This model is a fine-tuned SigLIP variant optimized for fashion and product imagery. It supports zero-shot image classification and multimodal retrieval tasks common in e-commerce. Hosted on Hugging Face, it can be used with OpenCLIP or Transformers libraries for building visual search and recommendation systems.
In the Other AI space, Marqo fashionSigLIP takes a focused approach. It focuses on performing accurate zero-shot image classification and retrieval specifically for fashion and e-commerce product images. Marqo fashionSigLIP is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
Behind Marqo fashionSigLIP is Marqo, and it first shipped in 2024. Development happens publicly on GitHub with 139 stars. Key capabilities include Zero-shot Classification, Fashion Understanding, and Image-Text Alignment.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match