microsoft/Florence-2-base-ft
Image-to-Text
β’
Updated
β’
12.6k
β’
59
a tiny vision language model
Efficient quantized retrieval over Wikipedia
State-of-the-art open-vocabulary image segmentation β‘οΈ
High-quality virtual try-on ~ Your cyber fitting room
Experiment with and compare different tokenizers
Zero-Shot Material Transfer from a Single Image
High-fidelity Virtual Try-on
Track, rank and evaluate open LLMs and chatbots