---
title: T2I-Distill
canonical_url: "https://www.modelscope.cn/models/DAMO_Academy/T2I-Distill"
md_url: "https://www.modelscope.cn/models/DAMO_Academy/T2I-Distill.md"
repository: DAMO_Academy/T2I-Distill
last_updated: 2025-12-31
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 84
stars: 0
---

# T2I-Distill

> T2I-Distill - DAMO_Academy 在 ModelScope 开源的模型。T2I-Distill: Few-Step Distillation for Text-to-Image Generation

- **Repository**: DAMO_Academy/T2I-Distill
- **Downloads**: 84
- **Stars**: 0
- **Last updated**: 2025-12-31

Source: https://www.modelscope.cn/models/DAMO_Academy/T2I-Distill

---

# T2I-Distill: Few-Step Distillation for Text-to-Image Generation

This repository contains the official checkpoints for the paper **"Few-Step Distillation for Text-to-Image Generation: A Practical Guide"**.

## 📄 Paper Information

- **Title**: Few-Step Distillation for Text-to-Image Generation: A Practical Guide
- **ArXiv**: [2512.13006](https://huggingface.co/papers/2512.13006)

## 💻 Usage

### Download the models

You can download the models directly from this repository using the `huggingface_hub` library:

```python
from huggingface_hub import snapshot_download

model_path = snapshot_download(repo_id="Alibaba-DAMO-Academy/T2I-Distill")
print(f"Model downloaded to: {model_path}")