README.md

---
tags:
- text-to-image
library_name: diffusers
license: apache-2.0
---

# DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
<div style="text-align: center;">
  <a href="https://arxiv.org/abs/2504.12364"><img src="https://img.shields.io/badge/arXiv-2504.12364-b31b1b.svg" alt="arXiv"></a>
  <a href="https://huggingface.co/papers/2504.12364"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/paper-page-sm.svg" alt="Paper page"></a>
</div>

## Introduction
We propose a score distillation based model merging paradigm DMM, compressing multiple models into a single versatile T2I model.
![](assets/method.jpg)

This checkpoint merges pre-trained models from many different domains, including *realistic style, Asian portrait, anime style, illustration, etc*.
Specifically, the source models are listed below:

- [JuggernautReborn](https://civitai.com/models/46422)
- [MajicmixRealisticV7](https://civitai.com/models/43331)
- [EpicRealismV5](https://civitai.com/models/25694)
- [RealisticVisionV5](https://civitai.com/models/4201)
- [MajicmixFantasyV3](https://civitai.com/models/41865)
- [MinimalismV2](https://www.liblib.art/modelinfo/8b4b7eb6aa2c480bbe65ca3d4625632d?from=personal_page&versionUuid=4b8e98cc17fc49ed826af941060ffd0b)
- [RealCartoon3dV17](https://civitai.com/models/94809)
- [AWPaintingV1.4](https://civitai.com/models/84476)


## Visualization

![](assets/visualization.jpg)

### Results

![](assets/results.jpg)

### Results combined with charactor LoRA

![](assets/results-lora.jpg)

### Results of interpolation between two styles

![](assets/results-interp.jpg)


## Online Demo
https://huggingface.co/spaces/MCG-NJU/DMM .

## Usage

Please refer to https://github.com/MCG-NJU/DMM .

```python
import torch
from modeling.dmm_pipeline import StableDiffusionDMMPipeline

pipe = StableDiffusionDMMPipeline.from_pretrained("path/to/pipeline/checkpoint", torch_dtype=torch.float16, use_safetensors=True)
pipe = pipe.to("cuda")

# select model index
model_id = 5
output = pipe(
    prompt="portrait photo of a girl, long golden hair, flowers, best quality",
    negative_prompt="worst quality,low quality,normal quality,lowres,watermark,nsfw",
    width=512,
    height=512,
    num_inference_steps=25,
    guidance_scale=7,
    model_id=model_id,
).images[0]
```