README.md

---
license: cc-by-nc-4.0
library_name: diffusers
tags:
- text-to-image
- stable-diffusion
- diffusion distillation
---

# DMD2 Model Card

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63363b864067f020756275b7/YhssMfS_1e6q5fHKh9qrc.jpeg)

> [**Improved Distribution Matching Distillation for Fast Image Synthesis**](https://arxiv.org/abs/2405.14867),            
> Tianwei Yin, Michaël Gharbi, Taesung Park, Richard Zhang, Eli Shechtman, Frédo Durand, William T. Freeman        

## Contact 

Feel free to contact us if you have any questions about the paper!

Tianwei Yin [tianweiy@mit.edu](mailto:tianweiy@mit.edu)

## Huggingface Demo

Our 4-step (much higher quality, 2X slower) Text-to-Image demo is hosted at [DMD2-4step](https://913f7051c61c070e4e.gradio.live)

Our 1-step Text-to-Image demo is hosted at [DMD2-1step](https://154dfe6ee5c63946cc.gradio.live)

## Usage

We can use the standard diffuser pipeline:

#### 4-step generation 

```.bash
import torch
from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
repo_name = "tianweiy/DMD2"
ckpt_name = "dmd2_sdxl_4step_unet_fp16.bin"
# Load model.
unet = UNet2DConditionModel.from_config(base_model_id, subfolder="unet").to("cuda", torch.float16)
unet.load_state_dict(torch.load(hf_hub_download(repo_name, ckpt_name), map_location="cuda"))
pipe = DiffusionPipeline.from_pretrained(base_model_id, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=4, guidance_scale=0).images[0]
```

#### 1-step generation 

```.bash
import torch
from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
repo_name = "tianweiy/DMD2"
ckpt_name = "dmd2_sdxl_1step_unet_fp16.bin"
# Load model.
unet = UNet2DConditionModel.from_config(base_model_id, subfolder="unet").to("cuda", torch.float16)
unet.load_state_dict(torch.load(hf_hub_download(repo_name, ckpt_name), map_location="cuda"))
pipe = DiffusionPipeline.from_pretrained(base_model_id, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
prompt="a photo of a cat"
image=pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0, timesteps=[399]).images[0]
```

For more information, please refer to the [code repository](https://github.com/tianweiy/DMD2)


## License

Improved Distribution Matching Distillation is released under [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en).


## Citation 

If you find DMD2 useful or relevant to your research, please kindly cite our papers:

```bib
@article{yin2024improved,
    title={Improved Distribution Matching Distillation for Fast Image Synthesis},
    author={Yin, Tianwei and Gharbi, Micha{\"e}l and Park, Taesung and Zhang, Richard and Shechtman, Eli and Durand, Fredo and Freeman, William T},
    journal={arXiv:2405.14867},
    year={2024}
}

@inproceedings{yin2024onestep,
    title={One-step Diffusion with Distribution Matching Distillation},
    author={Yin, Tianwei and Gharbi, Micha{\"e}l and Zhang, Richard and Shechtman, Eli and Durand, Fr{\'e}do and Freeman, William T and Park, Taesung},
    booktitle={CVPR},
    year={2024}
}
```


## Acknowledgments 

This work was done while Tianwei Yin was a full-time student at MIT. It was developed based on our reimplementation of the original DMD paper. This work was supported by the National Science Foundation under Cooperative Agreement PHY-2019786 (The NSF AI Institute for Artificial Intelligence and Fundamental Interactions, http://iaifi.org/), by NSF Grant 2105819, by NSF CISE award 1955864, and by funding from Google, GIST, Amazon, and Quanta Computer.