metadata
tags:
- vision
- text-to-image
- endpoints-template
inference: true
pipeline_tag: text-to-image
base_model: Salesforce/blip-image-captioning-base
library_name: generic
Fork of Salesforce/blip-image-captioning-base for a text-to-image Inference endpoint.
Based on https://huggingface.co/sergeipetrov/blip_captioning
This repository implements a custom task for text-to-image for 🤗 Inference Endpoints to allow image capturing.
The code for the customized pipeline is in the handler.py.
To use deploy this model an Inference Endpoint you have to select Custom as task to use the handler.py file.
expected Request payload
Image to be labeled as binary.
CURL
curl URL \
-X POST \
--data-binary @car.png \
-H "Content-Type: image/png"
Python
requests.post(ENDPOINT_URL, headers={"Content-Type": "image/png"}, data=open("car.png", 'rb').read()).json()