nightmareai/majesty-diffusion:735ee4c3 – Run with an API on Replicate

Version

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

nightmareai /majesty-diffusion:735ee4c3

Input

clip_prompts

string

Shift + Return to add a new line

The portrait of a Majestic Princess, trending on artstation
The portrait of a Majestic Princess, trending on artstation

Prompts for CLIP guidance, multiple prompts allowed, one per line. Supports weights.

Default: "The portrait of a Majestic Princess, trending on artstation\n"

latent_prompt

string

Shift + Return to add a new line

The portrait of a Majestic Princess, trending on artstationThe portrait of a Majestic Princess, trending on artstation

Prompt for latent diffusion, single prompt, no weights.

Default: "The portrait of a Majestic Princess, trending on artstation"

height

integer

Output height (height OR width must be less than 1024 to avoid OOM)

Default: 512

width

integer

Output width

Default: 512

clip_scale

integer

Determines how much the CLIP prompts affect the image. Note the numeric scale is not the same as the latent prompt.

Default: 9500

latent_scale

integer

Determines how much the latent_prompt affects the image. Lower help with text interpretation, higher help with composition. Try values between 0-15. If you see too much text, lower it

aesthetic_loss_scale

integer

Aesthetic loss scale

Default: 400

starting_timestep

number

Starting timestep

Default: 0.9

model

string

Latent diffusion model (recommended to stick with finetuned - ongo and erlich may need to download, taking extra time)

Default: "finetuned"

latent_negative

string

Shift + Return to add a new line

Negative prompt for Latent Diffusion (things to steer away from)

Default: ""

output_steps

integer

Steps between outputs, 0 to disable progressive output. Minor speed impact.

Default: 10

init_image

file

Initial image (optional, used instead of noise if supplied)

init_mask

file

A mask same width and height as the initial image with the color white indicating where to inpaint

init_scale

integer

Controls how much the init image should influence the final result. Experiment with values around 1000

Default: 1000

init_brightness

number

Init image brightness

Default: 0

custom_settings

string

Shift + Return to add a new line

Custom settings cfg content, for custom or API usage. See Majesty docs.

Default: "\n"

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

npx create-replicate --model=nightmareai/majesty-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";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "nightmareai/majesty-diffusion:735ee4c3b41245b7b138acfb244981ab0bf8235b7cd122356f340c7df7f2994b",
  {
    input: {
      model: "finetuned",
      width: 512,
      height: 512,
      clip_scale: 9500,
      init_scale: 1000,
      clip_prompts: "The portrait of a Majestic Princess, trending on artstation\n",
      output_steps: 10,
      latent_prompt: "The portrait of a Majestic Princess, trending on artstation",
      custom_settings: "\n",
      init_brightness: 0,
      latent_negative: "",
      starting_timestep: 0.9,
      aesthetic_loss_scale: 400
    }
  }
);

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

output = replicate.run(
    "nightmareai/majesty-diffusion:735ee4c3b41245b7b138acfb244981ab0bf8235b7cd122356f340c7df7f2994b",
    input={
        "model": "finetuned",
        "width": 512,
        "height": 512,
        "clip_scale": 9500,
        "init_scale": 1000,
        "clip_prompts": "The portrait of a Majestic Princess, trending on artstation\n",
        "output_steps": 10,
        "latent_prompt": "The portrait of a Majestic Princess, trending on artstation",
        "custom_settings": "\n",
        "init_brightness": 0,
        "latent_negative": "",
        "starting_timestep": 0.9,
        "aesthetic_loss_scale": 400
    }
)

# The nightmareai/majesty-diffusion model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/nightmareai/majesty-diffusion/api#output-schema
    print(item)

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 nightmareai/majesty-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": "735ee4c3b41245b7b138acfb244981ab0bf8235b7cd122356f340c7df7f2994b",
    "input": {
      "model": "finetuned",
      "width": 512,
      "height": 512,
      "clip_scale": 9500,
      "init_scale": 1000,
      "clip_prompts": "The portrait of a Majestic Princess, trending on artstation\\n",
      "output_steps": 10,
      "latent_prompt": "The portrait of a Majestic Princess, trending on artstation",
      "custom_settings": "\\n",
      "init_brightness": 0,
      "latent_negative": "",
      "starting_timestep": 0.9,
      "aesthetic_loss_scale": 400
    }
  }' \
  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/nightmareai/majesty-diffusion@sha256:735ee4c3b41245b7b138acfb244981ab0bf8235b7cd122356f340c7df7f2994b \
  -i 'model="finetuned"' \
  -i 'width=512' \
  -i 'height=512' \
  -i 'clip_scale=9500' \
  -i 'init_scale=1000' \
  -i $'clip_prompts="The portrait of a Majestic Princess, trending on artstation\\n"' \
  -i 'output_steps=10' \
  -i 'latent_prompt="The portrait of a Majestic Princess, trending on artstation"' \
  -i $'custom_settings="\\n"' \
  -i 'init_brightness=0' \
  -i 'latent_negative=""' \
  -i 'starting_timestep=0.9' \
  -i 'aesthetic_loss_scale=400'

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/nightmareai/majesty-diffusion@sha256:735ee4c3b41245b7b138acfb244981ab0bf8235b7cd122356f340c7df7f2994b
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "finetuned",
      "width": 512,
      "height": 512,
      "clip_scale": 9500,
      "init_scale": 1000,
      "clip_prompts": "The portrait of a Majestic Princess, trending on artstation\\n",
      "output_steps": 10,
      "latent_prompt": "The portrait of a Majestic Princess, trending on artstation",
      "custom_settings": "\\n",
      "init_brightness": 0,
      "latent_negative": "",
      "starting_timestep": 0.9,
      "aesthetic_loss_scale": 400
    }
  }' \
  http://localhost:5000/predictions

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

Output

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