nightmareai/disco-diffusion:3c128f65 – Run with an API on Replicate

Version

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

nightmareai /disco-diffusion:3c128f65

Playground API

Input

steps

integer

Number of steps, higher numbers will give more refined output but will take longer

Default: 100

prompt

string

Shift + Return to add a new line

A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.

Text Prompt

Default: "A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation."

width

integer

Width of the output image, higher numbers will take longer

Default: 1280

height

integer

Height of the output image, higher numbers will take longer

Default: 768

diffusion_model

string

Diffusion Model

Default: "512x512_diffusion_uncond_finetune_008100"

diffusion_sampling_mode

string

Diffusion Sampling Mode

Default: "ddim"

ViTB32

boolean

Use ViTB32 model

Default: true

ViTB16

boolean

Use ViTB16 model

Default: true

ViTL14

boolean

Use ViTB14 model

Default: false

ViTL14_336

boolean

Use ViTL14_336 model

Default: false

RN50

boolean

Use RN50 model

Default: true

RN50x4

boolean

Use RN50x4 model

Default: false

RN50x16

boolean

Use RN50x16 model

Default: false

RN50x64

boolean

Use RN50x64 model

Default: false

RN50x101

boolean

Use RN50x101 model

Default: false

RN101

boolean

Use RN101 model

Default: false

ViTB32_laion2b_e16

boolean

Use ViTB32_laion2b_e16 model

Default: false

ViTB32_laion400m_e31

boolean

Use ViTB32_laion400m_e31 model

Default: false

ViTB32_laion400m_e32

boolean

Use ViTB32_laion400m_e32 model

Default: false

ViTB32quickgelu_laion400m_e31

boolean

Use ViTB32quickgelu_laion400m_e31 model

Default: false

ViTB32quickgelu_laion400m_e32

boolean

Use ViTB32quickgelu_laion400m_e32 model

Default: false

ViTB16_laion400m_e31

boolean

Use ViTB16_laion400m_e31 model

Default: false

ViTB16_laion400m_e32

boolean

Use ViTB16_laion400m_e32 model

Default: false

RN50_yffcc15m

boolean

Use RN50_yffcc15m model

Default: false

RN50_cc12m

boolean

Use RN50_cc12m model

Default: false

RN50_quickgelu_yfcc15m

boolean

Use RN50_quickgelu_yfcc15m model

Default: false

RN50_quickgelu_cc12m

boolean

Use RN50_quickgelu_cc12m model

Default: false

RN101_yfcc15m

boolean

Use RN101_yfcc15m model

Default: false

RN101_quickgelu_yfcc15m

boolean

Use RN101_quickgelu_yfcc15m model

Default: false

use_secondary_model

boolean

Use secondary model

Default: true

clip_guidance_scale

integer

CLIP Guidance Scale

Default: 5000

tv_scale

integer

TV Scale

Default: 0

range_scale

integer

Range Scale

Default: 150

sat_scale

integer

Saturation Scale

Default: 0

cutn_batches

integer

Cut Batches

Default: 4

skip_augs

boolean

Skip Augmentations

Default: false

init_image

file

Initial image to start generation from

target_image

file

Target image to generate towards, similarly to the text prompt

init_scale

integer

Initial Scale

Default: 1000

target_scale

integer

Target Scale

Default: 20000

skip_steps

integer

Skip Steps

Default: 10

display_rate

integer

Steps between outputs, lower numbers may slow down generation.

Default: 20

seed

integer

(minimum: 0, maximum: 4294967295)

Seed (leave empty to use a random seed)

