zust-ai/zust-qr:b4f2ad25 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

zust-ai /zust-qr:b4f2ad25

Playground API

Input

is_heartbeat

boolean

Check if server alive

Default: false

pipe_type

string

Shift + Return to add a new line

qr_image or qr_prompt

Default: "qr_prompt"

seed

integer

Seed

prompt_strength

number

(minimum: 1)

Prompt strength

Default: 9

num_inference_steps

integer

(minimum: 1)

Iterations

Default: 35

size

integer

Size of the output image (square)

Default: 512

qr_background

string

Shift + Return to add a new line

{"image_url": "https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1", "caption": "a sports car parked in front of a building"}{"image_url": "https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1", "caption": "a sports car parked in front of a building"}

Reference Image for the QR

Default: "{\"image_url\": \"https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1\", \"caption\": \"a sports car parked in front of a building\"}"

qr_text

string

Shift + Return to add a new line

Text to encode into QR

Default: "http://qr.zust.ai"

qr_prompt

string

Shift + Return to add a new line

Prompt for Stylized QR Code

qr_negative_prompt

string

Shift + Return to add a new line

Negative Prompt for Stylized QR Code

qr_background_strength

number

Reference image's strength

qr_fill_color

string

Shift + Return to add a new line

Fill color for creaing QR code

Default: "#404040"

qr_control_scale

string

Shift + Return to add a new line

Controlnet conditioning scale (multiple controlnet)

qr_control_start

string

Shift + Return to add a new line

Controlnet guide start (multiple controlnet)

qr_control_end

string

Shift + Return to add a new line

Controlnet guide end (multiple controlnet)

fixer_control_scale

string

Shift + Return to add a new line

Fixer controlnet conditioning scale (multiple controlnet)

fixer_control_start

string

Shift + Return to add a new line

Fixer controlnet guide start (multiple controlnet)

fixer_control_end

string

Shift + Return to add a new line

Fixer controlnet guide end (multiple controlnet)

with_detail

boolean

Detailed output

Default: false

margin

integer

(minimum: 1)

Margin around QR

Default: 10

margin_noise_level

number

Noise in the margin area

Default: 0.3

fixer_iteration_count

integer

(minimum: 0)

Iteration to fix the QR

Default: 1

fixer_iteration_noise_strength

number

(minimum: 0)

Noise to add in regeneration

Default: 0.5

fixer_inference_steps

integer

(minimum: 1)

Iterations

Default: 70

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

npx create-replicate --model=zust-ai/zust-qr

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

const output = await replicate.run(
  "zust-ai/zust-qr:b4f2ad252e6d5d11f96bb188d7d25df53687cdea9ecbbf95c64e1f155cf2c4d7",
  {
    input: {
      size: 512,
      margin: 10,
      qr_text: "http://qr.zust.ai",
      pipe_type: "qr_prompt",
      with_detail: false,
      is_heartbeat: false,
      qr_background: "{\"image_url\": \"https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1\", \"caption\": \"a sports car parked in front of a building\"}",
      qr_fill_color: "#404040",
      prompt_strength: 9,
      margin_noise_level: 0.3,
      num_inference_steps: 35,
      fixer_inference_steps: 70,
      fixer_iteration_count: 1,
      fixer_iteration_noise_strength: 0.5
    }
  }
);

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

output = replicate.run(
    "zust-ai/zust-qr:b4f2ad252e6d5d11f96bb188d7d25df53687cdea9ecbbf95c64e1f155cf2c4d7",
    input={
        "size": 512,
        "margin": 10,
        "qr_text": "http://qr.zust.ai",
        "pipe_type": "qr_prompt",
        "with_detail": False,
        "is_heartbeat": False,
        "qr_background": "{\"image_url\": \"https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1\", \"caption\": \"a sports car parked in front of a building\"}",
        "qr_fill_color": "#404040",
        "prompt_strength": 9,
        "margin_noise_level": 0.3,
        "num_inference_steps": 35,
        "fixer_inference_steps": 70,
        "fixer_iteration_count": 1,
        "fixer_iteration_noise_strength": 0.5
    }
)
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 zust-ai/zust-qr 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": "zust-ai/zust-qr:b4f2ad252e6d5d11f96bb188d7d25df53687cdea9ecbbf95c64e1f155cf2c4d7",
    "input": {
      "size": 512,
      "margin": 10,
      "qr_text": "http://qr.zust.ai",
      "pipe_type": "qr_prompt",
      "with_detail": false,
      "is_heartbeat": false,
      "qr_background": "{\\"image_url\\": \\"https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1\\", \\"caption\\": \\"a sports car parked in front of a building\\"}",
      "qr_fill_color": "#404040",
      "prompt_strength": 9,
      "margin_noise_level": 0.3,
      "num_inference_steps": 35,
      "fixer_inference_steps": 70,
      "fixer_iteration_count": 1,
      "fixer_iteration_noise_strength": 0.5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/zust-ai/zust-qr@sha256:b4f2ad252e6d5d11f96bb188d7d25df53687cdea9ecbbf95c64e1f155cf2c4d7 \
  -i 'size=512' \
  -i 'margin=10' \
  -i 'qr_text="http://qr.zust.ai"' \
  -i 'pipe_type="qr_prompt"' \
  -i 'with_detail=false' \
  -i 'is_heartbeat=false' \
  -i $'qr_background="{\\"image_url\\": \\"https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1\\", \\"caption\\": \\"a sports car parked in front of a building\\"}"' \
  -i 'qr_fill_color="#404040"' \
  -i 'prompt_strength=9' \
  -i 'margin_noise_level=0.3' \
  -i 'num_inference_steps=35' \
  -i 'fixer_inference_steps=70' \
  -i 'fixer_iteration_count=1' \
  -i 'fixer_iteration_noise_strength=0.5'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/zust-ai/zust-qr@sha256:b4f2ad252e6d5d11f96bb188d7d25df53687cdea9ecbbf95c64e1f155cf2c4d7
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "size": 512,
      "margin": 10,
      "qr_text": "http://qr.zust.ai",
      "pipe_type": "qr_prompt",
      "with_detail": false,
      "is_heartbeat": false,
      "qr_background": "{\\"image_url\\": \\"https://images.unsplash.com/photo-1686881537217-5bf3b5998cf1\\", \\"caption\\": \\"a sports car parked in front of a building\\"}",
      "qr_fill_color": "#404040",
      "prompt_strength": 9,
      "margin_noise_level": 0.3,
      "num_inference_steps": 35,
      "fixer_inference_steps": 70,
      "fixer_iteration_count": 1,
      "fixer_iteration_noise_strength": 0.5
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

No output yet! Press "Submit" to start a prediction.