Monster Labs QrCode ControlNet on top of SD Realistic Vision v5.1

Cold

Public

405.9K runs

A100 (40GB)

License

GitHub

Weights

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance

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: 1

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=lucataco/illusion-diffusion-hq

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

const output = await replicate.run(
  "lucataco/illusion-diffusion-hq:3c64e669051f9b358e748c8e2fb8a06e64122a9ece762ef133252e2c99da77c1",
  {
    input: {
      seed: 1057727382,
      image: "https://replicate.delivery/pbxt/Ja8F0jwa45Bv8AxkH0VjcyhQ4KTN0RJiLYivSskJmeCWc30n/spiral.png",
      width: 768,
      border: 1,
      height: 768,
      prompt: "(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "ugly, disfigured, low quality, blurry, nsfw",
      qr_code_content: "",
      qrcode_background: "gray",
      num_inference_steps: 40,
      controlnet_conditioning_scale: 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 lucataco/illusion-diffusion-hq using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/illusion-diffusion-hq:3c64e669051f9b358e748c8e2fb8a06e64122a9ece762ef133252e2c99da77c1",
    input={
        "seed": 1057727382,
        "image": "https://replicate.delivery/pbxt/Ja8F0jwa45Bv8AxkH0VjcyhQ4KTN0RJiLYivSskJmeCWc30n/spiral.png",
        "width": 768,
        "border": 1,
        "height": 768,
        "prompt": "(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
        "qr_code_content": "",
        "qrcode_background": "gray",
        "num_inference_steps": 40,
        "controlnet_conditioning_scale": 1
    }
)

# 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 lucataco/illusion-diffusion-hq 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": "lucataco/illusion-diffusion-hq:3c64e669051f9b358e748c8e2fb8a06e64122a9ece762ef133252e2c99da77c1",
    "input": {
      "seed": 1057727382,
      "image": "https://replicate.delivery/pbxt/Ja8F0jwa45Bv8AxkH0VjcyhQ4KTN0RJiLYivSskJmeCWc30n/spiral.png",
      "width": 768,
      "border": 1,
      "height": 768,
      "prompt": "(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
      "qr_code_content": "",
      "qrcode_background": "gray",
      "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.

Output

{
  "completed_at": "2023-09-24T05:44:01.816875Z",
  "created_at": "2023-09-24T05:43:54.064980Z",
  "data_removed": false,
  "error": null,
  "id": "kcusc63brykrmm5iwald3b445q",
  "input": {
    "seed": 1057727382,
    "image": "https://replicate.delivery/pbxt/Ja8F0jwa45Bv8AxkH0VjcyhQ4KTN0RJiLYivSskJmeCWc30n/spiral.png",
    "width": 768,
    "border": 1,
    "height": 768,
    "prompt": "(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
    "qr_code_content": "",
    "qrcode_background": "gray",
    "num_inference_steps": 40,
    "controlnet_conditioning_scale": 1
  },
  "logs": "Seed: 1057727382\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:05,  6.96it/s]\n  5%|▌         | 2/40 [00:00<00:05,  6.89it/s]\n  8%|▊         | 3/40 [00:00<00:05,  6.87it/s]\n 10%|█         | 4/40 [00:00<00:05,  6.85it/s]\n 12%|█▎        | 5/40 [00:00<00:05,  6.83it/s]\n 15%|█▌        | 6/40 [00:00<00:04,  6.83it/s]\n 18%|█▊        | 7/40 [00:01<00:04,  6.79it/s]\n 20%|██        | 8/40 [00:01<00:04,  6.79it/s]\n 22%|██▎       | 9/40 [00:01<00:04,  6.80it/s]\n 25%|██▌       | 10/40 [00:01<00:04,  6.80it/s]\n 28%|██▊       | 11/40 [00:01<00:04,  6.81it/s]\n 30%|███       | 12/40 [00:01<00:04,  6.84it/s]\n 32%|███▎      | 13/40 [00:01<00:03,  6.83it/s]\n 35%|███▌      | 14/40 [00:02<00:03,  6.83it/s]\n 38%|███▊      | 15/40 [00:02<00:03,  6.83it/s]\n 40%|████      | 16/40 [00:02<00:03,  6.84it/s]\n 42%|████▎     | 17/40 [00:02<00:03,  6.84it/s]\n 45%|████▌     | 18/40 [00:02<00:03,  6.85it/s]\n 48%|████▊     | 19/40 [00:02<00:03,  6.85it/s]\n 50%|█████     | 20/40 [00:02<00:02,  6.84it/s]\n 52%|█████▎    | 21/40 [00:03<00:02,  6.84it/s]\n 55%|█████▌    | 22/40 [00:03<00:02,  6.84it/s]\n 57%|█████▊    | 23/40 [00:03<00:02,  6.84it/s]\n 60%|██████    | 24/40 [00:03<00:02,  6.84it/s]\n 62%|██████▎   | 25/40 [00:03<00:02,  6.84it/s]\n 65%|██████▌   | 26/40 [00:03<00:02,  6.83it/s]\n 68%|██████▊   | 27/40 [00:03<00:01,  6.83it/s]\n 70%|███████   | 28/40 [00:04<00:01,  6.83it/s]\n 72%|███████▎  | 29/40 [00:04<00:01,  6.82it/s]\n 75%|███████▌  | 30/40 [00:04<00:01,  6.82it/s]\n 78%|███████▊  | 31/40 [00:04<00:01,  6.84it/s]\n 80%|████████  | 32/40 [00:04<00:01,  6.83it/s]\n 82%|████████▎ | 33/40 [00:04<00:01,  6.83it/s]\n 85%|████████▌ | 34/40 [00:04<00:00,  6.83it/s]\n 88%|████████▊ | 35/40 [00:05<00:00,  6.83it/s]\n 90%|█████████ | 36/40 [00:05<00:00,  6.83it/s]\n 92%|█████████▎| 37/40 [00:05<00:00,  6.83it/s]\n 95%|█████████▌| 38/40 [00:05<00:00,  6.83it/s]\n 98%|█████████▊| 39/40 [00:05<00:00,  6.83it/s]\n100%|██████████| 40/40 [00:05<00:00,  6.82it/s]\n100%|██████████| 40/40 [00:05<00:00,  6.83it/s]",
  "metrics": {
    "predict_time": 7.797666,
    "total_time": 7.751895
  },
  "output": [
    "https://replicate.delivery/pbxt/HPJuktTvnJojD94PbrmeDWHcgmHfxLc5bOK7XlLFUSeB1vOjA/output-0.png"
  ],
  "started_at": "2023-09-24T05:43:54.019209Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/kcusc63brykrmm5iwald3b445q",
    "cancel": "https://api.replicate.com/v1/predictions/kcusc63brykrmm5iwald3b445q/cancel"
  },
  "version": "3c64e669051f9b358e748c8e2fb8a06e64122a9ece762ef133252e2c99da77c1"
}

