zust-ai/zust-diffusion:f875cf07 | 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-diffusion:f875cf07

Playground API

Input

is_heartbeat

boolean

Check if Server Alive

Default: false

pipe_type

string

Shift + Return to add a new line

sdxl or cleanup

Default: "sdxl"

with_detail

boolean

Detailed Output

Default: false

seed

integer

Seed

subjects

string

Shift + Return to add a new line

[{"top": 0.3583984375, "left": 0.546875, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png"}][{"top": 0.3583984375, "left": 0.546875, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png"}]

Subject Placement & URLs

Default: "[{\"top\": 0.3583984375, \"left\": 0.546875, \"scale\": 0.0009765625, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\"}]"

width

integer

Width (1024, 1216, 832)

Default: 1024

height

integer

Height (1024, 832, 1216)

Default: 1024

prompt

string

Shift + Return to add a new line

trolley suitcase on a mountain rock with hot air balloons in the blue skytrolley suitcase on a mountain rock with hot air balloons in the blue sky

Prompt

Default: "trolley suitcase on a mountain rock with hot air balloons in the blue sky"

negative_prompt

string

Shift + Return to add a new line

floating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawingfloating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawing

Negative Prompt

Default: "floating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawing"

num_images_per_prompt

integer

(minimum: 1)

Number of Generations (Firstpass)

Default: 2

firstpass_inference_steps

integer

(minimum: 1)

Firstpass Iterations

Default: 20

firstpass_prompt_strength

number

(minimum: 1)

Firstpass Prompt Strength

Default: 5

firstpass_subject_control_strength

number

(minimum: 0, maximum: 2)

Subject ControlNet Guidance (Firstpass)

Default: 0.5

inpaint_fix_inference_steps

integer

(minimum: 1)

Inpaint.fix Iterations

Default: 30

inpaint_fix_prompt_strength

number

(minimum: 1)

Inpaint.fix Prompt Strength

Default: 5

inpaint_fix_subject_control_strength

number

(minimum: 0, maximum: 2)

Subject ControlNet Guidance (Inpaint.fix)

Default: 1

inpaint_fix_noise_strength

number

Hires Noise Strength

Default: 0.6

hires_fix_erode

integer

Hires.fix Erosion Kernel

Default: 5

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

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

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-diffusion 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-diffusion:f875cf07ce8ceabdf556c428ce77c783be5882c97a49470304bade05fd9ed8c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "trolley suitcase on a mountain rock with hot air balloons in the blue sky",
      subjects: "[{\"top\": 0.3583984375, \"left\": 0.546875, \"scale\": 0.0009765625, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\"}]",
      pipe_type: "sdxl",
      with_detail: false,
      is_heartbeat: false,
      hires_fix_erode: 5,
      negative_prompt: "floating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawing",
      num_images_per_prompt: 2,
      firstpass_inference_steps: 20,
      firstpass_prompt_strength: 5,
      inpaint_fix_noise_strength: 0.6,
      inpaint_fix_inference_steps: 30,
      inpaint_fix_prompt_strength: 5,
      firstpass_subject_control_strength: 0.5,
      inpaint_fix_subject_control_strength: 1
    }
  }
);

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

output = replicate.run(
    "zust-ai/zust-diffusion:f875cf07ce8ceabdf556c428ce77c783be5882c97a49470304bade05fd9ed8c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "trolley suitcase on a mountain rock with hot air balloons in the blue sky",
        "subjects": "[{\"top\": 0.3583984375, \"left\": 0.546875, \"scale\": 0.0009765625, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\"}]",
        "pipe_type": "sdxl",
        "with_detail": False,
        "is_heartbeat": False,
        "hires_fix_erode": 5,
        "negative_prompt": "floating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawing",
        "num_images_per_prompt": 2,
        "firstpass_inference_steps": 20,
        "firstpass_prompt_strength": 5,
        "inpaint_fix_noise_strength": 0.6,
        "inpaint_fix_inference_steps": 30,
        "inpaint_fix_prompt_strength": 5,
        "firstpass_subject_control_strength": 0.5,
        "inpaint_fix_subject_control_strength": 1
    }
)
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-diffusion 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-diffusion:f875cf07ce8ceabdf556c428ce77c783be5882c97a49470304bade05fd9ed8c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "trolley suitcase on a mountain rock with hot air balloons in the blue sky",
      "subjects": "[{\\"top\\": 0.3583984375, \\"left\\": 0.546875, \\"scale\\": 0.0009765625, \\"image_url\\": \\"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\\"}]",
      "pipe_type": "sdxl",
      "with_detail": false,
      "is_heartbeat": false,
      "hires_fix_erode": 5,
      "negative_prompt": "floating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawing",
      "num_images_per_prompt": 2,
      "firstpass_inference_steps": 20,
      "firstpass_prompt_strength": 5,
      "inpaint_fix_noise_strength": 0.6,
      "inpaint_fix_inference_steps": 30,
      "inpaint_fix_prompt_strength": 5,
      "firstpass_subject_control_strength": 0.5,
      "inpaint_fix_subject_control_strength": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

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