Product
Platform
Universe
Annotate
Auto Label
Train
Deploy
Inference
Integrations
Ecosystem
Notebooks
Autodistill
Supervision
Multimodal Maestro
Open Source
Roboflow Labeling
Solutions
BY INDUSTRY
Aerospace & Defense
Agriculture
Healthcare & Medicine
Automotive
Banking & Finance
Government
Oil and Gas
Retail & Ecommerce
Safety & Security
Telecommunications
Transportation
Manufacturing
Utilities
Resources
Contact Sales
User Forum
Inference Templates
Blog
Explore Models
Pricing
Docs
Talk to Sales
Sign in
Product
Platform
Universe
Annotate
Auto Label
Train
Deploy
Inference
Integrations
Ecosystem
Notebooks
Autodistill
Supervision
Multimodal Maestro
Open Source
Roboflow Labeling
Solutions
BY INDUSTRY
Aerospace & Defense
Agriculture
Healthcare & Medicine
Automotive
Banking & Finance
Government
Oil and Gas
Retail & Ecommerce
Safety & Security
Telecommunications
Transportation
Manufacturing
Utilities
Developers
Contact Sales
User Forum
Inference Templates
Blog
Explore Models
Pricing
Contact Sales
Top Zero-Shot Object Detection Models
Zero-shot object detection models let you detect objects using an open vocabulary without training a custom model.
Filter Models
Search Models
Filter By Task
All Models
Object Detection
Classification
Instance Segmentation
Semantic Segmentation
Keypoint Detection
Vision-Language
OCR
Filter By Feature
Foundation Vision
Multimodal Vision
LLMS with Vision Capabilities
Image Embedding
Real-Time Vision
Zero-shot Detection
Image Captioning
Image Similarity
Image Tagging
Visual Question Answering
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Apply
Deploy select models (i.e. YOLOv8, CLIP) using the Roboflow Hosted API, or your own hardware using
Roboflow Inference
.
Showing
of
models.
YOLO-World
YOLO-World is a zero-shot object detection model.
Object Detection
Deploy with Roboflow
MetaCLIP
MetaCLIP is a zero-shot classification and embedding model developed by Meta AI.
Classification
Deploy with Roboflow
OWLv2
OWLv2 is a transformer-based object detection model developed by Google Research. OWLv2 is the successor to OWL ViT.
Object Detection
Deploy with Roboflow
OWL ViT
OWL-ViT is a transformer-based object detection model developed by Google Research.
Object Detection
Deploy with Roboflow
BLIPv2
BLIPv2 is a multimodal model developed by Salesforce Research.
Classification
Deploy with Roboflow
Visual Question Answering
Image Tagging
Image Similarity
Image Captioning
Zero-shot Detection
Real-Time Vision
Image Embedding
LLMS with Vision Capabilities
Multimodal Vision
Foundation Vision