---
title: ai_image_corrupted
canonical_url: "https://www.modelscope.cn/models/deepghs/ai_image_corrupted"
md_url: "https://www.modelscope.cn/models/deepghs/ai_image_corrupted.md"
repository: deepghs/ai_image_corrupted
last_updated: 2024-12-04
license: openrail
pipeline_tag: image-classification
tasks:
  - image-classification
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
downloads: 1230
stars: 0
tags:
  - art
---

# ai_image_corrupted

> ai_image_corrupted - deepghs 在 ModelScope 开源的模型。This is the classifier model for predicting the anime-style stable-diffusion-generated images are corrupted or not.

deepghs/ai_image_corrupted 是 ModelScope 魔搭社区上的image-classification模型，采用 openrail 许可。

- **Repository**: deepghs/ai_image_corrupted
- **License**: openrail
- **Tasks**: image-classification
- **Tags**: art
- **Downloads**: 1230
- **Stars**: 0
- **Last updated**: 2024-12-04

Source: https://www.modelscope.cn/models/deepghs/ai_image_corrupted

---

This is the classifier model for predicting the anime-style stable-diffusion-generated images are corrupted or not.

Trained on dataset [deepghs/ai_image_corrupted](https://huggingface.co/datasets/deepghs/ai_image_corrupted).

## Models

|           Name            |  FLOPS  |  Params  |  Accuracy  |  AUC   |                                                       Confusion                                                       |        Labels         |
|:-------------------------:|:-------:|:--------:|:----------:|:------:|:---------------------------------------------------------------------------------------------------------------------:|:---------------------:|
|   caformer_s36_v0_focal   | 22.10G  |  37.21M  |   95.65%   | 0.9916 |   [confusion](https://huggingface.co/deepghs/ai_image_corrupted/blob/main/caformer_s36_v0_focal/plot_confusion.png)   | `corrupted`, `normal` |
|    caformer_s36_v0_sce    | 22.10G  |  37.21M  |   95.77%   | 0.9894 |    [confusion](https://huggingface.co/deepghs/ai_image_corrupted/blob/main/caformer_s36_v0_sce/plot_confusion.png)    | `corrupted`, `normal` |
| mobilenetv3_v0_focal_dist |  0.63G  |  4.18M   |   94.02%   | 0.9842 | [confusion](https://huggingface.co/deepghs/ai_image_corrupted/blob/main/mobilenetv3_v0_focal_dist/plot_confusion.png) | `corrupted`, `normal` |

## How to Use

You can use this model with [dghs-imgutils](https://dghs-imgutils.deepghs.org/main/api_doc/generic/classify.html).

```python
from imgutils.generic import classify_predict_score

classify_predict_score(
    'sample_image.png',
    repo_id='deepghs/ai_image_corrupted',
    model_name='mobilenetv3_v0_focal_dist',
)
# {'corrupted': 0.7807788848876953, 'normal': 0.2192210853099823}
```

## Note

This model is trained on SD1.5 images, generated by 8 different base models.

So the better solution for this problem is to use some metrics like artstyle embeddings, 
this model will be deprecated as soon as the artstyle embedding model for anime images is completed.

## Citation

```
@misc{Citation,
  title={AI-Corrupt Score for Anime Images},
  author={narugo1992},
  year={2023},
  howpublished={\url{https://huggingface.co/deepghs/ai_image_corrupted}}
}
```