This is the classifier model for predicting the anime-style stable-diffusion-generated images are corrupted or not.
Modellquelle
Quellenbeschreibung
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.
Quellen
1 QuelleVerifiziert 28. Sept.
Modellartefakte
6 Artefaktecaformer_s36_v0_focal/model.ckpt
ckpt · 157 MB · SHA-256 3268bf908470…d7e6 · Hugging Face
Herunterladencaformer_s36_v0_focal/model.onnx
onnx · 143 MB · SHA-256 ae63bb14ab82…b5b4 · Hugging Face
HerunterladenQuellenauszüge
2 Auszüge| Name | FLOPS | Params | Accuracy | AUC | Confusion | Labels |
|---|
| caformer_s36_v0_focal | 22.10G | 37.21M | 95.65% | 0.9916 | confusion | corrupted, normal |
| caformer_s36_v0_sce | 22.10G | 37.21M | 95.77% | 0.9894 | confusion | corrupted, normal |
| mobilenetv3_v0_focal_dist | 0.63G | 4.18M | 94.02% | 0.9842 | confusion | corrupted, normal |
You can use this model with dghs-imgutils.
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}
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.
@misc{Citation,
title={AI-Corrupt Score for Anime Images},
author={narugo1992},
year={2023},
howpublished={\url{https://huggingface.co/deepghs/ai_image_corrupted}}
}
caformer_s36_v0_sce/model.ckpt
ckpt · 157 MB · SHA-256 1e8d5d4946c7…8fe1 · Hugging Face
mobilenetv3_v0_focal_dist/model.ckpt
ckpt · 30,6 MB · SHA-256 51595a9c67e8…7968 · Hugging Face
Herunterladenmobilenetv3_v0_focal_dist/model.onnx
onnx · 16,0 MB · SHA-256 8b1b50ff2d97…7b7d · Hugging Face
Herunterladen--- license: openrail metrics: - accuracy pipeline_tag: image-classification tags: - art datasets: - deepghs/ai_image_corrupted library_name: dghs-imgutils --- 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}} } ```
Source context: 0 downloads · 0 likes · Pipeline image-classification · Library dghs-imgutils · Repo Library-Mutsumi/ai_image_corrupted