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

npx create-replicate --model=nightmareai/disco-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/disco-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nightmareai/disco-diffusion:3c128f652e9f24e72896ac0b019e47facfd6bccf93104d50f09f1f2196325507",
  {
    input: {
      RN50: true,
      RN101: false,
      steps: 100,
      width: 1280,
      RN50x4: false,
      ViTB16: true,
      ViTB32: true,
      ViTL14: false,
      height: 768,
      prompt: "A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.",
      RN50x16: false,
      RN50x64: false,
      RN50x101: false,
      tv_scale: 0,
      sat_scale: 0,
      skip_augs: false,
      RN50_cc12m: false,
      ViTL14_336: false,
      init_scale: 1000,
      skip_steps: 10,
      range_scale: 150,
      cutn_batches: 4,
      display_rate: 20,
      target_scale: 20000,
      RN101_yfcc15m: false,
      RN50_yffcc15m: false,
      diffusion_model: "512x512_diffusion_uncond_finetune_008100",
      ViTB32_laion2b_e16: false,
      clip_guidance_scale: 5000,
      use_secondary_model: true,
      RN50_quickgelu_cc12m: false,
      ViTB16_laion400m_e31: false,
      ViTB16_laion400m_e32: false,
      ViTB32_laion400m_e31: false,
      ViTB32_laion400m_e32: false,
      RN50_quickgelu_yfcc15m: false,
      RN101_quickgelu_yfcc15m: false,
      diffusion_sampling_mode: "ddim",
      ViTB32quickgelu_laion400m_e31: false,
      ViTB32quickgelu_laion400m_e32: false
    }
  }
);

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

output = replicate.run(
    "nightmareai/disco-diffusion:3c128f652e9f24e72896ac0b019e47facfd6bccf93104d50f09f1f2196325507",
    input={
        "RN50": True,
        "RN101": False,
        "steps": 100,
        "width": 1280,
        "RN50x4": False,
        "ViTB16": True,
        "ViTB32": True,
        "ViTL14": False,
        "height": 768,
        "prompt": "A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.",
        "RN50x16": False,
        "RN50x64": False,
        "RN50x101": False,
        "tv_scale": 0,
        "sat_scale": 0,
        "skip_augs": False,
        "RN50_cc12m": False,
        "ViTL14_336": False,
        "init_scale": 1000,
        "skip_steps": 10,
        "range_scale": 150,
        "cutn_batches": 4,
        "display_rate": 20,
        "target_scale": 20000,
        "RN101_yfcc15m": False,
        "RN50_yffcc15m": False,
        "diffusion_model": "512x512_diffusion_uncond_finetune_008100",
        "ViTB32_laion2b_e16": False,
        "clip_guidance_scale": 5000,
        "use_secondary_model": True,
        "RN50_quickgelu_cc12m": False,
        "ViTB16_laion400m_e31": False,
        "ViTB16_laion400m_e32": False,
        "ViTB32_laion400m_e31": False,
        "ViTB32_laion400m_e32": False,
        "RN50_quickgelu_yfcc15m": False,
        "RN101_quickgelu_yfcc15m": False,
        "diffusion_sampling_mode": "ddim",
        "ViTB32quickgelu_laion400m_e31": False,
        "ViTB32quickgelu_laion400m_e32": False
    }
)

# The nightmareai/disco-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/disco-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/disco-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": "nightmareai/disco-diffusion:3c128f652e9f24e72896ac0b019e47facfd6bccf93104d50f09f1f2196325507",
    "input": {
      "RN50": true,
      "RN101": false,
      "steps": 100,
      "width": 1280,
      "RN50x4": false,
      "ViTB16": true,
      "ViTB32": true,
      "ViTL14": false,
      "height": 768,
      "prompt": "A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.",
      "RN50x16": false,
      "RN50x64": false,
      "RN50x101": false,
      "tv_scale": 0,
      "sat_scale": 0,
      "skip_augs": false,
      "RN50_cc12m": false,
      "ViTL14_336": false,
      "init_scale": 1000,
      "skip_steps": 10,
      "range_scale": 150,
      "cutn_batches": 4,
      "display_rate": 20,
      "target_scale": 20000,
      "RN101_yfcc15m": false,
      "RN50_yffcc15m": false,
      "diffusion_model": "512x512_diffusion_uncond_finetune_008100",
      "ViTB32_laion2b_e16": false,
      "clip_guidance_scale": 5000,
      "use_secondary_model": true,
      "RN50_quickgelu_cc12m": false,
      "ViTB16_laion400m_e31": false,
      "ViTB16_laion400m_e32": false,
      "ViTB32_laion400m_e31": false,
      "ViTB32_laion400m_e32": false,
      "RN50_quickgelu_yfcc15m": false,
      "RN101_quickgelu_yfcc15m": false,
      "diffusion_sampling_mode": "ddim",
      "ViTB32quickgelu_laion400m_e31": false,
      "ViTB32quickgelu_laion400m_e32": false
    }
  }' \
  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.