lucataco / sdxl-controlnet

SDXL ControlNet - Canny

Warm

Public
2.6M runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

image

file

Input image for img2img or inpaint mode

prompt

string

Shift + Return to add a new line

aerial view, a futuristic research complex in a bright foggy jungle, hard lightingaerial view, a futuristic research complex in a bright foggy jungle, hard lighting

Input prompt

Default: "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: "low quality, bad quality, sketches"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

condition_scale

number

(minimum: 0, maximum: 1)

controlnet conditioning scale for generalization

Default: 0.5

seed

integer

Random seed. Set to 0 to randomize the seed

Default: 0

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

npx create-replicate --model=lucataco/sdxl-controlnet

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

const output = await replicate.run(
  "lucataco/sdxl-controlnet:06d6fae3b75ab68a28cd2900afa6033166910dd09fd9751047043a5bbb4c184b",
  {
    input: {
      seed: 18457,
      image: "https://replicate.delivery/pbxt/JLbxAaKmGIUprMAPLUBAiNOdys3UeUmtrphUEX3xafrkfzHL/replicate-prediction-gwlekklbmfsw4vub4vi3uhvgpy.png",
      prompt: "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting",
      condition_scale: 0.5,
      negative_prompt: "low quality, bad quality, sketches",
      num_inference_steps: 50
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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 lucataco/sdxl-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/sdxl-controlnet:06d6fae3b75ab68a28cd2900afa6033166910dd09fd9751047043a5bbb4c184b",
    input={
        "seed": 18457,
        "image": "https://replicate.delivery/pbxt/JLbxAaKmGIUprMAPLUBAiNOdys3UeUmtrphUEX3xafrkfzHL/replicate-prediction-gwlekklbmfsw4vub4vi3uhvgpy.png",
        "prompt": "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting",
        "condition_scale": 0.5,
        "negative_prompt": "low quality, bad quality, sketches",
        "num_inference_steps": 50
    }
)
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 lucataco/sdxl-controlnet 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": "06d6fae3b75ab68a28cd2900afa6033166910dd09fd9751047043a5bbb4c184b",
    "input": {
      "seed": 18457,
      "image": "https://replicate.delivery/pbxt/JLbxAaKmGIUprMAPLUBAiNOdys3UeUmtrphUEX3xafrkfzHL/replicate-prediction-gwlekklbmfsw4vub4vi3uhvgpy.png",
      "prompt": "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting",
      "condition_scale": 0.5,
      "negative_prompt": "low quality, bad quality, sketches",
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-12-06T21:06:07.074533Z",
  "created_at": "2024-12-06T21:05:58.031000Z",
  "data_removed": false,
  "error": null,
  "id": "kfqq651b1xrm80ckkq5s81dsdr",
  "input": {
    "seed": 18457,
    "image": "https://replicate.delivery/pbxt/JLbxAaKmGIUprMAPLUBAiNOdys3UeUmtrphUEX3xafrkfzHL/replicate-prediction-gwlekklbmfsw4vub4vi3uhvgpy.png",
    "prompt": "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting",
    "condition_scale": 0.5,
