Running
59
💻
Grounding DINO Demo
Cutting edge open-vocabulary object detection app
Foundation Models for Vision 🧩
Foundation models for computer vision.
-
-
Running66👀
Owlv2
State-of-the-art Zero-shot Object Detection
-
Runtime error41🌖
BLIP2 with transformers
BLIP2 (cutting edge image captioning) in 🤗transformers
-
Runtime error377🐨
IDEFICS Playground
-
Running120🕯️🎭
Candle Segment Anything Wasm
Segment Anything Model on the Browser with Candle/Rust/WASM
-
Runtime error16🏢
Pix2struct DocVQA
-
openai/clip-vit-large-patch14
Zero-Shot Image Classification • Updated • 29.5M • 1.46k -
openai/clip-vit-base-patch32
Zero-Shot Image Classification • Updated • 23.3M • • 545 -
Salesforce/blip2-flan-t5-xxl
Image-Text-to-Text • Updated • 17.5k • 85 -
Salesforce/blip2-opt-2.7b
Image-Text-to-Text • Updated • 432k • 317 -
google/pix2struct-large
Image-to-Text • Updated • 122k • 34 -
google/pix2struct-docvqa-base
Visual Question Answering • Updated • 9.62k • 37 -
google/pix2struct-docvqa-large
Visual Question Answering • Updated • 487 • 31 -
google/pix2struct-ai2d-base
Visual Question Answering • Updated • 1.14k • 42 -
google/pix2struct-screen2words-base
Visual Question Answering • Updated • 100 • 22 -
google/pix2struct-textcaps-base
Image-to-Text • Updated • 3.63k • 28 -
Running on T4357📚
Grounded Segment Anything
-
HuggingFaceM4/idefics-80b-instruct
Text Generation • Updated • 2.2k • 182 -
HuggingFaceM4/idefics-9b-instruct
Text Generation • Updated • 11.6k • 104 -
HuggingFaceM4/idefics-9b
Text Generation • Updated • 3.41k • 47 -
HuggingFaceM4/idefics-80b
Text Generation • Updated • 172 • 66 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • Updated • 3.29M • 308 -
Runtime error30👀
Compare VLMs
-
Runtime error35💻
Compare Depth Models
Depth Anything (foundation depth model) vs it's predecessors