jagilley

controlnet-canny

Cold

Modify images using canny edge detection

Public

830.5K runs

Run with an API

Playground API Examples README Versions

Prediction

jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487

Model

jagilley/controlnet-canny:02a11802

uhhdpy73z5dbvdyavio2faeaye

Status

Succeeded

Source

Web

Hardware

–

Total duration

32.3s

Created

over 2 years ago by @jagilley

Input

image
scale: 9
prompt: a metallic cyborg bird
a_prompt: best quality, extremely detailed
n_prompt: longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
ddim_steps: 20
num_samples: 1
low_threshold: 100
high_threshold: 200
image_resolution: 512

{
  "image": "https://replicate.delivery/pbxt/IMPLYODUwdmHTsnLKi5YiFccIAK6g9l5KK1FNyCtpGS1g0UN/1200.jpeg",
  "scale": 9,
  "prompt": "a metallic cyborg bird",
  "a_prompt": "best quality, extremely detailed",
  "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "ddim_steps": 20,
  "num_samples": "1",
  "low_threshold": 100,
  "high_threshold": 200,
  "image_resolution": "512"
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487",
  {
    input: {
      image: "https://replicate.delivery/pbxt/IMPLYODUwdmHTsnLKi5YiFccIAK6g9l5KK1FNyCtpGS1g0UN/1200.jpeg",
      scale: 9,
      prompt: "a metallic cyborg bird",
      a_prompt: "best quality, extremely detailed",
      n_prompt: "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      ddim_steps: 20,
      num_samples: "1",
      low_threshold: 100,
      high_threshold: 200,
      image_resolution: "512"
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487",
    input={
        "image": "https://replicate.delivery/pbxt/IMPLYODUwdmHTsnLKi5YiFccIAK6g9l5KK1FNyCtpGS1g0UN/1200.jpeg",
        "scale": 9,
        "prompt": "a metallic cyborg bird",
        "a_prompt": "best quality, extremely detailed",
        "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "ddim_steps": 20,
        "num_samples": "1",
        "low_threshold": 100,
        "high_threshold": 200,
        "image_resolution": "512"
    }
)

# 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.

Run jagilley/controlnet-canny 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": "jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487",
    "input": {
      "image": "https://replicate.delivery/pbxt/IMPLYODUwdmHTsnLKi5YiFccIAK6g9l5KK1FNyCtpGS1g0UN/1200.jpeg",
      "scale": 9,
      "prompt": "a metallic cyborg bird",
      "a_prompt": "best quality, extremely detailed",
      "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "ddim_steps": 20,
      "num_samples": "1",
      "low_threshold": 100,
      "high_threshold": 200,
      "image_resolution": "512"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-02-22T21:13:09.461984Z",
  "created_at": "2023-02-22T21:12:37.147510Z",
  "data_removed": false,
  "error": null,
  "id": "uhhdpy73z5dbvdyavio2faeaye",
  "input": {
    "image": "https://replicate.delivery/pbxt/IMPLYODUwdmHTsnLKi5YiFccIAK6g9l5KK1FNyCtpGS1g0UN/1200.jpeg",
    "scale": 9,
    "prompt": "a metallic cyborg bird",
    "a_prompt": "best quality, extremely detailed",
    "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "ddim_steps": 20,
    "num_samples": "1",
    "low_threshold": 100,
    "high_threshold": 200,
    "image_resolution": "512"
  },
  "logs": "Global seed set to 382784\nData shape for DDIM sampling is (1, 4, 64, 104), eta 0.0\nRunning DDIM Sampling with 20 timesteps\nDDIM Sampler:   0%|          | 0/20 [00:00<?, ?it/s]\nDDIM Sampler:   5%|▌         | 1/20 [00:01<00:28,  1.51s/it]\nDDIM Sampler:  10%|█         | 2/20 [00:02<00:26,  1.48s/it]\nDDIM Sampler:  15%|█▌        | 3/20 [00:04<00:25,  1.48s/it]\nDDIM Sampler:  20%|██        | 4/20 [00:05<00:23,  1.47s/it]\nDDIM Sampler:  25%|██▌       | 5/20 [00:07<00:22,  1.47s/it]\nDDIM Sampler:  30%|███       | 6/20 [00:08<00:20,  1.47s/it]\nDDIM Sampler:  35%|███▌      | 7/20 [00:10<00:19,  1.48s/it]\nDDIM Sampler:  40%|████      | 8/20 [00:11<00:17,  1.48s/it]\nDDIM Sampler:  45%|████▌     | 9/20 [00:13<00:16,  1.48s/it]\nDDIM Sampler:  50%|█████     | 10/20 [00:14<00:14,  1.48s/it]\nDDIM Sampler:  55%|█████▌    | 11/20 [00:16<00:13,  1.49s/it]\nDDIM Sampler:  60%|██████    | 12/20 [00:17<00:11,  1.49s/it]\nDDIM Sampler:  65%|██████▌   | 13/20 [00:19<00:10,  1.49s/it]\nDDIM Sampler:  70%|███████   | 14/20 [00:20<00:08,  1.49s/it]\nDDIM Sampler:  75%|███████▌  | 15/20 [00:22<00:07,  1.50s/it]\nDDIM Sampler:  80%|████████  | 16/20 [00:23<00:05,  1.50s/it]\nDDIM Sampler:  85%|████████▌ | 17/20 [00:25<00:04,  1.50s/it]\nDDIM Sampler:  90%|█████████ | 18/20 [00:26<00:03,  1.50s/it]\nDDIM Sampler:  95%|█████████▌| 19/20 [00:28<00:01,  1.50s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:29<00:00,  1.51s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:29<00:00,  1.49s/it]",
  "metrics": {
    "predict_time": 32.249509,
    "total_time": 32.314474
  },
  "output": [
    "https://replicate.delivery/pbxt/lyWELufWUrTCe0PSTZye7IOe6lIYQpWdhIJH1Xfe8urLZ3QIE/output_0.png",
    "https://replicate.delivery/pbxt/Fp3G1dILv6YRNxTLm6VfVc9mzRHktHlvae9U6TGKGSAkdDhQA/output_1.png"
  ],
  "started_at": "2023-02-22T21:12:37.212475Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/uhhdpy73z5dbvdyavio2faeaye",
    "cancel": "https://api.replicate.com/v1/predictions/uhhdpy73z5dbvdyavio2faeaye/cancel"
  },
  "version": "02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487"
}

