metadata
title: README
emoji: 🧥
colorFrom: indigo
colorTo: green
sdk: static
pinned: false
license: mit
short_description: Open-source fashion intelligence and visual search.
HopitAI
HopitAI builds open-source fashion intelligence models for visual search, product matching, catalog retrieval, and ecommerce discovery.
MODA Fashion Retrieval
MODA is a family of fashion image retrieval models designed to turn product and outfit images into useful embeddings for similarity search.
Try the interactive demo · View the GitHub repo · Start with DeepFashion2
Featured Models
| Model | Best for |
|---|---|
| MODA-Fashion-Distilled | Best overall quality |
| MODA-Fashion-Distilled-512d | Compact vector search indexes |
| MODA-Fashion-DeepFashion2 | Simple reproducible recipe |
| MODA-Fashion-Vision-FP16 | Smaller edge and mobile deployment |
| MODA-Fashion-Matryoshka | Flexible embedding dimensions |
Quick Start
huggingface-cli download HopitAI/moda-fashion-deepfashion2 --local-dir ./moda-fashion-deepfashion2
import open_clip
model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms(
"hf-hub:HopitAI/moda-fashion-deepfashion2"
)
Use Cases
- Find visually similar products in a fashion catalog.
- Match street-style looks to shoppable items.
- Deduplicate product images across marketplaces.
- Build embedding indexes for ecommerce search and recommendations.