A BioCLIP 2.5-H wing classifier for Neotropical butterflies and moths.
This page is the inference API. Try the model in the web app:
Upload a butterfly or moth photo and get a hierarchical ID (genus ▸ species ▸ subspecies). A frozen BioCLIP 2.5-H backbone feeds a cosine/ArcFace head trained on Sanger/Ikiam specimens, museum photographs and research-grade iNaturalist observations; a YOLO26-seg model first crops the photo to the wings (masks from SAM 3), and an optional side-of-Andes / country prior re-ranks the result.
Coverage: about 4,100 Neotropical butterfly species across all major families and about 8,000 moth species (mainly Erebidae, Sphingidae, Geometridae, Saturniidae, Crambidae and Noctuidae), 11,965 species in total. Moth training photos are museum and specimen images plus research-grade iNaturalist observations. Confident calls on sparsely sampled groups (skippers, hairstreaks, small moths) warrant extra caution, and mimetic Ithomiini subspecies are genuinely hard to tell apart.
/health· liveness + mode (real/mock)/metadata· label space + whether the wing-crop loaded/predict_raw· images[] → top-64 leaf probs + wing masks/predict· images[] + prior → marginalised rankscurl -F images=@butterfly.jpg \ https://fr4nzzch-butterfly-id.hf.space/predict_raw
The trained classifier head + wing-cropper are downloadable (CC-BY-NC-4.0) from fr4nzzch/butterfly-id-classifier. The frozen BioCLIP 2.5-H backbone is upstream at imageomics/bioclip-2.5-vith14.
The subspecies-level taxonomic identifications used to train the classifier were compiled from Butterflies of America, Sangay, Noreste, and Cotacachi.