Open-vocabulary detector that draws boxes around objects named in a free-text prompt, without a fixed class list.
google/owlv2-base-patch16-ensemble
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelObject detection155M paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.Apache 2.0Single armMobile baseDrone
About
CLIP-based zero-shot detector from Google that localizes objects from text queries or from an example image crop.
Why it matters for physical AI
Image-conditioned queries let a robot find 'more of this object' from a single reference photo.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download google/owlv2-base-patch16-ensembleUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
Open-vocabulary perception on a Jetson Orin: what's your pipeline?
Grounding DINO for boxes followed by SAM 2.1 for masks is a common language-driven pick-and-place front end.
More object detection
Browse allSmall real-time DETR-style detector for the 80 COCO classes that refines box edges as distributions for tighter localization.