windxtech/tattoo-generator – Run with an API on Replicate

windxtech / tattoo-generator

Cold

Public
205 runs
T4

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a realism tattoo design, set on a white background, a lion with big manea realism tattoo design, set on a white background, a lion with big mane

Input prompt

Default: "a hyper realism tattoo design, set on a pure white background of a lion with beautiful mane"

negative_prompt

string

Shift + Return to add a new line

blurry, low quality, distorted, disfigured, ugly, bad anatomyblurry, low quality, distorted, disfigured, ugly, bad anatomy

Specify things to not see in the output

Default: "blurry, low quality, distorted, disfigured, ugly, bad anatomy"

image

file

Input image for img2img. Leave blank to use text-to-image.

strength

number

(minimum: 0, maximum: 1)

Strength for img2img (0.0–1.0). Higher = more influence from prompt.

Default: 0.5

style

string

Choose a style for the image.

Default: "Realism"

lora_scale

number

(minimum: 0, maximum: 1)

Scale for LoRA weights (0.0-1.0). Higher values make the style more prominent.

Default: 0.5

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output

Default: 1

num_inference_steps

integer

(minimum: 20, maximum: 100)

Number of denoising steps

Default: 30

guidance_scale

number

(minimum: 5, maximum: 15)

Scale for classifier-free guidance

Default: 7

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

seed

integer

Random seed. Leave blank to randomize

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

npx create-replicate --model=windxtech/tattoo-generator

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 windxtech/tattoo-generator using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "windxtech/tattoo-generator:0fe0fd450695b2fd99305d27a07ee6349943c200dc849d07633a98c24daef9a8",
  {
    input: {
      style: "Realism",
      width: 512,
      height: 512,
      prompt: "a realism tattoo design, set on a white background, a lion with big mane",
      strength: 0.5,
      scheduler: "DPMSolverMultistep",
      lora_scale: 0.5,
      num_outputs: 1,
      guidance_scale: 7,
      negative_prompt: "blurry, low quality, distorted, disfigured, ugly, bad anatomy",
      num_inference_steps: 20
    }
  }
);

// 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 windxtech/tattoo-generator using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "windxtech/tattoo-generator:0fe0fd450695b2fd99305d27a07ee6349943c200dc849d07633a98c24daef9a8",
    input={
        "style": "Realism",
        "width": 512,
        "height": 512,
        "prompt": "a realism tattoo design, set on a white background, a lion with big mane",
        "strength": 0.5,
        "scheduler": "DPMSolverMultistep",
        "lora_scale": 0.5,
        "num_outputs": 1,
        "guidance_scale": 7,
        "negative_prompt": "blurry, low quality, distorted, disfigured, ugly, bad anatomy",
        "num_inference_steps": 20
    }
)
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 windxtech/tattoo-generator 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": "windxtech/tattoo-generator:0fe0fd450695b2fd99305d27a07ee6349943c200dc849d07633a98c24daef9a8",
    "input": {
      "style": "Realism",
      "width": 512,
      "height": 512,
      "prompt": "a realism tattoo design, set on a white background, a lion with big mane",
      "strength": 0.5,
      "scheduler": "DPMSolverMultistep",
      "lora_scale": 0.5,
      "num_outputs": 1,
      "guidance_scale": 7,
      "negative_prompt": "blurry, low quality, distorted, disfigured, ugly, bad anatomy",
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-05-09T06:22:10.221922Z",
  "created_at": "2025-05-09T06:19:55.506000Z",
  "data_removed": false,
  "error": null,
  "id": "003hjk2gy9rge0cppesrm8jfh4",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "a realism tattoo design, set on a white background, a lion with big mane",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7,
    "num_inference_steps": 20
  },
  "logs": "Using seed: 49946\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:14,  1.34it/s]\n 15%|█▌        | 3/20 [00:01<00:06,  2.70it/s]\n 20%|██        | 4/20 [00:01<00:06,  2.55it/s]\n 25%|██▌       | 5/20 [00:02<00:06,  2.45it/s]\n 30%|███       | 6/20 [00:02<00:05,  2.39it/s]\n 35%|███▌      | 7/20 [00:02<00:05,  2.34it/s]\n 40%|████      | 8/20 [00:03<00:05,  2.32it/s]\n 45%|████▌     | 9/20 [00:03<00:04,  2.30it/s]\n 50%|█████     | 10/20 [00:04<00:04,  2.29it/s]\n 55%|█████▌    | 11/20 [00:04<00:03,  2.29it/s]\n 60%|██████    | 12/20 [00:05<00:03,  2.28it/s]\n 65%|██████▌   | 13/20 [00:05<00:03,  2.27it/s]\n 70%|███████   | 14/20 [00:06<00:02,  2.26it/s]\n 75%|███████▌  | 15/20 [00:06<00:02,  2.26it/s]\n 80%|████████  | 16/20 [00:06<00:01,  2.25it/s]\n 85%|████████▌ | 17/20 [00:07<00:01,  2.25it/s]\n 90%|█████████ | 18/20 [00:07<00:00,  2.25it/s]\n 95%|█████████▌| 19/20 [00:08<00:00,  2.25it/s]\n100%|██████████| 20/20 [00:08<00:00,  2.25it/s]\n100%|██████████| 20/20 [00:08<00:00,  2.28it/s]",
  "metrics": {
    "predict_time": 10.039240042,
    "total_time": 134.715922
  },
  "output": [
    "https://replicate.delivery/czjl/Eyrd2nkTfeoX2UsIeef2xg3xDBLL1TN6MJmKY4Q2SJURioWlC/out-0.png"
  ],
  "started_at": "2025-05-09T06:22:00.182682Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/fddq-7y4qstnyrhkso7lbo3rkorelbnzqa7uvwanezakoxww2dmvvncha",
    "get": "https://api.replicate.com/v1/predictions/003hjk2gy9rge0cppesrm8jfh4",
    "cancel": "https://api.replicate.com/v1/predictions/003hjk2gy9rge0cppesrm8jfh4/cancel"
  },
  "version": "a1f9ccb4c3321f68aa1de8b47b950502b682893bd92e13eae2efd901f93ff52e"
}

Generated in

10.0 seconds

Tweak it ShareReport

This output was created using a different version of the model, windxtech/tattoo-generator:a1f9ccb4.

Examples

View more examples

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.