spuuntries/urna-kp3l | Run with an API on Replicate

Input

image

*file

Input image

prompt

string

Shift + Return to add a new line

Input prompt

Default: "Describe this image"

max_new_tokens

integer

(minimum: 1, maximum: 2048)

Maximum number of tokens to generate

Default: 512

temperature

number

(minimum: 0, maximum: 2)

Temperature for sampling (0 to use transformer defaults)

Default: 0

top_p

number

(minimum: 0, maximum: 1)

Top-p (nucleus) sampling parameter (0 to use transformer defaults)

Default: 0

top_k

integer

(minimum: 0, maximum: 100)

Top-k sampling parameter (0 to disable/use transformer defaults)

Default: 0

repetition_penalty

number

(minimum: 0, maximum: 2)

Repetition penalty (0 to use transformer defaults)

Default: 0

do_sample

boolean

Whether to use sampling

Default: true

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

npx create-replicate --model=spuuntries/urna-kp3l

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 spuuntries/urna-kp3l using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "spuuntries/urna-kp3l:9338a4573a17178b70515c0ef2e613d3b4213e2dc860ef23b3ad6149dacadc1e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/NE1oV1iWQ1kjQn8z7XaeVb4v2CnY3w3Oh2Orkh686VSTzYgV/sayang3.jpg",
      top_k: 0,
      top_p: 0,
      prompt: "Apakah orang ini tersenyum?",
      do_sample: true,
      temperature: 0,
      max_new_tokens: 256,
      repetition_penalty: 0
    }
  }
);

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 spuuntries/urna-kp3l using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "spuuntries/urna-kp3l:9338a4573a17178b70515c0ef2e613d3b4213e2dc860ef23b3ad6149dacadc1e",
    input={
        "image": "https://replicate.delivery/pbxt/NE1oV1iWQ1kjQn8z7XaeVb4v2CnY3w3Oh2Orkh686VSTzYgV/sayang3.jpg",
        "top_k": 0,
        "top_p": 0,
        "prompt": "Apakah orang ini tersenyum?",
        "do_sample": True,
        "temperature": 0,
        "max_new_tokens": 256,
        "repetition_penalty": 0
    }
)

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 spuuntries/urna-kp3l 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": "spuuntries/urna-kp3l:9338a4573a17178b70515c0ef2e613d3b4213e2dc860ef23b3ad6149dacadc1e",
    "input": {
      "image": "https://replicate.delivery/pbxt/NE1oV1iWQ1kjQn8z7XaeVb4v2CnY3w3Oh2Orkh686VSTzYgV/sayang3.jpg",
      "top_k": 0,
      "top_p": 0,
      "prompt": "Apakah orang ini tersenyum?",
      "do_sample": true,
      "temperature": 0,
      "max_new_tokens": 256,
      "repetition_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Di tengah gambar, seorang pemuda berdiri dengan senyum cerah di wajahnya. Wajahnya dihiasi dengan kumis yang khas, menambahkan sentuhan pesona pada penampilannya. Dia mengenakan kemeja abu-abu, yang kontras dengan keseluruhan skema warna yang redup di ruangan. Sebuah syal hitam terikat di lehernya, memberikan sentuhan elegan dan menambahkan elemen intrik pada gambar. Tangan kanannya memegang telepon ke telinga kirinya, menunjukkan bahwa dia mungkin sedang dalam percakapan atau mungkin tenggelam dalam pikiran. Latar belakangnya kabur, menarik fokus pada wajah dan ekspresi berlumuran senyum pemuda itu.

Generated in

2.5 seconds

Tweak it Iterate in playground Share Report View full prediction

Run time and cost

This model costs approximately $0.11 to run on Replicate, or 9 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 A100 (80GB) GPU hardware. Predictions typically complete within 77 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This was a project that I recycled for many of my classes as their Final Project assignments, namely: Software Development and Design, Natural Language Processing, Digital Image Processing, and Deep Learning. The write-up is coming soon, still wrapping things up nicely.