Grounding DINO Demo
💻
110
Cutting edge open-vocabulary object detection app
Foundation Models for Vision
-
-
Owlv2
👀94State-of-the-art Zero-shot Object Detection
-
openai/clip-vit-base-patch32
Zero-Shot Image Classification • Updated • 14.6M • 828 -
openai/clip-vit-large-patch14
Zero-Shot Image Classification • 0.4B • Updated • 7.9M • 1.94k -
google/pix2struct-large
Image-to-Text • 1B • Updated • 737 • 34 -
google/pix2struct-ai2d-base
Visual Question Answering • 0.3B • Updated • 1.59k • 43 -
HuggingFaceM4/idefics-80b-instruct
Text Generation • 80B • Updated • 2.18k • 189 -
BLIP2 with transformers
🌖41BLIP2 (cutting edge image captioning) in 🤗transformers