nateraw/qrcode-stable-diffusion:9cdabf8f – Run with an API on Replicate

Version

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

nateraw /qrcode-stable-diffusion:9cdabf8f

Input

prompt

*string

Shift + Return to add a new line

The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibliThe french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli

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

batch_size

integer

(minimum: 1, maximum: 4)

Batch size for this prediction

Default: 1

strength

number

(minimum: 0, maximum: 1)

Indicates how much to transform the masked portion of the reference `image`. Must be between 0 and 1.

Default: 0.9

controlnet_conditioning_scale

number

(minimum: 1, maximum: 2)

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

Default: 1.5

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

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

const output = await replicate.run(
  "nateraw/qrcode-stable-diffusion:9cdabf8f8a991351960c7ce2105de2909514b40bd27ac202dba57935b07d29d4",
  {
    input: {
      seed: 1234,
      prompt: "The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli",
      strength: 0.9,
      batch_size: 1,
      guidance_scale: 7.5,
      negative_prompt: "ugly, disfigured, low quality, blurry, nsfw",
      qr_code_content: "https://replicate.com",
      num_inference_steps: 40,
      controlnet_conditioning_scale: 1.5
    }
  }
);

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

output = replicate.run(
    "nateraw/qrcode-stable-diffusion:9cdabf8f8a991351960c7ce2105de2909514b40bd27ac202dba57935b07d29d4",
    input={
        "seed": 1234,
        "prompt": "The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli",
        "strength": 0.9,
        "batch_size": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
        "qr_code_content": "https://replicate.com",
        "num_inference_steps": 40,
        "controlnet_conditioning_scale": 1.5
    }
)
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 nateraw/qrcode-stable-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": "9cdabf8f8a991351960c7ce2105de2909514b40bd27ac202dba57935b07d29d4",
    "input": {
      "seed": 1234,
      "prompt": "The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli",
      "strength": 0.9,
      "batch_size": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
      "qr_code_content": "https://replicate.com",
      "num_inference_steps": 40,
      "controlnet_conditioning_scale": 1.5
    }
  }' \
  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/nateraw/qrcode-stable-diffusion@sha256:9cdabf8f8a991351960c7ce2105de2909514b40bd27ac202dba57935b07d29d4 \
  -i 'seed=1234' \
  -i 'prompt="The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli"' \
  -i 'strength=0.9' \
  -i 'batch_size=1' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="ugly, disfigured, low quality, blurry, nsfw"' \
  -i 'qr_code_content="https://replicate.com"' \
  -i 'num_inference_steps=40' \
  -i 'controlnet_conditioning_scale=1.5'

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/nateraw/qrcode-stable-diffusion@sha256:9cdabf8f8a991351960c7ce2105de2909514b40bd27ac202dba57935b07d29d4
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 1234,
      "prompt": "The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli",
      "strength": 0.9,
      "batch_size": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
      "qr_code_content": "https://replicate.com",
      "num_inference_steps": 40,
      "controlnet_conditioning_scale": 1.5
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-06-30T02:39:25.006348Z",
  "created_at": "2023-06-30T02:32:43.529254Z",
  "data_removed": false,
  "error": null,
  "id": "vzurxizbjue7tk54vkxnlzvzta",
  "input": {
    "seed": 1234,
    "prompt": "The french countryside, green pastures, lush environment, vivid colors, animation by studio ghibli",
    "strength": 0.9,
    "batch_size": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
    "qr_code_content": "https://replicate.com",
    "num_inference_steps": 40,
    "controlnet_conditioning_scale": 1.5
  },
  "logs": "Generating QR Code from content\n  0%|          | 0/36 [00:00<?, ?it/s]\n  3%|▎         | 1/36 [00:00<00:21,  1.61it/s]\n  6%|▌         | 2/36 [00:01<00:18,  1.81it/s]\n  8%|▊         | 3/36 [00:01<00:17,  1.89it/s]\n 11%|█         | 4/36 [00:02<00:16,  1.92it/s]\n 14%|█▍        | 5/36 [00:02<00:16,  1.94it/s]\n 17%|█▋        | 6/36 [00:03<00:15,  1.95it/s]\n 19%|█▉        | 7/36 [00:03<00:14,  1.95it/s]\n 22%|██▏       | 8/36 [00:04<00:14,  1.96it/s]\n 25%|██▌       | 9/36 [00:04<00:13,  1.96it/s]\n 28%|██▊       | 10/36 [00:05<00:13,  1.97it/s]\n 31%|███       | 11/36 [00:05<00:12,  1.97it/s]\n 33%|███▎      | 12/36 [00:06<00:12,  1.96it/s]\n 36%|███▌      | 13/36 [00:06<00:11,  1.96it/s]\n 39%|███▉      | 14/36 [00:07<00:11,  1.95it/s]\n 42%|████▏     | 15/36 [00:07<00:10,  1.95it/s]\n 44%|████▍     | 16/36 [00:08<00:10,  1.95it/s]\n 47%|████▋     | 17/36 [00:08<00:09,  1.95it/s]\n 50%|█████     | 18/36 [00:09<00:09,  1.95it/s]\n 53%|█████▎    | 19/36 [00:09<00:08,  1.95it/s]\n 56%|█████▌    | 20/36 [00:10<00:08,  1.94it/s]\n 58%|█████▊    | 21/36 [00:10<00:07,  1.94it/s]\n 61%|██████    | 22/36 [00:11<00:07,  1.94it/s]\n 64%|██████▍   | 23/36 [00:11<00:06,  1.94it/s]\n 67%|██████▋   | 24/36 [00:12<00:06,  1.94it/s]\n 69%|██████▉   | 25/36 [00:12<00:05,  1.94it/s]\n 72%|███████▏  | 26/36 [00:13<00:05,  1.94it/s]\n 75%|███████▌  | 27/36 [00:13<00:04,  1.94it/s]\n 78%|███████▊  | 28/36 [00:14<00:04,  1.93it/s]\n 81%|████████  | 29/36 [00:14<00:03,  1.94it/s]\n 83%|████████▎ | 30/36 [00:15<00:03,  1.93it/s]\n 86%|████████▌ | 31/36 [00:15<00:02,  1.93it/s]\n 89%|████████▉ | 32/36 [00:16<00:02,  1.93it/s]\n 92%|█████████▏| 33/36 [00:17<00:01,  1.93it/s]\n 94%|█████████▍| 34/36 [00:17<00:01,  1.93it/s]\n 97%|█████████▋| 35/36 [00:18<00:00,  1.93it/s]\n100%|██████████| 36/36 [00:18<00:00,  1.92it/s]\n100%|██████████| 36/36 [00:18<00:00,  1.94it/s]",
  "metrics": {
    "predict_time": 27.185761,
    "total_time": 401.477094
  },
  "output": [
    "https://replicate.delivery/pbxt/ELT1NcUX34Y9JRTgMBAC0fdsVJG0j5flt6ksOaouz8YcJfViA/output-0.png"
  ],
  "started_at": "2023-06-30T02:38:57.820587Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/vzurxizbjue7tk54vkxnlzvzta",
    "cancel": "https://api.replicate.com/v1/predictions/vzurxizbjue7tk54vkxnlzvzta/cancel"
  },
  "version": "9cdabf8f8a991351960c7ce2105de2909514b40bd27ac202dba57935b07d29d4"
}

Generated in

27.2 seconds

Tweak itReport

Generating QR Code from content
  0%|          | 0/36 [00:00<?, ?it/s]
  3%|▎         | 1/36 [00:00<00:21,  1.61it/s]
  6%|▌         | 2/36 [00:01<00:18,  1.81it/s]
  8%|▊         | 3/36 [00:01<00:17,  1.89it/s]
 11%|█         | 4/36 [00:02<00:16,  1.92it/s]
 14%|█▍        | 5/36 [00:02<00:16,  1.94it/s]
 17%|█▋        | 6/36 [00:03<00:15,  1.95it/s]
 19%|█▉        | 7/36 [00:03<00:14,  1.95it/s]
 22%|██▏       | 8/36 [00:04<00:14,  1.96it/s]
 25%|██▌       | 9/36 [00:04<00:13,  1.96it/s]
 28%|██▊       | 10/36 [00:05<00:13,  1.97it/s]
 31%|███       | 11/36 [00:05<00:12,  1.97it/s]
 33%|███▎      | 12/36 [00:06<00:12,  1.96it/s]
 36%|███▌      | 13/36 [00:06<00:11,  1.96it/s]
 39%|███▉      | 14/36 [00:07<00:11,  1.95it/s]
 42%|████▏     | 15/36 [00:07<00:10,  1.95it/s]
 44%|████▍     | 16/36 [00:08<00:10,  1.95it/s]
 47%|████▋     | 17/36 [00:08<00:09,  1.95it/s]
 50%|█████     | 18/36 [00:09<00:09,  1.95it/s]
 53%|█████▎    | 19/36 [00:09<00:08,  1.95it/s]
 56%|█████▌    | 20/36 [00:10<00:08,  1.94it/s]
 58%|█████▊    | 21/36 [00:10<00:07,  1.94it/s]
 61%|██████    | 22/36 [00:11<00:07,  1.94it/s]
 64%|██████▍   | 23/36 [00:11<00:06,  1.94it/s]
 67%|██████▋   | 24/36 [00:12<00:06,  1.94it/s]
 69%|██████▉   | 25/36 [00:12<00:05,  1.94it/s]
 72%|███████▏  | 26/36 [00:13<00:05,  1.94it/s]
 75%|███████▌  | 27/36 [00:13<00:04,  1.94it/s]
 78%|███████▊  | 28/36 [00:14<00:04,  1.93it/s]
 81%|████████  | 29/36 [00:14<00:03,  1.94it/s]
 83%|████████▎ | 30/36 [00:15<00:03,  1.93it/s]
 86%|████████▌ | 31/36 [00:15<00:02,  1.93it/s]
 89%|████████▉ | 32/36 [00:16<00:02,  1.93it/s]
 92%|█████████▏| 33/36 [00:17<00:01,  1.93it/s]
 94%|█████████▍| 34/36 [00:17<00:01,  1.93it/s]
 97%|█████████▋| 35/36 [00:18<00:00,  1.93it/s]
100%|██████████| 36/36 [00:18<00:00,  1.92it/s]
100%|██████████| 36/36 [00:18<00:00,  1.94it/s]