Zero-Shot Image Classification
Transformers
Safetensors
siglip2_vision_model
feature-extraction
vision
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("ostris/siglip2-base-patch16-style-naflex")
model = AutoModel.from_pretrained("ostris/siglip2-base-patch16-style-naflex", device_map="auto")Quick Links
SigLIP 2 Style naflex
This is a finetune of the vision model of google/siglip2-base-patch16-naflex.
It has been finetuned on over 90k styles with 4-5 images per style using an arcface loss with patch lengths of (256, 576, 784, 1024). The arcface head has been removed. The pooled embedding should now
function as a style embedding.
- Downloads last month
- 104
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="ostris/siglip2-base-patch16-style-naflex") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )