B
BLIP
salesforce/BLIP
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
★5.7kstars
Jupyter Notebook
BSD-3-Clause
Updated: 1d ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Jupyter Notebook, focusing on image-captioning and image-text-retrieval
Who made it?Maintained by salesforce team, 5.7K⭐ on GitHub, #259 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the salesforce team identified the need for better image-captioning solutions. BLIP was created to simplify image-text-retrieval workflows.
What can it do?Key use cases: vision-and-language-pre-training, vision-language, vision-language-transformer
How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/salesforce/BLIP
🔗 github.com/salesforce/BLIP
Topics
image-captioningimage-text-retrievalvision-and-language-pre-trainingvision-languagevision-language-transformervisual-question-answeringvisual-reasoning