astramlco/easycontrol-ghibli | Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

Ghibli Studio style, Charming hand-drawn anime-style illustrationGhibli Studio style, Charming hand-drawn anime-style illustration

Enter a text prompt to guide image generation.

Default: "Ghibli Studio style, Charming hand-drawn anime-style illustration"

spatial_img

*file

Ghibli-style spatial control image.

height

integer

(minimum: 256, maximum: 1024)

Set the height of the generated image (pixels).

Default: 768

width

integer

(minimum: 256, maximum: 1024)

Set the width of the generated image (pixels).

Default: 768

seed

integer

Set a random seed for generation (-1 for random).

Default: 42

use_zero_init

boolean

Use CFG zero star.

Default: true

zero_steps

integer

(minimum: 0)

Zero init steps.

Default: 1

control_type

string

Control type (currently only Ghibli supported).

Default: "Ghibli"

output_format

string

Choose the format of the output images.

Default: "png"

output_quality

integer

(minimum: 1, maximum: 100)

Set the quality of the output image for jpg and webp (1-100).

Default: 90

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

npx create-replicate --model=astramlco/easycontrol-ghibli

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 astramlco/easycontrol-ghibli using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "astramlco/easycontrol-ghibli:9ad8a8970c83024fbce9ea054bb62652fec08c6c12dd39eda39cd0833ad36e2f",
  {
    input: {
      seed: 42,
      width: 1024,
      height: 640,
      prompt: "Ghibli Studio style, Charming hand-drawn anime-style illustration",
      zero_steps: 1,
      spatial_img: "https://replicate.delivery/pbxt/MrG49FYK6CNEUu543tYO11kboFgD2HiqWyzs8nh9frBRP4Tq/replicate-prediction-rggsm01t8hrmc0cp6d6b8y672w.webp",
      control_type: "Ghibli",
      output_format: "png",
      use_zero_init: true,
      output_quality: 90
    }
  }
);

