zust-ai/zust-diffusion:074800d6 | 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:074800d6

Playground API

Input

is_heartbeat

boolean

Check if server alive

Default: false

pipe_type

string

Shift + Return to add a new line

txt2img or img2img or multi_txt2img or multi_img2img

Default: "txt2img"

width

integer

Width of the output image

Default: 768

height

integer

Height of the output image

Default: 768

prompt

string

Shift + Return to add a new line

["standing on a dark marble platform, heavy shadow, in an outdoor patio, plants, flowers, fairy lights, high definition, ultra realistic, intricate"]["standing on a dark marble platform, heavy shadow, in an outdoor patio, plants, flowers, fairy lights, high definition, ultra realistic, intricate"]

Prompt

Default: "[\"standing on a dark marble platform, heavy shadow, in an outdoor patio, plants, flowers, fairy lights, high definition, ultra realistic, intricate\"]"

negative_prompt

string

Shift + Return to add a new line

["text, sign, signature, watermark, levitated, in the air, floating, gap, extras, person, male, female, artifacts, dazed, drawing, sketch, painting, low res, low quality, low-res, low resolution, fake, fuzzy, poor quality, amateur photography, out of focus, cropped, deformations"]["text, sign, signature, watermark, levitated, in the air, floating, gap, extras, person, male, female, artifacts, dazed, drawing, sketch, painting, low res, low quality, low-res, low resolution, fake, fuzzy, poor quality, amateur photography, out of focus, cropped, deformations"]

Negative prompt

Default: "[\"text, sign, signature, watermark, levitated, in the air, floating, gap, extras, person, male, female, artifacts, dazed, drawing, sketch, painting, low res, low quality, low-res, low resolution, fake, fuzzy, poor quality, amateur photography, out of focus, cropped, deformations\"]"

num_images_per_prompt

integer

(minimum: 1)

Number of generations

Default: 1

num_inference_steps

integer

(minimum: 1)

Iterations

Default: 25

seed

integer

Seed

prompt_strength

number

(minimum: 1)

Prompt strength

Default: 7.5

background_strength

number

Strength of background for img2img

Default: 0.8

platform_control_strength

number

(minimum: 0, maximum: 1)

Platform ControlNet guidance

Default: 0.2

subject_control_strength

number

(minimum: 0, maximum: 2)

Subject ControlNet guidance

Default: 0.8

with_detail

boolean

Detailed output

Default: false

platform

string

Shift + Return to add a new line

{"top": 0.71484375, "left": 0.08203125, "scale": 0.0013020833333333333, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_platform.png"}{"top": 0.71484375, "left": 0.08203125, "scale": 0.0013020833333333333, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_platform.png"}

Platform image for subject base

Default: "{\"top\": 0.71484375, \"left\": 0.08203125, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_platform.png\"}"

background

string

Shift + Return to add a new line

{"top": 0, "left": 0, "scale": 0.0013020833333333333, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_background.png"}{"top": 0, "left": 0, "scale": 0.0013020833333333333, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_background.png"}

Background image for img2img

Default: "{\"top\": 0, \"left\": 0, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_background.png\"}"

subjects

string

Shift + Return to add a new line

[{"top": 0.15885416666666666, "left": 0.2916666666666667, "scale": 0.0013020833333333333, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png"}][{"top": 0.15885416666666666, "left": 0.2916666666666667, "scale": 0.0013020833333333333, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png"}]

Subject placement settings and image urls

Default: "[{\"top\": 0.15885416666666666, \"left\": 0.2916666666666667, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\"}]"

