andreasjansson/illusion – Run with an API on Replicate

andreasjansson / illusion

Monster Labs' control_v1p_sd15_qrcode_monster ControlNet on top of SD 1.5

Cold

Public
402.2K runs
L40S
GitHub

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

An oil painting of medieval city streets with buildings and trees and peopleAn oil painting of medieval city streets with buildings and trees and people

The prompt to guide QR Code generation.

qr_code_content

*string

Shift + Return to add a new line

The website/content your QR Code will point to.

negative_prompt

string

Shift + Return to add a new line

ugly, disfigured, low quality, blurry, nsfwugly, disfigured, low quality, blurry, nsfw

The negative prompt to guide image generation.

Default: "ugly, disfigured, low quality, blurry, nsfw"

num_inference_steps

integer

(minimum: 20, maximum: 100)

Number of diffusion steps

Default: 40

guidance_scale

number

(minimum: 0.1, maximum: 30)

Scale for classifier-free guidance

Default: 7.5

seed

integer

Seed

Default: -1

width

integer

Width out the output image

Default: 768

height

integer

Height out the output image

Default: 768

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs

Default: 1

image

file

Input image. If none is provided, a QR code will be generated

controlnet_conditioning_scale

number

(minimum: 0, maximum: 4)

The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added to the residual in the original unet.

Default: 2.2

border

integer

(minimum: 0, maximum: 4)

QR code border size

Default: 1

qrcode_background

string

Background color of raw QR code

Default: "gray"

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

npx create-replicate --model=andreasjansson/illusion

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

const output = await replicate.run(
  "andreasjansson/illusion:75d51a73fce3c00de31ed9ab4358c73e8fc0f627dc8ce975818e653317cb919b",
  {
    input: {
      seed: -1,
      image: "https://replicate.delivery/pbxt/Ja3ByHnLrLmMc1uI7z0PZyBdQWdU4eQUoJJvXRMnGQbT9y5o/F6WmkWWacAAcyLe.png",
      width: 768,
      border: 4,
      height: 768,
      prompt: "An oil painting of medieval city streets with buildings and trees and people",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "ugly, disfigured, low quality, blurry, nsfw",
      qr_code_content: "",
      qrcode_background: "white",
      num_inference_steps: 40,
      controlnet_conditioning_scale: 1
    }
  }
);
console.log(output);

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

output = replicate.run(
    "andreasjansson/illusion:75d51a73fce3c00de31ed9ab4358c73e8fc0f627dc8ce975818e653317cb919b",
    input={
        "seed": -1,
        "image": "https://replicate.delivery/pbxt/Ja3ByHnLrLmMc1uI7z0PZyBdQWdU4eQUoJJvXRMnGQbT9y5o/F6WmkWWacAAcyLe.png",
        "width": 768,
        "border": 4,
        "height": 768,
        "prompt": "An oil painting of medieval city streets with buildings and trees and people",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
        "qr_code_content": "",
        "qrcode_background": "white",
        "num_inference_steps": 40,
        "controlnet_conditioning_scale": 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 andreasjansson/illusion 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": "75d51a73fce3c00de31ed9ab4358c73e8fc0f627dc8ce975818e653317cb919b",
    "input": {
      "seed": -1,
      "image": "https://replicate.delivery/pbxt/Ja3ByHnLrLmMc1uI7z0PZyBdQWdU4eQUoJJvXRMnGQbT9y5o/F6WmkWWacAAcyLe.png",
      "width": 768,
      "border": 4,
      "height": 768,
      "prompt": "An oil painting of medieval city streets with buildings and trees and people",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
      "qr_code_content": "",
      "qrcode_background": "white",
      "num_inference_steps": 40,
      "controlnet_conditioning_scale": 1
    }
  }' \
  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/andreasjansson/illusion@sha256:75d51a73fce3c00de31ed9ab4358c73e8fc0f627dc8ce975818e653317cb919b \
  -i 'seed=-1' \
  -i 'image="https://replicate.delivery/pbxt/Ja3ByHnLrLmMc1uI7z0PZyBdQWdU4eQUoJJvXRMnGQbT9y5o/F6WmkWWacAAcyLe.png"' \
  -i 'width=768' \
  -i 'border=4' \
  -i 'height=768' \
  -i 'prompt="An oil painting of medieval city streets with buildings and trees and people"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="ugly, disfigured, low quality, blurry, nsfw"' \
  -i 'qr_code_content=""' \
  -i 'qrcode_background="white"' \
  -i 'num_inference_steps=40' \
  -i 'controlnet_conditioning_scale=1'