Generated in

7.8 seconds

Tweak it Iterate in playgroundReport View full prediction

Seed: 1057727382
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:05,  6.96it/s]
  5%|▌         | 2/40 [00:00<00:05,  6.89it/s]
  8%|▊         | 3/40 [00:00<00:05,  6.87it/s]
 10%|█         | 4/40 [00:00<00:05,  6.85it/s]
 12%|█▎        | 5/40 [00:00<00:05,  6.83it/s]
 15%|█▌        | 6/40 [00:00<00:04,  6.83it/s]
 18%|█▊        | 7/40 [00:01<00:04,  6.79it/s]
 20%|██        | 8/40 [00:01<00:04,  6.79it/s]
 22%|██▎       | 9/40 [00:01<00:04,  6.80it/s]
 25%|██▌       | 10/40 [00:01<00:04,  6.80it/s]
 28%|██▊       | 11/40 [00:01<00:04,  6.81it/s]
 30%|███       | 12/40 [00:01<00:04,  6.84it/s]
 32%|███▎      | 13/40 [00:01<00:03,  6.83it/s]
 35%|███▌      | 14/40 [00:02<00:03,  6.83it/s]
 38%|███▊      | 15/40 [00:02<00:03,  6.83it/s]
 40%|████      | 16/40 [00:02<00:03,  6.84it/s]
 42%|████▎     | 17/40 [00:02<00:03,  6.84it/s]
 45%|████▌     | 18/40 [00:02<00:03,  6.85it/s]
 48%|████▊     | 19/40 [00:02<00:03,  6.85it/s]
 50%|█████     | 20/40 [00:02<00:02,  6.84it/s]
 52%|█████▎    | 21/40 [00:03<00:02,  6.84it/s]
 55%|█████▌    | 22/40 [00:03<00:02,  6.84it/s]
 57%|█████▊    | 23/40 [00:03<00:02,  6.84it/s]
 60%|██████    | 24/40 [00:03<00:02,  6.84it/s]
 62%|██████▎   | 25/40 [00:03<00:02,  6.84it/s]
 65%|██████▌   | 26/40 [00:03<00:02,  6.83it/s]
 68%|██████▊   | 27/40 [00:03<00:01,  6.83it/s]
 70%|███████   | 28/40 [00:04<00:01,  6.83it/s]
 72%|███████▎  | 29/40 [00:04<00:01,  6.82it/s]
 75%|███████▌  | 30/40 [00:04<00:01,  6.82it/s]
 78%|███████▊  | 31/40 [00:04<00:01,  6.84it/s]
 80%|████████  | 32/40 [00:04<00:01,  6.83it/s]
 82%|████████▎ | 33/40 [00:04<00:01,  6.83it/s]
 85%|████████▌ | 34/40 [00:04<00:00,  6.83it/s]
 88%|████████▊ | 35/40 [00:05<00:00,  6.83it/s]
 90%|█████████ | 36/40 [00:05<00:00,  6.83it/s]
 92%|█████████▎| 37/40 [00:05<00:00,  6.83it/s]
 95%|█████████▌| 38/40 [00:05<00:00,  6.83it/s]
 98%|█████████▊| 39/40 [00:05<00:00,  6.83it/s]
100%|██████████| 40/40 [00:05<00:00,  6.82it/s]
100%|██████████| 40/40 [00:05<00:00,  6.83it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.017 to run on Replicate, or 58 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 A100 (40GB) GPU hardware. Predictions typically complete within 15 seconds.

Readme

About

This is a fork of andreasjansson/cog-qrcode cog model, but implemented onto Realistic Vision v5.1

Based on the original model andreasjansson/illusion which (at this time) is running on SD 2.1

(Use seed=-1 to randomize)

Support

Give me a follow if you like my work! @lucataco93