Try the Model

Use the widget below to experiment with BLIP. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

BLIP (Bootstrapping Language-Image Preprocessing) is a multimodal model developed by Salesforce Research. BLIP can be used for visual question answering and image classification. BLIP has been superseded by BLIPv2, also maintained by Salesforce Research.

BLIP License

BLIP

is licensed under a

BSD-3-Clause

license.

Performance

Deploy a BLIP API

You can use Roboflow Inference to deploy a

BLIP

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with BLIP

You can automatically label a dataset using BLIP with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use BLIP to train a computer vision model.

No items found.