Instructions to use nzs234/siglip2-so400m-aesthetic-scorer-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nzs234/siglip2-so400m-aesthetic-scorer-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="nzs234/siglip2-so400m-aesthetic-scorer-v1") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nzs234/siglip2-so400m-aesthetic-scorer-v1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| library_name: transformers | |
| tags: | |
| - image-classification | |
| - aesthetic-scoring | |
| - siglip2 | |
| - custom-code | |
| license: other | |
| # SigLIP2 Aesthetic Scorer (Local Bundle) | |
| This repository contains a standalone local bundle for aesthetic scoring: | |
| - Backbone: `google/siglip2-so400m-patch16-512` (saved locally) | |
| - Head: custom MLP regressor (`head.safetensors`) | |
| - Score range: `1..9` | |
| ## Files | |
| - `backbone/` : local SigLIP2 backbone + processor files | |
| - `head.safetensors` : MLP head weights | |
| - `metadata.json` : model config and score range | |
| ## Output | |
| The model outputs a continuous score, and common usage rounds it to integer `score_1 ... score_9`. | |