---
library_name: diffusers
pipeline_tag: text-to-image
license: other
tags:
  - SiD-DiT
  - score-distillation
  - flow-matching
  - text-to-image
base_model:
  - stabilityai/stable-diffusion-3-medium-diffusers
---

<h1 align="center">
  SiD-DiT: Score Distillation of Flow Matching Models
</h1>



<p align="left">

  <!-- HF demo -->
  <a href="https://yigu1008.github.io/SiD-DiT/demo.html">
    <img src="https://img.shields.io/badge/Demo-Huggingface-ffd21e?style=for-the-badge&logo=huggingface" />
  </a>

  <!-- Code repo -->
  <a href="https://github.com/apple/ml-sid-dit">
    <img src="https://img.shields.io/badge/Code-GitHub-181717?style=for-the-badge&logo=github" />
  </a>

  <!-- Project page -->
  <a href="https://yigu1008.github.io/SiD-DiT/">
    <img src="https://img.shields.io/badge/Project-Page-555555?style=for-the-badge" />
  </a>

  <!-- Arxiv -->
  <a href="https://arxiv.org/abs/2509.25127">
    <img src="https://img.shields.io/badge/arXiv-SiD--DIT-b31b1b?style=for-the-badge" />
  </a>


</p>

## Model Card

SiD-DiT is a score-distillation pipeline for pretrained text-to-image
flow-matching models. We introduce a general framework that can accelerate sampling in flow-matching models by 
distilling pretrained flow-matching teachers into high-quality few-step students, providing a principled way to 
unify acceleration techniques across both diffusion- and flow-based generators.

## Installation

```bash
# download model files from this repo
git clone https://huggingface.co/YGu1998/SiD-DiT-SD3-medium

# install packages

cd SiD_pipelines
pip install -r requirements.txt
cd ..
```

## Inference with SiD-DiT

```python
import torch
from SiD_pipelines import SiDSD3Pipeline


if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

model_repo_id = "YGu1998/SiD-DiT-SD3-medium"

prompt = ["a studio portrait of an elderly woman smiling, soft window light, 85mm lens"]

pipe = SiDSD3Pipeline.from_pretrained(
    model_repo_id,
    torch_dtype=torch_dtype,
).to(device)

generator = torch.Generator(device=device).manual_seed(42)


image = pipe(
    prompt=prompt,
    guidance_scale=1.0,
    num_inference_steps=4,
    width=1024,
    height=1024,
    generator=generator,
    time_scale=1000,
).images[0]

image.save("example.png")
```


## License
- **Base model:** `stabilityai/stable-diffusion-3-medium-diffusers`
- **Base license:** Stability AI **Non-Commercial Research Community License**
  (`stabilityai-nc-research-community`)

This checkpoint is a **non-commercial research derivative** of Stable Diffusion 3 Medium
and **inherits the same license**. You may only use these weights under the terms of the
Stability AI Non-Commercial Research Community License. In particular, commercial or
revenue-generating use (including production services, internal business tooling intended
for commercial advantage, or hosted APIs) requires an appropriate commercial license from
Stability AI.

This repository does not grant any additional rights beyond the base model license.
You are responsible for ensuring that your use of this checkpoint complies with the
Stability AI license and applicable law.