No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from baidu/ERNIE-Image-Aes
All models by baidu β
[π Paper]
ERNIE-Image-Aes is a 8B vision-language model for image aesthetic scoring, initialized from ArtiMuse and fine-tuned on a diverse, professionally annotated dataset. It substantially outperforms existing aesthetic predictors (LAION-AES, ArtiMuse, UniPercept) in generalization across diverse image categories.
Key advantages:
Off-the-shelf aesthetic predictors exhibit systematic biases:
ERNIE-Image-Aes addresses these failure modes through a purpose-built annotation pipeline with explicit category balance.
Annotation Protocol:
Please follow the setup instructions in the ArtiMuse repository.
Our work builds upon ArtiMuse and InternVL-3. We sincerely thank the authors for their excellent contributions to the community.
If you find this work useful, please consider citing: