---
title: MPS
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/MPS"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/MPS.md"
repository: AI-ModelScope/MPS
chinese_name: "图像生成-多维度人类偏好模型"
last_updated: 2025-04-23
license: "Apache License 2.0"
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - clip
architectures:
  - CLIPModel
library_name:
  - pytorch
frameworks:
  - Pytorch
inference_backends:
  - "deploy_task vlm"
  - "sglang 0.5.2"
downloads: 51953
stars: 2
---

# MPS

> MPS - AI-ModelScope 在 ModelScope 开源的模型。Multi-dimensional Preference Score (MPS). Github链接https://github.com/Kwai-Kolors/MPS

AI-ModelScope/MPS 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 Apache License 2.0 许可，可用 deploy_task vlm、sglang 0.5.2 部署。

- **Repository**: AI-ModelScope/MPS
- **License**: Apache License 2.0
- **Tasks**: image-text-to-text
- **Inference backends**: deploy_task vlm, sglang 0.5.2
- **Downloads**: 51953
- **Stars**: 2
- **Last updated**: 2025-04-23

Source: https://www.modelscope.cn/models/AI-ModelScope/MPS

---

# Learning Multi-dimensional Human Preference for Text-to-Image Generation (CVPR 2024)

## MPS (Multi-dimensional Preference Score)

Github: https://github.com/Kwai-Kolors/MPS

评价多维度文生图生成模型的偏好分数。

- `MPS_overall_checkpoint.pth` 文件包含整体权重和可执行代码。
- `MPS_overall_state_dict.pt` 文件只包含整体权重。

#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('AI-ModelScope/MPS')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/AI-ModelScope/MPS.git
```