jagilley / controlnet-hed

scale: 9
prompt: oil painting of handsome older gentleman, masterpiece
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
input_image
num_samples: 1
image_resolution: 512
detect_resolution: 512

{
  "scale": 9,
  "prompt": "oil painting of handsome older gentleman, masterpiece",
  "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,
  "input_image": "https://replicate.delivery/pbxt/IJBChpRrky1GqjRBPmtMjtYciqUNgefsCk9fHAJ8QrN9vYBY/old.png",
  "num_samples": "1",
  "image_resolution": "512",
  "detect_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-hed using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jagilley/controlnet-hed:cde353130c86f37d0af4060cd757ab3009cac68eb58df216768f907f0d0a0653",
  {
    input: {
      scale: 9,
      prompt: "oil painting of handsome older gentleman, masterpiece",
      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,
      input_image: "https://replicate.delivery/pbxt/IJBChpRrky1GqjRBPmtMjtYciqUNgefsCk9fHAJ8QrN9vYBY/old.png",
      num_samples: "1",
      image_resolution: "512",
      detect_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-hed using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jagilley/controlnet-hed:cde353130c86f37d0af4060cd757ab3009cac68eb58df216768f907f0d0a0653",
    input={
        "scale": 9,
        "prompt": "oil painting of handsome older gentleman, masterpiece",
        "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,
        "input_image": "https://replicate.delivery/pbxt/IJBChpRrky1GqjRBPmtMjtYciqUNgefsCk9fHAJ8QrN9vYBY/old.png",
        "num_samples": "1",
        "image_resolution": "512",
        "detect_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-hed 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-hed:cde353130c86f37d0af4060cd757ab3009cac68eb58df216768f907f0d0a0653",
    "input": {
      "scale": 9,
      "prompt": "oil painting of handsome older gentleman, masterpiece",
      "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,
      "input_image": "https://replicate.delivery/pbxt/IJBChpRrky1GqjRBPmtMjtYciqUNgefsCk9fHAJ8QrN9vYBY/old.png",
      "num_samples": "1",
      "image_resolution": "512",
      "detect_resolution": 512
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-02-13T18:57:09.782538Z",
  "created_at": "2023-02-13T18:56:42.968908Z",
  "data_removed": false,
  "error": null,
  "id": "u7wqln2w7fhddian4reydccsj4",
  "input": {
    "scale": 9,
    "prompt": "oil painting of handsome older gentleman, masterpiece",
    "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,
    "input_image": "https://replicate.delivery/pbxt/IJBChpRrky1GqjRBPmtMjtYciqUNgefsCk9fHAJ8QrN9vYBY/old.png",
    "num_samples": "1",
    "image_resolution": "512",
    "detect_resolution": 512
  },
  "logs": "Global seed set to 134830\nData shape for DDIM sampling is (1, 4, 88, 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<00:23,  1.25s/it]\nDDIM Sampler:  10%|█         | 2/20 [00:02<00:22,  1.23s/it]\nDDIM Sampler:  15%|█▌        | 3/20 [00:03<00:20,  1.22s/it]\nDDIM Sampler:  20%|██        | 4/20 [00:04<00:19,  1.22s/it]\nDDIM Sampler:  25%|██▌       | 5/20 [00:06<00:18,  1.22s/it]\nDDIM Sampler:  30%|███       | 6/20 [00:07<00:17,  1.22s/it]\nDDIM Sampler:  35%|███▌      | 7/20 [00:08<00:15,  1.22s/it]\nDDIM Sampler:  40%|████      | 8/20 [00:09<00:14,  1.22s/it]\nDDIM Sampler:  45%|████▌     | 9/20 [00:10<00:13,  1.22s/it]\nDDIM Sampler:  50%|█████     | 10/20 [00:12<00:12,  1.22s/it]\nDDIM Sampler:  55%|█████▌    | 11/20 [00:13<00:11,  1.23s/it]\nDDIM Sampler:  60%|██████    | 12/20 [00:14<00:09,  1.23s/it]\nDDIM Sampler:  65%|██████▌   | 13/20 [00:15<00:08,  1.23s/it]\nDDIM Sampler:  70%|███████   | 14/20 [00:17<00:07,  1.23s/it]\nDDIM Sampler:  75%|███████▌  | 15/20 [00:18<00:06,  1.23s/it]\nDDIM Sampler:  80%|████████  | 16/20 [00:19<00:04,  1.23s/it]\nDDIM Sampler:  85%|████████▌ | 17/20 [00:20<00:03,  1.23s/it]\nDDIM Sampler:  90%|█████████ | 18/20 [00:22<00:02,  1.23s/it]\nDDIM Sampler:  95%|█████████▌| 19/20 [00:23<00:01,  1.24s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:24<00:00,  1.24s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:24<00:00,  1.23s/it]",
  "metrics": {
    "predict_time": 26.74832,
    "total_time": 26.81363
  },
  "output": [
    "https://replicate.delivery/pbxt/SewYttnDSwxOHKNbiNAeze2iQluVYldRcer6PrKkTLuSgO4BB/output_0.png",
    "https://replicate.delivery/pbxt/XHe8yQpnaty6FaeFFTYFXUcE3wrnrofAzFyM473DR6DLQH8gA/output_1.png"
  ],
  "started_at": "2023-02-13T18:56:43.034218Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/u7wqln2w7fhddian4reydccsj4",
    "cancel": "https://api.replicate.com/v1/predictions/u7wqln2w7fhddian4reydccsj4/cancel"
  },
  "version": "cde353130c86f37d0af4060cd757ab3009cac68eb58df216768f907f0d0a0653"
}

Generated in

26.8 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model