// 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 astramlco/easycontrol-ghibli using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "astramlco/easycontrol-ghibli:9ad8a8970c83024fbce9ea054bb62652fec08c6c12dd39eda39cd0833ad36e2f",
    input={
        "seed": 42,
        "width": 1024,
        "height": 640,
        "prompt": "Ghibli Studio style, Charming hand-drawn anime-style illustration",
        "zero_steps": 1,
        "spatial_img": "https://replicate.delivery/pbxt/MrG49FYK6CNEUu543tYO11kboFgD2HiqWyzs8nh9frBRP4Tq/replicate-prediction-rggsm01t8hrmc0cp6d6b8y672w.webp",
        "control_type": "Ghibli",
        "output_format": "png",
        "use_zero_init": True,
        "output_quality": 90
    }
)
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 astramlco/easycontrol-ghibli 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": "astramlco/easycontrol-ghibli:9ad8a8970c83024fbce9ea054bb62652fec08c6c12dd39eda39cd0833ad36e2f",
    "input": {
      "seed": 42,
      "width": 1024,
      "height": 640,
      "prompt": "Ghibli Studio style, Charming hand-drawn anime-style illustration",
      "zero_steps": 1,
      "spatial_img": "https://replicate.delivery/pbxt/MrG49FYK6CNEUu543tYO11kboFgD2HiqWyzs8nh9frBRP4Tq/replicate-prediction-rggsm01t8hrmc0cp6d6b8y672w.webp",
      "control_type": "Ghibli",
      "output_format": "png",
      "use_zero_init": true,
      "output_quality": 90
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-04-18T11:25:13.078819Z",
  "created_at": "2025-04-18T11:22:59.085000Z",
  "data_removed": false,
  "error": null,
  "id": "5p78be9thnrme0cp92hse3env8",
  "input": {
    "seed": 42,
    "width": 1024,
    "height": 640,
    "prompt": "Ghibli Studio style, Charming hand-drawn anime-style illustration",
    "zero_steps": 1,
    "spatial_img": "https://replicate.delivery/pbxt/MrG49FYK6CNEUu543tYO11kboFgD2HiqWyzs8nh9frBRP4Tq/replicate-prediction-rggsm01t8hrmc0cp6d6b8y672w.webp",
    "control_type": "Ghibli",
    "output_format": "png",
    "use_zero_init": true,
    "output_quality": 90
  },
  "logs": "Using seed: 42\nLoaded spatial image from: /tmp/tmpyby92jzzreplicate-prediction-rggsm01t8hrmc0cp6d6b8y672w.webp\nGenerating image with use_zero_init=True...\n<PIL.Image.Image image mode=RGB size=1360x768 at 0x70C81147B460>\n  0%|          | 0/25 [00:00<?, ?it/s]\n  4%|▍         | 1/25 [00:00<00:13,  1.82it/s]\n  8%|▊         | 2/25 [00:00<00:10,  2.25it/s]\n 12%|█▏        | 3/25 [00:01<00:10,  2.13it/s]\n 16%|█▌        | 4/25 [00:01<00:10,  2.08it/s]\n 20%|██        | 5/25 [00:02<00:09,  2.05it/s]\n 24%|██▍       | 6/25 [00:02<00:09,  2.04it/s]\n 28%|██▊       | 7/25 [00:03<00:08,  2.03it/s]\n 32%|███▏      | 8/25 [00:03<00:08,  2.02it/s]\n 36%|███▌      | 9/25 [00:04<00:07,  2.01it/s]\n 40%|████      | 10/25 [00:04<00:07,  2.01it/s]\n 44%|████▍     | 11/25 [00:05<00:06,  2.01it/s]\n 48%|████▊     | 12/25 [00:05<00:06,  2.00it/s]\n 52%|█████▏    | 13/25 [00:06<00:05,  2.00it/s]\n 56%|█████▌    | 14/25 [00:06<00:05,  2.00it/s]\n 60%|██████    | 15/25 [00:07<00:04,  2.00it/s]\n 64%|██████▍   | 16/25 [00:07<00:04,  2.00it/s]\n 68%|██████▊   | 17/25 [00:08<00:03,  2.00it/s]\n 72%|███████▏  | 18/25 [00:08<00:03,  2.00it/s]\n 76%|███████▌  | 19/25 [00:09<00:03,  2.00it/s]\n 80%|████████  | 20/25 [00:09<00:02,  2.00it/s]\n 84%|████████▍ | 21/25 [00:10<00:02,  2.00it/s]\n 88%|████████▊ | 22/25 [00:10<00:01,  2.00it/s]\n 92%|█████████▏| 23/25 [00:11<00:01,  1.99it/s]\n 96%|█████████▌| 24/25 [00:11<00:00,  1.99it/s]\n100%|██████████| 25/25 [00:12<00:00,  1.99it/s]\n100%|██████████| 25/25 [00:12<00:00,  2.01it/s]\nGenerated 'zeroinit' image in 13.41s\nSaved: output_seed42.png\nSaved output in 0.21s\nTotal prediction time: 13.66 seconds",
  "metrics": {
    "predict_time": 13.80636965,
    "total_time": 133.993819
  },
  "output": [
    "https://replicate.delivery/xezq/s7JZmWjLR6bZFx4cMLmSOGnRyjd8rcruedQo5FlHHQpMRfjUA/output_seed42.png"
  ],
  "started_at": "2025-04-18T11:24:59.272449Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-yc6j7zr5ohiwu2nxxik7qd5qytv34ycxvqxatz3vmqf2pieqceea",
    "get": "https://api.replicate.com/v1/predictions/5p78be9thnrme0cp92hse3env8",
    "cancel": "https://api.replicate.com/v1/predictions/5p78be9thnrme0cp92hse3env8/cancel"
  },
  "version": "9ad8a8970c83024fbce9ea054bb62652fec08c6c12dd39eda39cd0833ad36e2f"
}

Generated in

13.8 seconds

Tweak it Share Report View full prediction

Examples

View more examples

Run time and cost

This model costs approximately $0.088 to run on Replicate, or 11 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 91 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This is the EasyControl model to turn any images into Ghibli style.

Usage:

prompt: keep Ghibli Studio style, Charming hand-drawn anime-style illustration in the prompt to trigger Ghibli style image generation, and prepend your own prompt.
height and width: Dimensions of generated image. Those have to be a multiple of 8 px for now.
use_zero_init and zero_steps: Enable CFG-Zero*. It’s recommended for better control and image quality.
output_format and output_quality: Image type and optional compression quality.