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/andreasjansson/illusion@sha256:75d51a73fce3c00de31ed9ab4358c73e8fc0f627dc8ce975818e653317cb919b
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "image": "https://replicate.delivery/pbxt/Ja3ByHnLrLmMc1uI7z0PZyBdQWdU4eQUoJJvXRMnGQbT9y5o/F6WmkWWacAAcyLe.png",
      "width": 768,
      "border": 4,
      "height": 768,
      "prompt": "An oil painting of medieval city streets with buildings and trees and people",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
      "qr_code_content": "",
      "qrcode_background": "white",
      "num_inference_steps": 40,
      "controlnet_conditioning_scale": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-09-23T23:42:42.564603Z",
  "created_at": "2023-09-23T23:42:35.790473Z",
  "data_removed": false,
  "error": null,
  "id": "2gwatqdbjd6hno4qtqkk5y26je",
  "input": {
    "seed": -1,
    "image": "https://replicate.delivery/pbxt/Ja3ByHnLrLmMc1uI7z0PZyBdQWdU4eQUoJJvXRMnGQbT9y5o/F6WmkWWacAAcyLe.png",
    "width": 768,
    "border": 4,
    "height": 768,
    "prompt": "An oil painting of medieval city streets with buildings and trees and people",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
    "qr_code_content": "",
    "qrcode_background": "white",
    "num_inference_steps": 40,
    "controlnet_conditioning_scale": 1
  },
  "logs": "0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:04,  8.43it/s]\n  5%|▌         | 2/40 [00:00<00:04,  8.37it/s]\n  8%|▊         | 3/40 [00:00<00:04,  8.34it/s]\n 10%|█         | 4/40 [00:00<00:04,  8.32it/s]\n 12%|█▎        | 5/40 [00:00<00:04,  8.33it/s]\n 15%|█▌        | 6/40 [00:00<00:04,  8.32it/s]\n 18%|█▊        | 7/40 [00:00<00:03,  8.31it/s]\n 20%|██        | 8/40 [00:00<00:03,  8.30it/s]\n 22%|██▎       | 9/40 [00:01<00:03,  8.30it/s]\n 25%|██▌       | 10/40 [00:01<00:03,  8.30it/s]\n 28%|██▊       | 11/40 [00:01<00:03,  8.30it/s]\n 30%|███       | 12/40 [00:01<00:03,  8.30it/s]\n 32%|███▎      | 13/40 [00:01<00:03,  8.30it/s]\n 35%|███▌      | 14/40 [00:01<00:03,  8.30it/s]\n 38%|███▊      | 15/40 [00:01<00:03,  8.31it/s]\n 40%|████      | 16/40 [00:01<00:02,  8.33it/s]\n 42%|████▎     | 17/40 [00:02<00:02,  8.33it/s]\n 45%|████▌     | 18/40 [00:02<00:02,  8.33it/s]\n 48%|████▊     | 19/40 [00:02<00:02,  8.33it/s]\n 50%|█████     | 20/40 [00:02<00:02,  8.34it/s]\n 52%|█████▎    | 21/40 [00:02<00:02,  8.34it/s]\n 55%|█████▌    | 22/40 [00:02<00:02,  8.34it/s]\n 57%|█████▊    | 23/40 [00:02<00:02,  8.33it/s]\n 60%|██████    | 24/40 [00:02<00:01,  8.34it/s]\n 62%|██████▎   | 25/40 [00:03<00:01,  8.35it/s]\n 65%|██████▌   | 26/40 [00:03<00:01,  8.35it/s]\n 68%|██████▊   | 27/40 [00:03<00:01,  8.35it/s]\n 70%|███████   | 28/40 [00:03<00:01,  8.34it/s]\n 72%|███████▎  | 29/40 [00:03<00:01,  8.35it/s]\n 75%|███████▌  | 30/40 [00:03<00:01,  8.35it/s]\n 78%|███████▊  | 31/40 [00:03<00:01,  8.34it/s]\n 80%|████████  | 32/40 [00:03<00:00,  8.34it/s]\n 82%|████████▎ | 33/40 [00:03<00:00,  8.34it/s]\n 85%|████████▌ | 34/40 [00:04<00:00,  8.34it/s]\n 88%|████████▊ | 35/40 [00:04<00:00,  8.34it/s]\n 90%|█████████ | 36/40 [00:04<00:00,  8.34it/s]\n 92%|█████████▎| 37/40 [00:04<00:00,  8.33it/s]\n 95%|█████████▌| 38/40 [00:04<00:00,  8.32it/s]\n 98%|█████████▊| 39/40 [00:04<00:00,  8.32it/s]\n100%|██████████| 40/40 [00:04<00:00,  8.32it/s]\n100%|██████████| 40/40 [00:04<00:00,  8.33it/s]",
  "metrics": {
    "predict_time": 6.780116,
    "total_time": 6.77413
  },
  "output": [
    "https://replicate.delivery/pbxt/hHJNV9QteKX8DK2ckkUeXsqbEIKNGFXU1fN0MJoizz3iPlOjA/output-0.png"
  ],
  "started_at": "2023-09-23T23:42:35.784487Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2gwatqdbjd6hno4qtqkk5y26je",
    "cancel": "https://api.replicate.com/v1/predictions/2gwatqdbjd6hno4qtqkk5y26je/cancel"
  },
  "version": "75d51a73fce3c00de31ed9ab4358c73e8fc0f627dc8ce975818e653317cb919b"
}

