Vision Foundation Models
for the Tree of Life

Bridging computer vision and biology. BioCLIP models learn hierarchical representations of the natural world, enabling advanced species classification, trait prediction, and more.

Which BioCLIP component do you need?

Models

Choose the right BioCLIP model from the latest BioCLIP 2 (ViT-L/14) to BioCAP and the original BioCLIP (ViT-B/16).

Go to Models →

Training Data

Explore TreeOfLife datasets for training biological vision models, from 10M to 214M images across hundreds of thousands of taxa.

Go to Training Data →

Benchmarks

Evaluate your model on biologically relevant benchmarks, including Rare Species and IDLE-OO Camera Traps.

Go to Benchmarks →

Software

Use pybioclip, TreeOfLife-toolbox, TaxonoPy, and other tools for data processing or to integrate BioCLIP into your Python code or computational pipeline.

Go to Software →

Demos

Try interactive demos for zero-shot classification and open-ended species identification without writing any code.

Go to Demos →

Papers

Read the research papers behind BioCLIP, BioCLIP 2, BioCAP, and the TreeOfLife datasets.

Go to Papers →
Repository

Hugging Face Collection

The central warehouse for all BioCLIP assets. This collection aggregates all versions of the models, the training datasets, benchmarks, and interactive demos.

Use this if you need direct access to raw model weights (SafeTensors/PyTorch), want to access the TreeOfLife or benchmark datasets, or are looking for easy by-image predictions.

  • Models: BioCLIP, BioCLIP 2, BioCAP, BioCLIP 2.5 Huge.
  • Datasets: TreeOfLife-200M, TreeOfLife-10M, TreeOfLife-10M Captions.
  • Benchmarks: Rare Species, IDLE-OO Camera Traps.
  • Demos: Interactive Gradio apps for zero-shot and open-ended classification.
Browse Collection
🤗 Data, Models, and Demos