erode

integer

Erosion scale

Default: 0

with_cleanup

boolean

Cleanup using dilated mask

Default: false

dilate_strength

integer

Dilate strength

Default: 4

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:074800d6a441dd242712b3a84383cd40bdcff18be8831d6e82c5bd22643151a0",
  {
    input: {
      erode: 0,
      width: 768,
      height: 768,
      prompt: "[\"standing on a dark marble platform, heavy shadow, in an outdoor patio, plants, flowers, fairy lights, high definition, ultra realistic, intricate\"]",
      platform: "{\"top\": 0.71484375, \"left\": 0.08203125, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_platform.png\"}",
      subjects: "[{\"top\": 0.15885416666666666, \"left\": 0.2916666666666667, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\"}]",
      pipe_type: "txt2img",
      background: "{\"top\": 0, \"left\": 0, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_background.png\"}",
      with_detail: false,
      is_heartbeat: false,
      with_cleanup: false,
      dilate_strength: 4,
      negative_prompt: "[\"text, sign, signature, watermark, levitated, in the air, floating, gap, extras, person, male, female, artifacts, dazed, drawing, sketch, painting, low res, low quality, low-res, low resolution, fake, fuzzy, poor quality, amateur photography, out of focus, cropped, deformations\"]",
      prompt_strength: 7.5,
      background_strength: 0.8,
      num_inference_steps: 25,
      num_images_per_prompt: 1,
      subject_control_strength: 0.8,
      platform_control_strength: 0.2
    }
  }
);

// 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:074800d6a441dd242712b3a84383cd40bdcff18be8831d6e82c5bd22643151a0",
    input={
        "erode": 0,
        "width": 768,
        "height": 768,
        "prompt": "[\"standing on a dark marble platform, heavy shadow, in an outdoor patio, plants, flowers, fairy lights, high definition, ultra realistic, intricate\"]",
        "platform": "{\"top\": 0.71484375, \"left\": 0.08203125, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_platform.png\"}",
        "subjects": "[{\"top\": 0.15885416666666666, \"left\": 0.2916666666666667, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\"}]",
        "pipe_type": "txt2img",
        "background": "{\"top\": 0, \"left\": 0, \"scale\": 0.0013020833333333333, \"image_url\": \"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_background.png\"}",
        "with_detail": False,
        "is_heartbeat": False,
        "with_cleanup": False,
        "dilate_strength": 4,
        "negative_prompt": "[\"text, sign, signature, watermark, levitated, in the air, floating, gap, extras, person, male, female, artifacts, dazed, drawing, sketch, painting, low res, low quality, low-res, low resolution, fake, fuzzy, poor quality, amateur photography, out of focus, cropped, deformations\"]",
        "prompt_strength": 7.5,
        "background_strength": 0.8,
        "num_inference_steps": 25,
        "num_images_per_prompt": 1,
        "subject_control_strength": 0.8,
        "platform_control_strength": 0.2
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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:074800d6a441dd242712b3a84383cd40bdcff18be8831d6e82c5bd22643151a0",
    "input": {
      "erode": 0,
      "width": 768,
      "height": 768,
      "prompt": "[\\"standing on a dark marble platform, heavy shadow, in an outdoor patio, plants, flowers, fairy lights, high definition, ultra realistic, intricate\\"]",
      "platform": "{\\"top\\": 0.71484375, \\"left\\": 0.08203125, \\"scale\\": 0.0013020833333333333, \\"image_url\\": \\"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_platform.png\\"}",
      "subjects": "[{\\"top\\": 0.15885416666666666, \\"left\\": 0.2916666666666667, \\"scale\\": 0.0013020833333333333, \\"image_url\\": \\"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png\\"}]",
      "pipe_type": "txt2img",
      "background": "{\\"top\\": 0, \\"left\\": 0, \\"scale\\": 0.0013020833333333333, \\"image_url\\": \\"https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_background.png\\"}",
      "with_detail": false,
      "is_heartbeat": false,
      "with_cleanup": false,
      "dilate_strength": 4,
      "negative_prompt": "[\\"text, sign, signature, watermark, levitated, in the air, floating, gap, extras, person, male, female, artifacts, dazed, drawing, sketch, painting, low res, low quality, low-res, low resolution, fake, fuzzy, poor quality, amateur photography, out of focus, cropped, deformations\\"]",
      "prompt_strength": 7.5,
      "background_strength": 0.8,
      "num_inference_steps": 25,
      "num_images_per_prompt": 1,
      "subject_control_strength": 0.8,
      "platform_control_strength": 0.2
    }
  }' \
  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.