Generated in

32.3 seconds

Tweak it Iterate in playground ShareReport

Prediction

jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487

Model

jagilley/controlnet-canny:02a11802

jhvyxcao4jedhbc5irzecdd6wy

Status

Succeeded

Source

Web

Hardware

–

Total duration

32.6s

Created

over 2 years ago

Input

image
scale: 9
prompt: bird
a_prompt: best quality, extremely detailed
n_prompt: longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
ddim_steps: 20
num_samples: 1
low_threshold: 100
high_threshold: 200
image_resolution: 512

{
  "image": "https://replicate.delivery/pbxt/IMjSG2JLxIRfTr5dPhKGPeGrMFnn9ilWQ4tD0dwxQOHtYlUd/bird.png",
  "scale": 9,
  "prompt": "bird",
  "a_prompt": "best quality, extremely detailed",
  "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "ddim_steps": 20,
  "num_samples": "1",
  "low_threshold": 100,
  "high_threshold": 200,
  "image_resolution": "512"
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487",
  {
    input: {
      image: "https://replicate.delivery/pbxt/IMjSG2JLxIRfTr5dPhKGPeGrMFnn9ilWQ4tD0dwxQOHtYlUd/bird.png",
      scale: 9,
      prompt: "bird",
      a_prompt: "best quality, extremely detailed",
      n_prompt: "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      ddim_steps: 20,
      num_samples: "1",
      low_threshold: 100,
      high_threshold: 200,
      image_resolution: "512"
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487",
    input={
        "image": "https://replicate.delivery/pbxt/IMjSG2JLxIRfTr5dPhKGPeGrMFnn9ilWQ4tD0dwxQOHtYlUd/bird.png",
        "scale": 9,
        "prompt": "bird",
        "a_prompt": "best quality, extremely detailed",
        "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
        "ddim_steps": 20,
        "num_samples": "1",
        "low_threshold": 100,
        "high_threshold": 200,
        "image_resolution": "512"
    }
)

