---
title: ImageMetrics
canonical_url: "https://www.modelscope.cn/models/DiffSynth-Studio/ImageMetrics"
md_url: "https://www.modelscope.cn/models/DiffSynth-Studio/ImageMetrics.md"
repository: DiffSynth-Studio/ImageMetrics
last_updated: 2026-06-01
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 30.6B
tensor_type:
  - BF16
  - I64
  - F16
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 18062
stars: 0
---

# ImageMetrics

> ImageMetrics - DiffSynth-Studio 在 ModelScope 开源的模型。本仓库包含了接入 DiffSynth-Studio 的多款主流图像质量评估模型权重。支持图文语义对齐、人类视觉偏好、纯图像美学以及数据集分布等多个维度的评测。

DiffSynth-Studio/ImageMetrics 是 ModelScope 魔搭社区上的 30.6B 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可。

- **Repository**: DiffSynth-Studio/ImageMetrics
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 30.6B
- **Downloads**: 18062
- **Stars**: 0
- **Last updated**: 2026-06-01

Source: https://www.modelscope.cn/models/DiffSynth-Studio/ImageMetrics

---

# 图像质量评估模型


本仓库包含了接入 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) 的多款主流图像质量评估模型权重。支持图文语义对齐、人类视觉偏好、纯图像美学以及数据集分布等多个维度的评测。

## 评估效果效果展示

> **prompt**: A cat is sitting on a stone.

| 评估指标 | ![](./assets/image1.jpg) | ![](./assets/image2.jpg) |
|:---:|:---:|:---:|
| Pickscore | 22.958 | **23.321** |
| ImageReward | 1.419 | **1.786** |
| HPSv2 | 30.169 | **30.528** |
| HPSv3 | 12.287 | **12.969** |
| CLIP Score | **40.271** | 39.065 |
| Aesthetic | 5.096 | **5.848** |
| UnifiedReward | 'alignment': 4.5, 'coherence': 4.0, 'style': 3.5 | 'alignment': 4.0, 'coherence': 4.0, 'style': 3.5 |

---

## 指标总览

|指标名称|输入要求|输出结果|
|-|-|-|
|PickScore|prompt + PIL 图像|人类视觉偏好分数|
|ImageReward|prompt + PIL 图像|人类视觉偏好分数|
|HPSv2|prompt + PIL 图像|人类视觉偏好分数|
|HPSv3|prompt + PIL 图像|人类视觉偏好分数|
|CLIP Score|prompt + PIL 图像|图文相似度|
|Aesthetic|PIL 图像|美学分数|
|UnifiedReward|prompt + PIL 图像|多维评分|
|FID|参考图目录 + 生成图目录|分布距离|


## 快速使用

* 安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)

```
git clone https://github.com/modelscope/DiffSynth-Studio.git
cd DiffSynth-Studio
pip install -e .
```

* 示例 1：使用 PickScore 评估图文偏好

```python
from diffsynth.metrics import PickScoreMetric, ModelConfig
from modelscope import dataset_snapshot_download
from PIL import Image

dataset_snapshot_download(
    "DiffSynth-Studio/diffsynth_example_dataset",
    allow_file_pattern="flux/FLUX.1-dev/*",
    local_dir="./data/diffsynth_example_dataset",
)
image = Image.open("data/diffsynth_example_dataset/flux/FLUX.1-dev/1.jpg").convert("RGB")
prompt = "a dog"
metric = PickScoreMetric.from_pretrained(
    model_config=ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="PickScore/model.safetensors"),
    device="cuda"
)
score = metric.compute(prompt, image)[0]
print(f"PickScore score:: {score:.3f}")
```

* 示例 2：使用 Aesthetic 评估纯美学质量

```python
from diffsynth.metrics import AestheticMetric, ModelConfig
from modelscope import dataset_snapshot_download
from PIL import Image

dataset_snapshot_download(
    "DiffSynth-Studio/diffsynth_example_dataset",
    allow_file_pattern="flux/FLUX.1-dev/*",
    local_dir="./data/diffsynth_example_dataset",
)
image = Image.open("data/diffsynth_example_dataset/flux/FLUX.1-dev/1.jpg").convert("RGB")
metric = AestheticMetric.from_pretrained(
    model_config=ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="Aesthetic/model.safetensors"),
    device="cuda"
)
score = metric.compute(image)[0]
print(f"Aesthetic score: {score:.3f}")
```

关于所有指标的详细使用方法和说明，请参考 DiffSynth-Studio 的相关[文档](https://github.com/modelscope/DiffSynth-Studio/blob/main/docs/zh/Model_Details/Image-Quality-Metrics.md)。