Generated in

6.8 seconds

Tweak itReport

0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:04,  8.43it/s]
  5%|▌         | 2/40 [00:00<00:04,  8.37it/s]
  8%|▊         | 3/40 [00:00<00:04,  8.34it/s]
 10%|█         | 4/40 [00:00<00:04,  8.32it/s]
 12%|█▎        | 5/40 [00:00<00:04,  8.33it/s]
 15%|█▌        | 6/40 [00:00<00:04,  8.32it/s]
 18%|█▊        | 7/40 [00:00<00:03,  8.31it/s]
 20%|██        | 8/40 [00:00<00:03,  8.30it/s]
 22%|██▎       | 9/40 [00:01<00:03,  8.30it/s]
 25%|██▌       | 10/40 [00:01<00:03,  8.30it/s]
 28%|██▊       | 11/40 [00:01<00:03,  8.30it/s]
 30%|███       | 12/40 [00:01<00:03,  8.30it/s]
 32%|███▎      | 13/40 [00:01<00:03,  8.30it/s]
 35%|███▌      | 14/40 [00:01<00:03,  8.30it/s]
 38%|███▊      | 15/40 [00:01<00:03,  8.31it/s]
 40%|████      | 16/40 [00:01<00:02,  8.33it/s]
 42%|████▎     | 17/40 [00:02<00:02,  8.33it/s]
 45%|████▌     | 18/40 [00:02<00:02,  8.33it/s]
 48%|████▊     | 19/40 [00:02<00:02,  8.33it/s]
 50%|█████     | 20/40 [00:02<00:02,  8.34it/s]
 52%|█████▎    | 21/40 [00:02<00:02,  8.34it/s]
 55%|█████▌    | 22/40 [00:02<00:02,  8.34it/s]
 57%|█████▊    | 23/40 [00:02<00:02,  8.33it/s]
 60%|██████    | 24/40 [00:02<00:01,  8.34it/s]
 62%|██████▎   | 25/40 [00:03<00:01,  8.35it/s]
 65%|██████▌   | 26/40 [00:03<00:01,  8.35it/s]
 68%|██████▊   | 27/40 [00:03<00:01,  8.35it/s]
 70%|███████   | 28/40 [00:03<00:01,  8.34it/s]
 72%|███████▎  | 29/40 [00:03<00:01,  8.35it/s]
 75%|███████▌  | 30/40 [00:03<00:01,  8.35it/s]
 78%|███████▊  | 31/40 [00:03<00:01,  8.34it/s]
 80%|████████  | 32/40 [00:03<00:00,  8.34it/s]
 82%|████████▎ | 33/40 [00:03<00:00,  8.34it/s]
 85%|████████▌ | 34/40 [00:04<00:00,  8.34it/s]
 88%|████████▊ | 35/40 [00:04<00:00,  8.34it/s]
 90%|█████████ | 36/40 [00:04<00:00,  8.34it/s]
 92%|█████████▎| 37/40 [00:04<00:00,  8.33it/s]
 95%|█████████▌| 38/40 [00:04<00:00,  8.32it/s]
 98%|█████████▊| 39/40 [00:04<00:00,  8.32it/s]
100%|██████████| 40/40 [00:04<00:00,  8.32it/s]
100%|██████████| 40/40 [00:04<00:00,  8.33it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0049 to run on Replicate, or 204 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 6 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This is https://huggingface.co/monster-labs/control_v1p_sd15_qrcode_monster on top of Realistic Vision 5.1