lightweight-ai/test_sk2ig_f – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

Prompt for the generated image

Default: "High quality, 4K, UHD"

style_name

string

Select a visual style

Default: "Photographic"

negative_prompt

string

Shift + Return to add a new line

sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realisticsloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic

Negative prompt to avoid undesired results

Default: "ugly, blurry, deformed"

image

file

Upload an input image

hed_enabled

boolean

Enable HED preprocessing

Default: true

canny_enabled

boolean

Enable Canny preprocessing

Default: false

num_inference_steps

integer

Number of inference steps

Default: 25

guidance_scale

number

Classifier-free guidance scale

Default: 3.5

controlnet_conditioning_scale

number

ControlNet conditioning scale

Default: 0.7

seed

integer

Random seed for reproducibility

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

npx create-replicate --model=lightweight-ai/test_sk2ig_f

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";
import fs from "node:fs";

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

Run lightweight-ai/test_sk2ig_f using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lightweight-ai/test_sk2ig_f:efe3e58513bbeeee60c926eb5e9d67a774848dbcdc74000a1db71515a43e0110",
  {
    input: {
      seed: 88456,
      image: "https://replicate.delivery/pbxt/MqSQLpdaQBnj9kxWbJMfh4rYSyHJuhOtI7uACtN6XTXnAvXx/aa96dadef832b0af3ecbefea17fc8acc%20%28Copy%29.jpg",
      prompt: "a rose",
      style_name: "Pixel art",
      hed_enabled: true,
      canny_enabled: false,
      guidance_scale: 3.5,
      negative_prompt: "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
      num_inference_steps: 28,
      controlnet_conditioning_scale: 0.45
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 lightweight-ai/test_sk2ig_f using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lightweight-ai/test_sk2ig_f:efe3e58513bbeeee60c926eb5e9d67a774848dbcdc74000a1db71515a43e0110",
    input={
        "seed": 88456,
        "image": "https://replicate.delivery/pbxt/MqSQLpdaQBnj9kxWbJMfh4rYSyHJuhOtI7uACtN6XTXnAvXx/aa96dadef832b0af3ecbefea17fc8acc%20%28Copy%29.jpg",
        "prompt": "a rose",
        "style_name": "Pixel art",
        "hed_enabled": True,
        "canny_enabled": False,
        "guidance_scale": 3.5,
        "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
        "num_inference_steps": 28,
        "controlnet_conditioning_scale": 0.45
    }
)
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 lightweight-ai/test_sk2ig_f 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": "lightweight-ai/test_sk2ig_f:efe3e58513bbeeee60c926eb5e9d67a774848dbcdc74000a1db71515a43e0110",
    "input": {
      "seed": 88456,
      "image": "https://replicate.delivery/pbxt/MqSQLpdaQBnj9kxWbJMfh4rYSyHJuhOtI7uACtN6XTXnAvXx/aa96dadef832b0af3ecbefea17fc8acc%20%28Copy%29.jpg",
      "prompt": "a rose",
      "style_name": "Pixel art",
      "hed_enabled": true,
      "canny_enabled": false,
      "guidance_scale": 3.5,
      "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
      "num_inference_steps": 28,
      "controlnet_conditioning_scale": 0.45
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-04-16T07:19:00.962018Z",
  "created_at": "2025-04-16T07:17:04.248000Z",
  "data_removed": false,
  "error": null,
  "id": "s94x7ptyf1rm80cp7ntv7azjec",
  "input": {
    "seed": 88456,
    "image": "https://replicate.delivery/pbxt/MqSQLpdaQBnj9kxWbJMfh4rYSyHJuhOtI7uACtN6XTXnAvXx/aa96dadef832b0af3ecbefea17fc8acc%20%28Copy%29.jpg",
    "prompt": "a rose",
    "style_name": "Pixel art",
    "hed_enabled": true,
    "canny_enabled": false,
    "guidance_scale": 3.5,
    "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
    "num_inference_steps": 28,
    "controlnet_conditioning_scale": 0.45
  },
  "logs": "`height` and `width` have to be divisible by 16 but are 1030 and 736. Dimensions will be resized accordingly\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:13,  1.94it/s]\n  7%|▋         | 2/28 [00:00<00:09,  2.73it/s]\n 11%|█         | 3/28 [00:01<00:09,  2.60it/s]\n 14%|█▍        | 4/28 [00:01<00:09,  2.55it/s]\n 18%|█▊        | 5/28 [00:01<00:09,  2.52it/s]\n 21%|██▏       | 6/28 [00:02<00:08,  2.50it/s]\n 25%|██▌       | 7/28 [00:02<00:08,  2.49it/s]\n 29%|██▊       | 8/28 [00:03<00:08,  2.49it/s]\n 32%|███▏      | 9/28 [00:03<00:07,  2.48it/s]\n 36%|███▌      | 10/28 [00:04<00:07,  2.48it/s]\n 39%|███▉      | 11/28 [00:04<00:06,  2.47it/s]\n 43%|████▎     | 12/28 [00:04<00:06,  2.47it/s]\n 46%|████▋     | 13/28 [00:05<00:06,  2.47it/s]\n 50%|█████     | 14/28 [00:05<00:05,  2.47it/s]\n 54%|█████▎    | 15/28 [00:06<00:05,  2.47it/s]\n 57%|█████▋    | 16/28 [00:06<00:04,  2.47it/s]\n 61%|██████    | 17/28 [00:06<00:04,  2.47it/s]\n 64%|██████▍   | 18/28 [00:07<00:04,  2.47it/s]\n 68%|██████▊   | 19/28 [00:07<00:03,  2.47it/s]\n 71%|███████▏  | 20/28 [00:08<00:03,  2.47it/s]\n 75%|███████▌  | 21/28 [00:08<00:02,  2.47it/s]\n 79%|███████▊  | 22/28 [00:08<00:02,  2.47it/s]\n 82%|████████▏ | 23/28 [00:09<00:02,  2.46it/s]\n 86%|████████▌ | 24/28 [00:09<00:01,  2.46it/s]\n 89%|████████▉ | 25/28 [00:10<00:01,  2.46it/s]\n 93%|█████████▎| 26/28 [00:10<00:00,  2.46it/s]\n 96%|█████████▋| 27/28 [00:10<00:00,  2.46it/s]\n100%|██████████| 28/28 [00:11<00:00,  2.46it/s]\n100%|██████████| 28/28 [00:11<00:00,  2.47it/s]\n출력 이미지가 /tmp/outpaint_output.png에 저장되었습니다.",
  "metrics": {
    "predict_time": 13.154753338999999,
    "total_time": 116.714018
  },
  "output": [
    "https://replicate.delivery/xezq/AD5EoH0h3xLfHq7R0ikddpW4YelplRNM3wYDph70XD8kvQjUA/outpaint_output.png"
  ],
  "started_at": "2025-04-16T07:18:47.807264Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-53dx7hzl5ypzcabfnzfjbyjk277m6p6hb5z7cooffizkftr4nwpq",
    "get": "https://api.replicate.com/v1/predictions/s94x7ptyf1rm80cp7ntv7azjec",
    "cancel": "https://api.replicate.com/v1/predictions/s94x7ptyf1rm80cp7ntv7azjec/cancel"
  },
  "version": "82a04a0ad53cac48c1db8a25e082ff3f266a386a398cc50d60b8f0dd0518442b"
}

Generated in

13.2 seconds