siglip2-giant-opt-patch16-384

by google

Multilingual vision-language encoder with dense features and localization

1.2Mdl/month

1Bparams

HuggingFace Use in Pipeline

Identifiers

Model ID

google/siglip2-giant-opt-patch16-384

Feature URI

mixpeek://image_extractor@v1/google_siglip2_giant_v1

Overview

SigLIP 2 extends the sigmoid contrastive objective with captioning-based pretraining, self-supervised losses, and online data curation into a unified recipe. It produces stronger vision-language encoders with significantly improved localization and dense feature quality.

On Mixpeek, SigLIP 2 provides the strongest zero-shot visual embeddings from Google, achieving 85.0% ImageNet accuracy at the giant scale. Its improved spatial understanding makes it ideal for tasks requiring localization alongside retrieval.

Architecture

Vision Transformer (ViT-g) with ~1B parameters at 384px resolution. Combines sigmoid contrastive loss with captioning, self-distillation, and masked prediction objectives. Supports multi-resolution and native aspect ratio inputs.

Mixpeek SDK Integration

import { Mixpeek } from "mixpeek";

const mx = new Mixpeek({ apiKey: "API_KEY" });

await mx.collections.ingest({
  collection_id: "my-collection",
  source: { url: "https://example.com/image.jpg" },
  feature_extractors: [{
    name: "image_embedding",
    version: "v1",
    params: { model_id: "google/siglip2-giant-opt-patch16-384" }
  }]
});