lucataco/joy-caption-pre-alpha – Run with an API on Replicate

lucataco / joy-caption-pre-alpha

Image Caption model

Cold

Public
376 runs
L40S
GitHub
Paper

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=lucataco/joy-caption-pre-alpha

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 lucataco/joy-caption-pre-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/joy-caption-pre-alpha:31665fdccd897d20cbda1fa305e64f1b94a181e0350409ed2a40df7a243830a5",
  {
    input: {
      image: "https://replicate.delivery/pbxt/LeG83qLZsTAOBa0EWNXaK366IkixJjiHOOzAUNTmrPHHtVPY/astro-forest.png"
    }
  }
);

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 lucataco/joy-caption-pre-alpha using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/joy-caption-pre-alpha:31665fdccd897d20cbda1fa305e64f1b94a181e0350409ed2a40df7a243830a5",
    input={
        "image": "https://replicate.delivery/pbxt/LeG83qLZsTAOBa0EWNXaK366IkixJjiHOOzAUNTmrPHHtVPY/astro-forest.png"
    }
)
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 lucataco/joy-caption-pre-alpha 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": "lucataco/joy-caption-pre-alpha:31665fdccd897d20cbda1fa305e64f1b94a181e0350409ed2a40df7a243830a5",
    "input": {
      "image": "https://replicate.delivery/pbxt/LeG83qLZsTAOBa0EWNXaK366IkixJjiHOOzAUNTmrPHHtVPY/astro-forest.png"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

This is a highly detailed, digitally rendered photograph set in a dense forest during twilight. The central subject is a lone astronaut, seated on the forest floor with a campfire in front of them. The astronaut is dressed in a white spacesuit with a reflective helmet, which is adorned with the NASA logo and various patches. The suit appears to be made of a smooth, durable fabric with visible seams and pockets. The astronaut's face is obscured by the helmet's visor, but their gloved hands are visible, resting on their knees. The campfire is a vibrant orange-yellow, casting a warm glow on the surroundings and creating stark contrasts with the dark, shadowy forest. The forest is populated by tall, straight trees with rough bark, and the ground is covered in fallen leaves and twigs. The sky is dark, suggesting it is either late evening or early morning, with a hint of dawn light filtering through the trees. The scene is rich in texture, with the smoothness of the spacesuit contrasting sharply with the roughness of the forest floor and the ruggedness of the trees. The overall atmosphere is one of isolation and mystery, with the astronaut's presence evoking questions about survival and exploration.

Generated in

12.7 seconds

Tweak it Share Report

Run time and cost

This model costs approximately $0.14 to run on Replicate, or 7 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 L40S GPU hardware. Predictions typically complete within 145 seconds. The predict time for this model varies significantly based on the inputs.

Readme

About

JoyCaption Pre-Alpha Image Caption Model

Inspired by the huggingface space fancyfeast/joy-caption-pre-alpha and the quantized version from camenduru/joy-caption-jupyter