Models (3)
425K76
A ViT-H/14 CLIP-style vision foundation model for the tree of life, scaling BioCLIP 2 to a larger backbone and expanded TreeOfLife-200M data for zero-shot species classification.
Imaging
4247K76
A CLIP-style vision foundation model for the tree of life, trained on 214M organism images across 952K taxa for zero-shot and few-shot species classification and broader biological visual tasks.
Imaging
23819.1K267
A CLIP-style vision foundation model for the tree of life, trained on TreeOfLife-10M for zero-shot and few-shot species classification of plants, animals, and fungi from images.
Imaging