    "negative_prompt": "low quality, bad quality, sketches",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 18457\nOriginal width:1024, height:1024\nAspect Ratio: 1.00\nnew_width:1024, new_height:1024\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:08,  6.10it/s]\n  4%|▍         | 2/50 [00:00<00:08,  5.99it/s]\n  6%|▌         | 3/50 [00:00<00:07,  5.95it/s]\n  8%|▊         | 4/50 [00:00<00:07,  5.91it/s]\n 10%|█         | 5/50 [00:00<00:07,  5.90it/s]\n 12%|█▏        | 6/50 [00:01<00:07,  5.89it/s]\n 14%|█▍        | 7/50 [00:01<00:07,  5.89it/s]\n 16%|█▌        | 8/50 [00:01<00:07,  5.90it/s]\n 18%|█▊        | 9/50 [00:01<00:06,  5.90it/s]\n 20%|██        | 10/50 [00:01<00:06,  5.91it/s]\n 22%|██▏       | 11/50 [00:01<00:06,  5.91it/s]\n 24%|██▍       | 12/50 [00:02<00:06,  5.91it/s]\n 26%|██▌       | 13/50 [00:02<00:06,  5.90it/s]\n 28%|██▊       | 14/50 [00:02<00:06,  5.90it/s]\n 30%|███       | 15/50 [00:02<00:05,  5.90it/s]\n 32%|███▏      | 16/50 [00:02<00:05,  5.90it/s]\n 34%|███▍      | 17/50 [00:02<00:05,  5.89it/s]\n 36%|███▌      | 18/50 [00:03<00:05,  5.89it/s]\n 38%|███▊      | 19/50 [00:03<00:05,  5.90it/s]\n 40%|████      | 20/50 [00:03<00:05,  5.89it/s]\n 42%|████▏     | 21/50 [00:03<00:04,  5.89it/s]\n 44%|████▍     | 22/50 [00:03<00:04,  5.89it/s]\n 46%|████▌     | 23/50 [00:03<00:04,  5.89it/s]\n 48%|████▊     | 24/50 [00:04<00:04,  5.89it/s]\n 50%|█████     | 25/50 [00:04<00:04,  5.89it/s]\n 52%|█████▏    | 26/50 [00:04<00:04,  5.88it/s]\n 54%|█████▍    | 27/50 [00:04<00:03,  5.88it/s]\n 56%|█████▌    | 28/50 [00:04<00:03,  5.88it/s]\n 58%|█████▊    | 29/50 [00:04<00:03,  5.88it/s]\n 60%|██████    | 30/50 [00:05<00:03,  5.88it/s]\n 62%|██████▏   | 31/50 [00:05<00:03,  5.88it/s]\n 64%|██████▍   | 32/50 [00:05<00:03,  5.88it/s]\n 66%|██████▌   | 33/50 [00:05<00:02,  5.88it/s]\n 68%|██████▊   | 34/50 [00:05<00:02,  5.88it/s]\n 70%|███████   | 35/50 [00:05<00:02,  5.88it/s]\n 72%|███████▏  | 36/50 [00:06<00:02,  5.88it/s]\n 74%|███████▍  | 37/50 [00:06<00:02,  5.88it/s]\n 76%|███████▌  | 38/50 [00:06<00:02,  5.88it/s]\n 78%|███████▊  | 39/50 [00:06<00:01,  5.89it/s]\n 80%|████████  | 40/50 [00:06<00:01,  5.89it/s]\n 82%|████████▏ | 41/50 [00:06<00:01,  5.89it/s]\n 84%|████████▍ | 42/50 [00:07<00:01,  5.88it/s]\n 86%|████████▌ | 43/50 [00:07<00:01,  5.88it/s]\n 88%|████████▊ | 44/50 [00:07<00:01,  5.88it/s]\n 90%|█████████ | 45/50 [00:07<00:00,  5.88it/s]\n 92%|█████████▏| 46/50 [00:07<00:00,  5.88it/s]\n 94%|█████████▍| 47/50 [00:07<00:00,  5.89it/s]\n 96%|█████████▌| 48/50 [00:08<00:00,  5.89it/s]\n 98%|█████████▊| 49/50 [00:08<00:00,  5.89it/s]\n100%|██████████| 50/50 [00:08<00:00,  5.88it/s]\n100%|██████████| 50/50 [00:08<00:00,  5.89it/s]",
  "metrics": {
    "predict_time": 9.035931442,
    "total_time": 9.043533
  },
  "output": "https://replicate.delivery/xezq/P3EmIUnmPdqTJ5gdwTKHJfubWLFsdDcy4gFqyo5tQ66fkR4TA/output.png",
  "started_at": "2024-12-06T21:05:58.038601Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-wpd4lg74vdz6xhtofib7mcu6lzu5ugvgleg7ycg3kzn3my2s3uaq",
    "get": "https://api.replicate.com/v1/predictions/kfqq651b1xrm80ckkq5s81dsdr",
    "cancel": "https://api.replicate.com/v1/predictions/kfqq651b1xrm80ckkq5s81dsdr/cancel"
  },
  "version": "06d6fae3b75ab68a28cd2900afa6033166910dd09fd9751047043a5bbb4c184b"
}

Generated in

9.0 seconds

Tweak it ShareReport

Using seed: 18457
Original width:1024, height:1024
Aspect Ratio: 1.00
new_width:1024, new_height:1024
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:08,  6.10it/s]
  4%|▍         | 2/50 [00:00<00:08,  5.99it/s]
  6%|▌         | 3/50 [00:00<00:07,  5.95it/s]
  8%|▊         | 4/50 [00:00<00:07,  5.91it/s]
 10%|█         | 5/50 [00:00<00:07,  5.90it/s]
 12%|█▏        | 6/50 [00:01<00:07,  5.89it/s]
 14%|█▍        | 7/50 [00:01<00:07,  5.89it/s]
 16%|█▌        | 8/50 [00:01<00:07,  5.90it/s]
 18%|█▊        | 9/50 [00:01<00:06,  5.90it/s]
 20%|██        | 10/50 [00:01<00:06,  5.91it/s]
 22%|██▏       | 11/50 [00:01<00:06,  5.91it/s]
 24%|██▍       | 12/50 [00:02<00:06,  5.91it/s]
 26%|██▌       | 13/50 [00:02<00:06,  5.90it/s]
 28%|██▊       | 14/50 [00:02<00:06,  5.90it/s]
 30%|███       | 15/50 [00:02<00:05,  5.90it/s]
 32%|███▏      | 16/50 [00:02<00:05,  5.90it/s]
 34%|███▍      | 17/50 [00:02<00:05,  5.89it/s]
 36%|███▌      | 18/50 [00:03<00:05,  5.89it/s]
 38%|███▊      | 19/50 [00:03<00:05,  5.90it/s]
 40%|████      | 20/50 [00:03<00:05,  5.89it/s]
 42%|████▏     | 21/50 [00:03<00:04,  5.89it/s]
 44%|████▍     | 22/50 [00:03<00:04,  5.89it/s]
 46%|████▌     | 23/50 [00:03<00:04,  5.89it/s]
 48%|████▊     | 24/50 [00:04<00:04,  5.89it/s]
 50%|█████     | 25/50 [00:04<00:04,  5.89it/s]
 52%|█████▏    | 26/50 [00:04<00:04,  5.88it/s]
 54%|█████▍    | 27/50 [00:04<00:03,  5.88it/s]
 56%|█████▌    | 28/50 [00:04<00:03,  5.88it/s]
 58%|█████▊    | 29/50 [00:04<00:03,  5.88it/s]
 60%|██████    | 30/50 [00:05<00:03,  5.88it/s]
 62%|██████▏   | 31/50 [00:05<00:03,  5.88it/s]
 64%|██████▍   | 32/50 [00:05<00:03,  5.88it/s]
 66%|██████▌   | 33/50 [00:05<00:02,  5.88it/s]
 68%|██████▊   | 34/50 [00:05<00:02,  5.88it/s]
 70%|███████   | 35/50 [00:05<00:02,  5.88it/s]
 72%|███████▏  | 36/50 [00:06<00:02,  5.88it/s]
 74%|███████▍  | 37/50 [00:06<00:02,  5.88it/s]
 76%|███████▌  | 38/50 [00:06<00:02,  5.88it/s]
 78%|███████▊  | 39/50 [00:06<00:01,  5.89it/s]
 80%|████████  | 40/50 [00:06<00:01,  5.89it/s]
 82%|████████▏ | 41/50 [00:06<00:01,  5.89it/s]
 84%|████████▍ | 42/50 [00:07<00:01,  5.88it/s]
 86%|████████▌ | 43/50 [00:07<00:01,  5.88it/s]
 88%|████████▊ | 44/50 [00:07<00:01,  5.88it/s]
 90%|█████████ | 45/50 [00:07<00:00,  5.88it/s]
 92%|█████████▏| 46/50 [00:07<00:00,  5.88it/s]
 94%|█████████▍| 47/50 [00:07<00:00,  5.89it/s]
 96%|█████████▌| 48/50 [00:08<00:00,  5.89it/s]
 98%|█████████▊| 49/50 [00:08<00:00,  5.89it/s]
100%|██████████| 50/50 [00:08<00:00,  5.88it/s]
100%|██████████| 50/50 [00:08<00:00,  5.89it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0095 to run on Replicate, or 105 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 10 seconds.

Readme

About

Implementation of diffusers/controlnet-canny-sdxl-1.0

Changelog

10/3/23 - Now handles large input images, resizes to SDXL ratios, keeping the original aspect ratio

Support

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