UniPic-blue?logo=github" alt="GitHub Repo">
  </a>
  <a href="https://github.com/SkyworkAI/UniPic/stargazers">
    <img src="https://img.shields.io/github/stars/SkyworkAI/UniPic?style=social" alt="GitHub Stars">
  </a>
  <a href="https://github.com/SkyworkAI/UniPic/network/members">
    <img src="https://img.shields.io/github/forks/SkyworkAI/UniPic?style=social" alt="GitHub Forks">
  </a>
</p>

## 📖 Introduction
<div align="center"> <img src="unipic3.png" alt="Model Teaser" width="720"> </div>

**UniPic3-DMD-Model** is a few-step image editing and multi-image composition model trained using **Distribution Matching Distillation (DMD)**.
The model directly matches the **output distribution of a high-quality teacher model**, enabling sharp, visually detailed generations in very few inference steps.  
It is designed to maximize **perceptual quality and realism**, closely imitating strong proprietary or large teacher models. This model is initialized from a consistency-trained checkpoint and further refined via distribution-level distillation.

## 📊 Benchmarks
<div align="center"> <img src="unipic3_eval.png" alt="Model Teaser" width="720"> </div>


## 🧠 Usage

### 1. Clone the Repository
```bash
git clone https://github.com/SkyworkAI/UniPic
cd UniPic-3
```

### 2. Set Up the Environment
```bash
conda create -n unipic python=3.10
conda activate unipic3
pip install -r requirements.txt
```


### 3.Batch Inference
```bash
transformer_path = "Skywork/Unipic3-DMD/ema_transformer"

python -m torch.distributed.launch --nproc_per_node=1 --master_port 29501 --use_env \
    qwen_image_edit_fast/batch_inference.py \
    --jsonl_path data/val.jsonl \
    --output_dir work_dirs/output \
    --distributed \
    --num_inference_steps 8 \
    --true_cfg_scale 4.0 \
    --transformer transformer_path \
    --skip_existing
```

## 📄 License
This model is released under the MIT License.

## Citation
If you use Skywork UniPic 3.0 in your research, please cite:
```
@article{wei2026skywork,
  title={Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling},
  author={Wei, Hongyang and Liu, Hongbo and Wang, Zidong and Peng, Yi and Xu, Baixin and Wu, Size and Zhang, Xuying and He, Xianglong and Liu, Zexiang and Wang, Peiyu and others},
  journal={arXiv preprint arXiv:2601.15664},
  year={2026}
}
```