Edit model card

Fork of salesforce/BLIP for a image-captioning task on 🤗Inference endpoint.

This repository implements a custom task for image-captioning for 🤗 Inference Endpoints. The code for the customized pipeline is in the pipeline.py. To use deploy this model a an Inference Endpoint you have to select Custom as task to use the pipeline.py file. -> double check if it is selected

expected Request payload

  "image": "/9j/4AAQSkZJRgABAQEBLAEsAAD/2wBDAAMCAgICAgMC....", // base64 image as bytes

below is an example on how to run a request using Python and requests.

Run Request

  1. prepare an image.
!wget https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg

2.run request

import json
from typing import List
import requests as r
import base64


def predict(path_to_image: str = None):
    with open(path_to_image, "rb") as i:
        image = i.read()
    payload = {
        "inputs": [image],
        "parameters": {
                   "do_sample": True,
    response = r.post(
        ENDPOINT_URL, headers={"Authorization": f"Bearer {HF_TOKEN}"}, json=payload
    return response.json()
prediction = predict(

Example parameters depending on the decoding strategy:

  1. Beam search
        "parameters": {
  1. Nucleus sampling
        "parameters": {
                   "do_sample": True,
  1. Contrastive search
        "parameters": {

See generate() doc for additional detail

expected output

['buckingham palace with flower beds and red flowers']
Downloads last month

Space using florentgbelidji/blip_captioning 1