salesforce/blip – Run with an API on Replicate

salesforce / blip

Generate image captions

Warm

Public
161.9M runs
T4
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=salesforce/blip

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run salesforce/blip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "salesforce/blip:2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746",
  {
    input: {
      task: "image_captioning",
      image: "https://replicate.delivery/mgxm/f4e50a7b-e8ca-432f-8e68-082034ebcc70/demo.jpg"
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run salesforce/blip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "salesforce/blip:2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746",
    input={
        "task": "image_captioning",
        "image": "https://replicate.delivery/mgxm/f4e50a7b-e8ca-432f-8e68-082034ebcc70/demo.jpg"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run salesforce/blip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746",
    "input": {
      "task": "image_captioning",
      "image": "https://replicate.delivery/mgxm/f4e50a7b-e8ca-432f-8e68-082034ebcc70/demo.jpg"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/salesforce/blip@sha256:2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746 \
  -i 'task="image_captioning"' \
  -i 'image="https://replicate.delivery/mgxm/f4e50a7b-e8ca-432f-8e68-082034ebcc70/demo.jpg"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/salesforce/blip@sha256:2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "task": "image_captioning",
      "image": "https://replicate.delivery/mgxm/f4e50a7b-e8ca-432f-8e68-082034ebcc70/demo.jpg"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

Caption: a woman sitting on the beach with a dog

Generated in

6.7 seconds

Tweak it Report

This example was created by a different version, salesforce/blip:5a977fcb.

Run time and cost

This model costs approximately $0.00022 to run on Replicate, or 4545 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 1 seconds.

Readme

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

This is the PyTorch code of the BLIP paper.

Citation

If you find this code to be useful for your research, please consider citing.

@misc{li2022blip,
      title={BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation}, 
      author={Junnan Li and Dongxu Li and Caiming Xiong and Steven Hoi},
      year={2022},
      eprint={2201.12086},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgement

The implementation of BLIP relies on resources from ALBEF, Huggingface Transformers, and timm. We thank the original authors for their open-sourcing.