Model reference · open weights

siglip2-patch16-style-naflex

siglip2-patch16-style-naflex is an open-weight embedding model from ostris, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings ostris 1 variants 121 downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What siglip2-patch16-style-naflex is

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.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerostris
TypeEmbedding models
Parameters (lead)93M
Variants1
Runs withtransformers
Released2026-05-23
Popularity121 downloads / month
Likes4
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
siglip2-base-patch16-style-naflex93MBF16~0.2 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys siglip2-patch16-style-naflex for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (siglip2-patch16-style-naflex below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"siglip2-patch16-style-naflex","input":"text to embed"}'

Details

Languages, data & research

Tags

transformers safetensors siglip2_vision_model feature-extraction vision zero-shot-image-classification endpoints_compatible

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want siglip2-patch16-style-naflex on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms