yuni-eng/controlnet-sdxl – Run with an API on Replicate

yuni-eng / controlnet-sdxl

Create variations of an uploaded image. Please see README for more details

Cold

Public
1.1K runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

image

file

Input image to create in different art medium

prompt

string

Shift + Return to add a new line

Choose art medium to generate in that style. For example: a photo of, a acrylic paint of, an anime drawing of, a caricature of, a cartoon of, a drawing of, a graphitti of, an illustration of, a line art of, an oil painting of, a pencil sketch of

Default: ""

negative_prompt

string

Shift + Return to add a new line

poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainypoorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy

Specify things to not see in the output

Default: "poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy"

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output. > 2 might generate out-of-memory errors.

Default: 1

seed

integer

Random seed. Set to 0 to randomize the seed. If you need tweaks to a generated image, reuse the same seed number from output logs.

Default: 0

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference

Default: 100

guidance_scale

number

A higher guidance scale value generate images closely to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.

Default: 7.5

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

npx create-replicate --model=yuni-eng/controlnet-sdxl

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 yuni-eng/controlnet-sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "yuni-eng/controlnet-sdxl:0bdd2d10541b2210ebd284aaec263a20c855e59c7e1a2d905063ed717501b5ef",
  {
    input: {
      seed: 9465,
      image: "https://replicate.delivery/pbxt/JsFpilrSx3ulOeVYX91Nw3rfofoRnNL7QRF9t2v3US9SOBMw/kungfupanda.png",
      width: 768,
      height: 768,
      prompt: "a realistic photo ",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy",
      num_inference_steps: 100
    }
  }
);

// 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 yuni-eng/controlnet-sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "yuni-eng/controlnet-sdxl:0bdd2d10541b2210ebd284aaec263a20c855e59c7e1a2d905063ed717501b5ef",
    input={
        "seed": 9465,
        "image": "https://replicate.delivery/pbxt/JsFpilrSx3ulOeVYX91Nw3rfofoRnNL7QRF9t2v3US9SOBMw/kungfupanda.png",
        "width": 768,
        "height": 768,
        "prompt": "a realistic photo ",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy",
        "num_inference_steps": 100
    }
)
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 yuni-eng/controlnet-sdxl 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": "0bdd2d10541b2210ebd284aaec263a20c855e59c7e1a2d905063ed717501b5ef",
    "input": {
      "seed": 9465,
      "image": "https://replicate.delivery/pbxt/JsFpilrSx3ulOeVYX91Nw3rfofoRnNL7QRF9t2v3US9SOBMw/kungfupanda.png",
      "width": 768,
      "height": 768,
      "prompt": "a realistic photo ",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy",
      "num_inference_steps": 100
    }
  }' \
  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/yuni-eng/controlnet-sdxl@sha256:0bdd2d10541b2210ebd284aaec263a20c855e59c7e1a2d905063ed717501b5ef \
  -i 'seed=9465' \
  -i 'image="https://replicate.delivery/pbxt/JsFpilrSx3ulOeVYX91Nw3rfofoRnNL7QRF9t2v3US9SOBMw/kungfupanda.png"' \
  -i 'width=768' \
  -i 'height=768' \
  -i 'prompt="a realistic photo "' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy"' \
  -i 'num_inference_steps=100'

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/yuni-eng/controlnet-sdxl@sha256:0bdd2d10541b2210ebd284aaec263a20c855e59c7e1a2d905063ed717501b5ef
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 9465,
      "image": "https://replicate.delivery/pbxt/JsFpilrSx3ulOeVYX91Nw3rfofoRnNL7QRF9t2v3US9SOBMw/kungfupanda.png",
      "width": 768,
      "height": 768,
      "prompt": "a realistic photo ",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy",
      "num_inference_steps": 100
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-11-14T06:33:22.214749Z",
  "created_at": "2023-11-14T06:32:49.835943Z",
  "data_removed": false,
  "error": null,
  "id": "nswepbtbudf2znjbi6gthixv7u",
  "input": {
    "seed": 9465,
    "image": "https://replicate.delivery/pbxt/JsFpilrSx3ulOeVYX91Nw3rfofoRnNL7QRF9t2v3US9SOBMw/kungfupanda.png",
    "width": 768,
    "height": 768,
    "prompt": "a realistic photo ",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, bad anatomy, signature, cut off, low contrast, underexposed, overexposed, bad art, beginner, amateur, distorted face, blurry, draft, grainy",
    "num_inference_steps": 100
  },
  "logs": "Using seed: 9465\n  0%|          | 0/100 [00:00<?, ?it/s]\n  1%|          | 1/100 [00:00<00:29,  3.36it/s]\n  2%|▏         | 2/100 [00:00<00:29,  3.36it/s]\n  3%|▎         | 3/100 [00:00<00:28,  3.36it/s]\n  4%|▍         | 4/100 [00:01<00:28,  3.36it/s]\n  5%|▌         | 5/100 [00:01<00:28,  3.36it/s]\n  6%|▌         | 6/100 [00:01<00:28,  3.36it/s]\n  7%|▋         | 7/100 [00:02<00:27,  3.36it/s]\n  8%|▊         | 8/100 [00:02<00:27,  3.35it/s]\n  9%|▉         | 9/100 [00:02<00:27,  3.35it/s]\n 10%|█         | 10/100 [00:02<00:26,  3.35it/s]\n 11%|█         | 11/100 [00:03<00:26,  3.35it/s]\n 12%|█▏        | 12/100 [00:03<00:26,  3.35it/s]\n 13%|█▎        | 13/100 [00:03<00:25,  3.35it/s]\n 14%|█▍        | 14/100 [00:04<00:25,  3.35it/s]\n 15%|█▌        | 15/100 [00:04<00:25,  3.35it/s]\n 16%|█▌        | 16/100 [00:04<00:25,  3.35it/s]\n 17%|█▋        | 17/100 [00:05<00:24,  3.35it/s]\n 18%|█▊        | 18/100 [00:05<00:24,  3.35it/s]\n 19%|█▉        | 19/100 [00:05<00:24,  3.34it/s]\n 20%|██        | 20/100 [00:05<00:23,  3.34it/s]\n 21%|██        | 21/100 [00:06<00:23,  3.34it/s]\n 22%|██▏       | 22/100 [00:06<00:23,  3.34it/s]\n 23%|██▎       | 23/100 [00:06<00:23,  3.34it/s]\n 24%|██▍       | 24/100 [00:07<00:22,  3.34it/s]\n 25%|██▌       | 25/100 [00:07<00:22,  3.34it/s]\n 26%|██▌       | 26/100 [00:07<00:22,  3.34it/s]\n 27%|██▋       | 27/100 [00:08<00:21,  3.34it/s]\n 28%|██▊       | 28/100 [00:08<00:21,  3.34it/s]\n 29%|██▉       | 29/100 [00:08<00:21,  3.34it/s]\n 30%|███       | 30/100 [00:08<00:20,  3.34it/s]\n 31%|███       | 31/100 [00:09<00:20,  3.34it/s]\n 32%|███▏      | 32/100 [00:09<00:20,  3.34it/s]\n 33%|███▎      | 33/100 [00:09<00:20,  3.34it/s]\n 34%|███▍      | 34/100 [00:10<00:19,  3.34it/s]\n 35%|███▌      | 35/100 [00:10<00:19,  3.33it/s]\n 36%|███▌      | 36/100 [00:10<00:19,  3.33it/s]\n 37%|███▋      | 37/100 [00:11<00:18,  3.33it/s]\n 38%|███▊      | 38/100 [00:11<00:18,  3.33it/s]\n 39%|███▉      | 39/100 [00:11<00:18,  3.33it/s]\n 40%|████      | 40/100 [00:11<00:18,  3.33it/s]\n 41%|████      | 41/100 [00:12<00:17,  3.33it/s]\n 42%|████▏     | 42/100 [00:12<00:17,  3.33it/s]\n 43%|████▎     | 43/100 [00:12<00:17,  3.33it/s]\n 44%|████▍     | 44/100 [00:13<00:16,  