# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("NEXTAltair/cache_aestheic-shadow-v2")
model = AutoModelForImageClassification.from_pretrained("NEXTAltair/cache_aestheic-shadow-v2")Quick Links
Aesthetic Shadow V2 Mirror
English
This is a mirror of shadowlilac/aesthetic-shadow-v2.
Model Description
- Visual Transformer with 1.09B parameters
- Evaluates 1024x1024 high-resolution images
- Specialized in anime image quality assessment
Score Interpretation
- very aesthetic: ≥0.71
- aesthetic: 0.45-0.71
- displeasing: 0.27-0.45
- very displeasing: ≤0.27
Notice
This model is redistributed under the CC-BY-NC-4.0 license with acknowledgment to the original author.
Credit
Original model: shadowlilac/aesthetic-shadow-v2
Japanese
このモデルはshadowlilac/aesthetic-shadow-v2のミラーです。
モデルの説明
- 11億パラメータのビジュアルトランスフォーマー
- 1024x1024の高解像度画像を評価
- アニメ画像の品質評価に特化
スコアの解釈
- very aesthetic: 0.71以上
- aesthetic: 0.45～0.71
- displeasing: 0.27～0.45
- very displeasing: 0.27以下
注意事項
このモデルは元の作者の許可の下、CC-BY-NC-4.0ライセンスに従って再配布されています。
クレジット
Original model: shadowlilac/aesthetic-shadow-v2
- Downloads last month
- 10
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="NEXTAltair/cache_aestheic-shadow-v2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")