README.md

---
title: README
emoji: 📈
colorFrom: green
colorTo: red
sdk: static
pinned: false
---

# VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
    
<div align="center">
  
[[Paper](https://arxiv.org/abs/2504.07960)] &emsp; [[Project Page](https://visualcloze.github.io/)] &emsp; [[Github](https://github.com/lzyhha/VisualCloze)]

</div>

<div align="center">

[[🤗 Online Demo](https://huggingface.co/spaces/VisualCloze/VisualCloze)] &emsp; [[🤗 Dataset Card](https://huggingface.co/datasets/VisualCloze/Graph200K)]

</div>

<div align="center">
  
[[🤗 Model Card (<strong><span style="color:hotpink">Diffusers</span></strong>)](https://huggingface.co/VisualCloze/VisualClozePipeline-384)] &emsp; [[🤗 Model Card (<strong><span style="color:hotpink">LoRA</span></strong>)](https://huggingface.co/VisualCloze/VisualCloze/)]

</div>

## 📰 News
- [2025-4-21] 👋👋👋 We have implemented a version of [diffusers](https://github.com/lzyhha/diffusers/tree/main/src/diffusers/pipelines/visualcloze) that makes it easier to use the model through **pipelines** of the diffusers. For usage guidance, please refer to the [Model Card](https://huggingface.co/VisualCloze/VisualClozePipeline-384).

## 🌠 Key Features

An in-context learning based universal image generation framework. 

1. Support various in-domain tasks.
2. Generalize to <strong><span style="color:hotpink"> unseen tasks</span></strong> through in-context learning. 
3. Unify multiple tasks into one step and generate both target image and intermediate results. 
4. Support reverse-engineering a set of conditions from a target image.

🔥 Examples are shown in the [project page](https://visualcloze.github.io/).