Aller au contenu
ModelPrésentéExterne
Télécharger

Siglip2 Base Patch16 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...

TypeOtherVersionRevision 22707c0

Source du modèle

Type
Other
Taille du fichier
355 MB
Version
vRevision 22707c0
Mis à jour
17 sept. 2026
Téléchargements
24
Source
Hugging Face

Description de la source

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.

Sources

1 source
Hugging FacePrincipalVersion 22707c00d4671ecf5cc0fc7606ed6f6955704ea8
huggingface.co/ostris/siglip2-base-patch16-style-naflex/tree/22707c00d4671ecf5cc0fc7606ed6f6955704ea8

Vérifié 17 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 355 MB · SHA-256 d786f94dc050…5098 · Hugging Face

Télécharger

Extraits de sources

2 extraits

--- license: apache-2.0 tags: - vision library_name: transformers pipeline_tag: zero-shot-image-classification --- # SigLIP 2 Style naflex This is a finetune of the vision model of [google/siglip2-base-patch16-naflex](https://huggingface.co/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.

Source context: 24 downloads · 4 likes · Pipeline zero-shot-image-classification · Library transformers · Repo ostris/siglip2-base-patch16-style-naflex