---
title: MagicQuill-models
canonical_url: "https://www.modelscope.cn/models/ant-research/MagicQuill-models"
md_url: "https://www.modelscope.cn/models/ant-research/MagicQuill-models.md"
repository: ant-research/MagicQuill-models
last_updated: 2024-11-21
license: cc-by-nc-4.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
parameters: 14.5B
tensor_type:
  - I64
  - F32
  - F16
library_name:
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - pytorch
downloads: 11838
stars: 6
---

# MagicQuill-models

> MagicQuill-models - ant-research 在 ModelScope 开源的模型。Model Checkpoints for project.

ant-research/MagicQuill-models 是 ModelScope 魔搭社区上的 14.5B 参数image-to-image模型，采用 cc-by-nc-4.0 许可。

- **Repository**: ant-research/MagicQuill-models
- **License**: cc-by-nc-4.0
- **Tasks**: image-to-image
- **Parameters**: 14.5B
- **Downloads**: 11838
- **Stars**: 6
- **Last updated**: 2024-11-21

Source: https://www.modelscope.cn/models/ant-research/MagicQuill-models

---

Model Checkpoints for [project](https://github.com/magic-quill/MagicQuill).

The paper is [MagicQuill: An Intelligent Interactive Image Editing System](https://huggingface.co/papers/2411.09703).

# MagicQuill: An Intelligent Interactive Image Editing System
mage editing involves a variety of complex tasks and requires efficient and precise manipulation techniques. In this paper, we present MagicQuill, an integrated image editing system that enables swift actualization of creative ideas. Our system features a streamlined yet functionally robust interface, allowing for the articulation of editing operations (e.g., inserting elements, erasing objects, altering color) with minimal input. These interactions are monitored by a multimodal large language model (MLLM) to anticipate editing intentions in real time, bypassing the need for explicit prompt entry. Finally, we apply a powerful diffusion prior, enhanced by a carefully learned two-branch plug-in module, to process editing requests with precise control. Experimental results demonstrate the effectiveness of MagicQuill in achieving high-quality image edits. Please visit https://magic-quill.github.io to try out our system.

```python
#模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('AntResearch/MagicQuill-models')
```

# Git下载
```
git clone https://www.modelscope.cn/AntResearch/MagicQuill-models.git
```