# 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.

Run jagilley/controlnet-canny 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": "jagilley/controlnet-canny:02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487",
    "input": {
      "image": "https://replicate.delivery/pbxt/IMjSG2JLxIRfTr5dPhKGPeGrMFnn9ilWQ4tD0dwxQOHtYlUd/bird.png",
      "scale": 9,
      "prompt": "bird",
      "a_prompt": "best quality, extremely detailed",
      "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
      "ddim_steps": 20,
      "num_samples": "1",
      "low_threshold": 100,
      "high_threshold": 200,
      "image_resolution": "512"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-02-23T19:08:53.887924Z",
  "created_at": "2023-02-23T19:08:21.252513Z",
  "data_removed": false,
  "error": null,
  "id": "jhvyxcao4jedhbc5irzecdd6wy",
  "input": {
    "image": "https://replicate.delivery/pbxt/IMjSG2JLxIRfTr5dPhKGPeGrMFnn9ilWQ4tD0dwxQOHtYlUd/bird.png",
    "scale": 9,
    "prompt": "bird",
    "a_prompt": "best quality, extremely detailed",
    "n_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
    "ddim_steps": 20,
    "num_samples": "1",
    "low_threshold": 100,
    "high_threshold": 200,
    "image_resolution": "512"
  },
  "logs": "Global seed set to 318892\nData shape for DDIM sampling is (1, 4, 96, 64), eta 0.0\nRunning DDIM Sampling with 20 timesteps\nDDIM Sampler:   0%|          | 0/20 [00:00<?, ?it/s]\nDDIM Sampler:   5%|▌         | 1/20 [00:01<00:27,  1.46s/it]\nDDIM Sampler:  10%|█         | 2/20 [00:02<00:26,  1.45s/it]\nDDIM Sampler:  15%|█▌        | 3/20 [00:04<00:24,  1.45s/it]\nDDIM Sampler:  20%|██        | 4/20 [00:05<00:23,  1.45s/it]\nDDIM Sampler:  25%|██▌       | 5/20 [00:07<00:21,  1.45s/it]\nDDIM Sampler:  30%|███       | 6/20 [00:08<00:20,  1.45s/it]\nDDIM Sampler:  35%|███▌      | 7/20 [00:10<00:18,  1.46s/it]\nDDIM Sampler:  40%|████      | 8/20 [00:11<00:17,  1.47s/it]\nDDIM Sampler:  45%|████▌     | 9/20 [00:13<00:16,  1.47s/it]\nDDIM Sampler:  50%|█████     | 10/20 [00:14<00:14,  1.48s/it]\nDDIM Sampler:  55%|█████▌    | 11/20 [00:16<00:13,  1.49s/it]\nDDIM Sampler:  60%|██████    | 12/20 [00:17<00:11,  1.49s/it]\nDDIM Sampler:  65%|██████▌   | 13/20 [00:19<00:10,  1.50s/it]\nDDIM Sampler:  70%|███████   | 14/20 [00:20<00:09,  1.50s/it]\nDDIM Sampler:  75%|███████▌  | 15/20 [00:22<00:07,  1.51s/it]\nDDIM Sampler:  80%|████████  | 16/20 [00:23<00:06,  1.52s/it]\nDDIM Sampler:  85%|████████▌ | 17/20 [00:25<00:04,  1.53s/it]\nDDIM Sampler:  90%|█████████ | 18/20 [00:26<00:03,  1.53s/it]\nDDIM Sampler:  95%|█████████▌| 19/20 [00:28<00:01,  1.53s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:29<00:00,  1.54s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:29<00:00,  1.50s/it]",
  "metrics": {
    "predict_time": 32.556173,
    "total_time": 32.635411
  },
  "output": [
    "https://replicate.delivery/pbxt/OeiJh1REUflXZEq8sGxXYdQ64wosoglQXTPf7rnQAwhJeaFCB/output_0.png",
    "https://replicate.delivery/pbxt/P7bf4e9I8InIlkBeawkZ96N3aeFeJpcXaIHf1bjNROtcxrVIE/output_1.png"
  ],
  "started_at": "2023-02-23T19:08:21.331751Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jhvyxcao4jedhbc5irzecdd6wy",
    "cancel": "https://api.replicate.com/v1/predictions/jhvyxcao4jedhbc5irzecdd6wy/cancel"
  },
  "version": "02a11802691b4733143bb9f343758671e4c98ae36f06de0a01a1ee79d68f8487"
}

Generated in

32.6 seconds

Tweak it Iterate in playground ShareReport

Want to make some of these yourself?

Run this model

Prediction

Input

Output

Prediction

Input

Output

Logs (uhhdpy73z5dbvdyavio2faeaye)

Logs (jhvyxcao4jedhbc5irzecdd6wy)