cjwbw / docentr

End-to-End Document Image Enhancement Transformer

Cold

Public
4.6K runs
T4
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09

Model

cjwbw/docentr:0bc45621

hb3ahvlt2jfotdqtqrhfcnhdyq

Status

Succeeded

Source

Web

Hardware

–

Total duration

1m 44s

Created

almost 3 years ago

Input

image
model_size: base

{
  "image": "https://replicate.delivery/mgxm/7bb1c92e-0b30-4107-9a95-5b8f0040a80e/14.png",
  "model_size": "base"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09",
  {
    input: {
      image: "https://replicate.delivery/mgxm/7bb1c92e-0b30-4107-9a95-5b8f0040a80e/14.png",
      model_size: "base"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

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

output = replicate.run(
    "cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09",
    input={
        "image": "https://replicate.delivery/mgxm/7bb1c92e-0b30-4107-9a95-5b8f0040a80e/14.png",
        "model_size": "base"
    }
)
print(output)

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

Run cjwbw/docentr 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": "cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09",
    "input": {
      "image": "https://replicate.delivery/mgxm/7bb1c92e-0b30-4107-9a95-5b8f0040a80e/14.png",
      "model_size": "base"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-08-30T00:39:18.826442Z",
  "created_at": "2022-08-30T00:37:34.830909Z",
  "data_removed": false,
  "error": null,
  "id": "hb3ahvlt2jfotdqtqrhfcnhdyq",
  "input": {
    "image": "https://replicate.delivery/mgxm/7bb1c92e-0b30-4107-9a95-5b8f0040a80e/14.png",
    "model_size": "base"
  },
  "logs": "(0 / 59) processing patch...\n(1 / 59) processing patch...\n(2 / 59) processing patch...\n(3 / 59) processing patch...\n(4 / 59) processing patch...\n(5 / 59) processing patch...\n(6 / 59) processing patch...\n(7 / 59) processing patch...\n(8 / 59) processing patch...\n(9 / 59) processing patch...\n(10 / 59) processing patch...\n(11 / 59) processing patch...\n(12 / 59) processing patch...\n(13 / 59) processing patch...\n(14 / 59) processing patch...\n(15 / 59) processing patch...\n(16 / 59) processing patch...\n(17 / 59) processing patch...\n(18 / 59) processing patch...\n(19 / 59) processing patch...\n(20 / 59) processing patch...\n(21 / 59) processing patch...\n(22 / 59) processing patch...\n(23 / 59) processing patch...\n(24 / 59) processing patch...\n(25 / 59) processing patch...\n(26 / 59) processing patch...\n(27 / 59) processing patch...\n(28 / 59) processing patch...\n(29 / 59) processing patch...\n(30 / 59) processing patch...\n(31 / 59) processing patch...\n(32 / 59) processing patch...\n(33 / 59) processing patch...\n(34 / 59) processing patch...\n(35 / 59) processing patch...\n(36 / 59) processing patch...\n(37 / 59) processing patch...\n(38 / 59) processing patch...\n(39 / 59) processing patch...\n(40 / 59) processing patch...\n(41 / 59) processing patch...\n(42 / 59) processing patch...\n(43 / 59) processing patch...\n(44 / 59) processing patch...\n(45 / 59) processing patch...\n(46 / 59) processing patch...\n(47 / 59) processing patch...\n(48 / 59) processing patch...\n(49 / 59) processing patch...\n(50 / 59) processing patch...\n(51 / 59) processing patch...\n(52 / 59) processing patch...\n(53 / 59) processing patch...\n(54 / 59) processing patch...\n(55 / 59) processing patch...\n(56 / 59) processing patch...\n(57 / 59) processing patch...\n(58 / 59) processing patch...\n(59 / 59) processing patch...",
  "metrics": {
    "predict_time": 5.007354,
    "total_time": 103.995533
  },
  "output": "https://replicate.delivery/mgxm/218c6b06-a01f-41ea-8914-132c5c6479c6/output.png",
  "started_at": "2022-08-30T00:39:13.819088Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/hb3ahvlt2jfotdqtqrhfcnhdyq",
    "cancel": "https://api.replicate.com/v1/predictions/hb3ahvlt2jfotdqtqrhfcnhdyq/cancel"
  },
  "version": "0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09"
}

Generated in

5.0 seconds

Tweak it ShareReport

Prediction

cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09

Model

cjwbw/docentr:0bc45621

lzyiixk4cjgs3i6t7ue2o74kfe

Status

Succeeded

Source

Web

Hardware

–

Total duration

2.0s

Created

almost 3 years ago

Input

image
model_size: large

{
  "image": "https://replicate.delivery/mgxm/9c83a981-45ee-446a-a998-27a7c1e124f5/3.png",
  "model_size": "large"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09",
  {
    input: {
      image: "https://replicate.delivery/mgxm/9c83a981-45ee-446a-a998-27a7c1e124f5/3.png",
      model_size: "large"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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

Import the client:

import replicate

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

output = replicate.run(
    "cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09",
    input={
        "image": "https://replicate.delivery/mgxm/9c83a981-45ee-446a-a998-27a7c1e124f5/3.png",
        "model_size": "large"
    }
)
print(output)

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

Run cjwbw/docentr 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": "cjwbw/docentr:0bc456216d675a98405175bf49f2123a6e32a52e0d6a00159edf3f3dc010fa09",
    "input": {
      "image": "https://replicate.delivery/mgxm/9c83a981-45ee-446a-a998-27a7c1e124f5/3.png",
      "model_size": "large"
    }
  }' \
  https://api.replicate.com/v1/predictions

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