3.33it/s]\n 45%|████▌     | 45/100 [00:13<00:16,  3.33it/s]\n 46%|████▌     | 46/100 [00:13<00:16,  3.33it/s]\n 47%|████▋     | 47/100 [00:14<00:15,  3.33it/s]\n 48%|████▊     | 48/100 [00:14<00:15,  3.33it/s]\n 49%|████▉     | 49/100 [00:14<00:15,  3.33it/s]\n 50%|█████     | 50/100 [00:14<00:15,  3.33it/s]\n 51%|█████     | 51/100 [00:15<00:14,  3.33it/s]\n 52%|█████▏    | 52/100 [00:15<00:14,  3.33it/s]\n 53%|█████▎    | 53/100 [00:15<00:14,  3.33it/s]\n 54%|█████▍    | 54/100 [00:16<00:13,  3.33it/s]\n 55%|█████▌    | 55/100 [00:16<00:13,  3.33it/s]\n 56%|█████▌    | 56/100 [00:16<00:13,  3.33it/s]\n 57%|█████▋    | 57/100 [00:17<00:12,  3.33it/s]\n 58%|█████▊    | 58/100 [00:17<00:12,  3.33it/s]\n 59%|█████▉    | 59/100 [00:17<00:12,  3.33it/s]\n 60%|██████    | 60/100 [00:17<00:11,  3.33it/s]\n 61%|██████    | 61/100 [00:18<00:11,  3.33it/s]\n 62%|██████▏   | 62/100 [00:18<00:11,  3.34it/s]\n 63%|██████▎   | 63/100 [00:18<00:11,  3.34it/s]\n 64%|██████▍   | 64/100 [00:19<00:10,  3.33it/s]\n 65%|██████▌   | 65/100 [00:19<00:10,  3.33it/s]\n 66%|██████▌   | 66/100 [00:19<00:10,  3.33it/s]\n 67%|██████▋   | 67/100 [00:20<00:09,  3.33it/s]\n 68%|██████▊   | 68/100 [00:20<00:09,  3.33it/s]\n 69%|██████▉   | 69/100 [00:20<00:09,  3.33it/s]\n 70%|███████   | 70/100 [00:20<00:08,  3.34it/s]\n 71%|███████   | 71/100 [00:21<00:08,  3.33it/s]\n 72%|███████▏  | 72/100 [00:21<00:08,  3.33it/s]\n 73%|███████▎  | 73/100 [00:21<00:08,  3.33it/s]\n 74%|███████▍  | 74/100 [00:22<00:07,  3.33it/s]\n 75%|███████▌  | 75/100 [00:22<00:07,  3.33it/s]\n 76%|███████▌  | 76/100 [00:22<00:07,  3.33it/s]\n 77%|███████▋  | 77/100 [00:23<00:06,  3.33it/s]\n 78%|███████▊  | 78/100 [00:23<00:06,  3.33it/s]\n 79%|███████▉  | 79/100 [00:23<00:06,  3.33it/s]\n 80%|████████  | 80/100 [00:23<00:06,  3.33it/s]\n 81%|████████  | 81/100 [00:24<00:05,  3.33it/s]\n 82%|████████▏ | 82/100 [00:24<00:05,  3.33it/s]\n 83%|████████▎ | 83/100 [00:24<00:05,  3.33it/s]\n 84%|████████▍ | 84/100 [00:25<00:04,  3.33it/s]\n 85%|████████▌ | 85/100 [00:25<00:04,  3.33it/s]\n 86%|████████▌ | 86/100 [00:25<00:04,  3.33it/s]\n 87%|████████▋ | 87/100 [00:26<00:03,  3.33it/s]\n 88%|████████▊ | 88/100 [00:26<00:03,  3.33it/s]\n 89%|████████▉ | 89/100 [00:26<00:03,  3.33it/s]\n 90%|█████████ | 90/100 [00:26<00:03,  3.33it/s]\n 91%|█████████ | 91/100 [00:27<00:02,  3.33it/s]\n 92%|█████████▏| 92/100 [00:27<00:02,  3.33it/s]\n 93%|█████████▎| 93/100 [00:27<00:02,  3.33it/s]\n 94%|█████████▍| 94/100 [00:28<00:01,  3.32it/s]\n 95%|█████████▌| 95/100 [00:28<00:01,  3.32it/s]\n 96%|█████████▌| 96/100 [00:28<00:01,  3.32it/s]\n 97%|█████████▋| 97/100 [00:29<00:00,  3.32it/s]\n 98%|█████████▊| 98/100 [00:29<00:00,  3.32it/s]\n 99%|█████████▉| 99/100 [00:29<00:00,  3.32it/s]\n100%|██████████| 100/100 [00:29<00:00,  3.32it/s]\n100%|██████████| 100/100 [00:29<00:00,  3.33it/s]\nPrediction complete",
  "metrics": {
    "predict_time": 32.393994,
    "total_time": 32.378806
  },
  "output": [
    "https://replicate.delivery/pbxt/I2qbBAinaQ6OKRJ8M3Mdd73S4UxEPKWHFJocunwLTHTsGDeIA/out-0.png"
  ],
  "started_at": "2023-11-14T06:32:49.820755Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nswepbtbudf2znjbi6gthixv7u",
    "cancel": "https://api.replicate.com/v1/predictions/nswepbtbudf2znjbi6gthixv7u/cancel"
  },
  "version": "0bdd2d10541b2210ebd284aaec263a20c855e59c7e1a2d905063ed717501b5ef"
}

Generated in

32.4 seconds

Tweak itReport

Using seed: 9465
  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:00<00:29,  3.36it/s]
  2%|▏         | 2/100 [00:00<00:29,  3.36it/s]
  3%|▎         | 3/100 [00:00<00:28,  3.36it/s]
  4%|▍         | 4/100 [00:01<00:28,  3.36it/s]
  5%|▌         | 5/100 [00:01<00:28,  3.36it/s]
  6%|▌         | 6/100 [00:01<00:28,  3.36it/s]
  7%|▋         | 7/100 [00:02<00:27,  3.36it/s]
  8%|▊         | 8/100 [00:02<00:27,  3.35it/s]
  9%|▉         | 9/100 [00:02<00:27,  3.35it/s]
 10%|█         | 10/100 [00:02<00:26,  3.35it/s]
 11%|█         | 11/100 [00:03<00:26,  3.35it/s]
 12%|█▏        | 12/100 [00:03<00:26,  3.35it/s]
 13%|█▎        | 13/100 [00:03<00:25,  3.35it/s]
 14%|█▍        | 14/100 [00:04<00:25,  3.35it/s]
 15%|█▌        | 15/100 [00:04<00:25,  3.35it/s]
 16%|█▌        | 16/100 [00:04<00:25,  3.35it/s]
 17%|█▋        | 17/100 [00:05<00:24,  3.35it/s]
 18%|█▊        | 18/100 [00:05<00:24,  3.35it/s]
 19%|█▉        | 19/100 [00:05<00:24,  3.34it/s]
 20%|██        | 20/100 [00:05<00:23,  3.34it/s]
 21%|██        | 21/100 [00:06<00:23,  3.34it/s]
 22%|██▏       | 22/100 [00:06<00:23,  3.34it/s]
 23%|██▎       | 23/100 [00:06<00:23,  3.34it/s]
 24%|██▍       | 24/100 [00:07<00:22,  3.34it/s]
 25%|██▌       | 25/100 [00:07<00:22,  3.34it/s]
 26%|██▌       | 26/100 [00:07<00:22,  3.34it/s]
 27%|██▋       | 27/100 [00:08<00:21,  3.34it/s]
 28%|██▊       | 28/100 [00:08<00:21,  3.34it/s]
 29%|██▉       | 29/100 [00:08<00:21,  3.34it/s]
 30%|███       | 30/100 [00:08<00:20,  3.34it/s]
 31%|███       | 31/100 [00:09<00:20,  3.34it/s]
 32%|███▏      | 32/100 [00:09<00:20,  3.34it/s]
 33%|███▎      | 33/100 [00:09<00:20,  3.34it/s]
 34%|███▍      | 34/100 [00:10<00:19,  3.34it/s]
 35%|███▌      | 35/100 [00:10<00:19,  3.33it/s]
 36%|███▌      | 36/100 [00:10<00:19,  3.33it/s]
 37%|███▋      | 37/100 [00:11<00:18,  3.33it/s]
 38%|███▊      | 38/100 [00:11<00:18,  3.33it/s]
 39%|███▉      | 39/100 [00:11<00:18,  3.33it/s]
 40%|████      | 40/100 [00:11<00:18,  3.33it/s]
 41%|████      | 41/100 [00:12<00:17,  3.33it/s]
 42%|████▏     | 42/100 [00:12<00:17,  3.33it/s]
 43%|████▎     | 43/100 [00:12<00:17,  3.33it/s]
 44%|████▍     | 44/100 [00:13<00:16,  3.33it/s]
 45%|████▌     | 45/100 [00:13<00:16,  3.33it/s]
 46%|████▌     | 46/100 [00:13<00:16,  3.33it/s]
 47%|████▋     | 47/100 [00:14<00:15,  3.33it/s]
 48%|████▊     | 48/100 [00:14<00:15,  3.33it/s]
 49%|████▉     | 49/100 [00:14<00:15,  3.33it/s]
 50%|█████     | 50/100 [00:14<00:15,  3.33it/s]
 51%|█████     | 51/100 [00:15<00:14,  3.33it/s]
 52%|█████▏    | 52/100 [00:15<00:14,  3.33it/s]
 53%|█████▎    | 53/100 [00:15<00:14,  3.33it/s]
 54%|█████▍    | 54/100 [00:16<00:13,  3.33it/s]
 55%|█████▌    | 55/100 [00:16<00:13,  3.33it/s]
 56%|█████▌    | 56/100 [00:16<00:13,  3.33it/s]
 57%|█████▋    | 57/100 [00:17<00:12,  3.33it/s]
 58%|█████▊    | 58/100 [00:17<00:12,  3.33it/s]
 59%|█████▉    | 59/100 [00:17<00:12,  3.33it/s]
 60%|██████    | 60/100 [00:17<00:11,  3.33it/s]
 61%|██████    | 61/100 [00:18<00:11,  3.33it/s]
 62%|██████▏   | 62/100 [00:18<00:11,  3.34it/s]
 63%|██████▎   | 63/100 [00:18<00:11,  3.34it/s]
 64%|██████▍   | 64/100 [00:19<00:10,  3.33it/s]
 65%|██████▌   | 65/100 [00:19<00:10,  3.33it/s]
 66%|██████▌   | 66/100 [00:19<00:10,  3.33it/s]
 67%|██████▋   | 67/100 [00:20<00:09,  3.33it/s]
 68%|██████▊   | 68/100 [00:20<00:09,  3.33it/s]
 69%|██████▉   | 69/100 [00:20<00:09,  3.33it/s]
 70%|███████   | 70/100 [00:20<00:08,  3.34it/s]
 71%|███████   | 71/100 [00:21<00:08,  3.33it/s]
 72%|███████▏  | 72/100 [00:21<00:08,  3.33it/s]
 73%|███████▎  | 73/100 [00:21<00:08,  3.33it/s]
 74%|███████▍  | 74/100 [00:22<00:07,  3.33it/s]
 75%|███████▌  | 75/100 [00:22<00:07,  3.33it/s]
 76%|███████▌  | 76/100 [00:22<00:07,  3.33it/s]
 77%|███████▋  | 77/100 [00:23<00:06,  3.33it/s]
 78%|███████▊  | 78/100 [00:23<00:06,  3.33it/s]
 79%|███████▉  | 79/100 [00:23<00:06,  3.33it/s]
 80%|████████  | 80/100 [00:23<00:06,  3.33it/s]
 81%|████████  | 81/100 [00:24<00:05,  3.33it/s]
 82%|████████▏ | 82/100 [00:24<00:05,  3.33it/s]
 83%|████████▎ | 83/100 [00:24<00:05,  3.33it/s]
 84%|████████▍ | 84/100 [00:25<00:04,  3.33it/s]
 85%|████████▌ | 85/100 [00:25<00:04,  3.33it/s]
 86%|████████▌ | 86/100 [00:25<00:04,  3.33it/s]
 87%|████████▋ | 87/100 [00:26<00:03,  3.33it/s]
 88%|████████▊ | 88/100 [00:26<00:03,  3.33it/s]
 89%|████████▉ | 89/100 [00:26<00:03,  3.33it/s]
 90%|█████████ | 90/100 [00:26<00:03,  3.33it/s]
 91%|█████████ | 91/100 [00:27<00:02,  3.33it/s]
 92%|█████████▏| 92/100 [00:27<00:02,  3.33it/s]
 93%|█████████▎| 93/100 [00:27<00:02,  3.33it/s]
 94%|█████████▍| 94/100 [00:28<00:01,  3.32it/s]
 95%|█████████▌| 95/100 [00:28<00:01,  3.32it/s]
 96%|█████████▌| 96/100 [00:28<00:01,  3.32it/s]
 97%|█████████▋| 97/100 [00:29<00:00,  3.32it/s]
 98%|█████████▊| 98/100 [00:29<00:00,  3.32it/s]
 99%|█████████▉| 99/100 [00:29<00:00,  3.32it/s]
100%|██████████| 100/100 [00:29<00:00,  3.32it/s]
100%|██████████| 100/100 [00:29<00:00,  3.33it/s]
Prediction complete

Examples

View more examples

Run time and cost

This model costs approximately $0.013 to run on Replicate, or 76 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 14 seconds.

Readme

Create variations of an uploaded image. The model uses ControleNet Canny + SDXL.

Usage Instructions:

1) Start with an image on a black-and-white background. If you do not have a base image, you can use our coloring page generator here: https://replicate.com/yuni-eng/coloring. Use this model to generate your desired black and white colored image

2) Upload the base image in this model

3) prompt for art medium variations or generate images in different color palettes.

References:

1) Adopted from: https://github.com/lucataco/cog-sdxl-controlnet

2) Some inspirations on how to generate creative outputs: https://karimjedda.com/beautiful-data-visualizations-powered-by-generative-ai/