Prediction

jagilley/controlnet:8ebda4c70b3ea2a2bf86e44595afb562a2cdf85525c620f1671a78113c9f325b

Model

jagilley/controlnet:8ebda4c7

gcynsad625ezjpcpqtnnhyfxrq

Status

Succeeded

Source

Web

Hardware

–

Total duration

14m 37s

Created

about 2 years ago by @jagilley

Input

image
scale: 9
prompt: a cute dog
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
model_type: canny
num_samples: 1
low_threshold: 100
high_threshold: 200
value_threshold: 0.1
image_resolution: 512
detect_resolution: 512
distance_threshold: 0.1

{
  "image": "https://replicate.delivery/pbxt/IMpV0c2SLNPxcnFxJzNrYymUxrzOd9UoQzdLxV1Ew3jAzXRW/doge.png",
  "scale": 9,
  "prompt": "a cute dog",
  "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,
  "model_type": "canny",
  "num_samples": "1",
  "low_threshold": 100,
  "high_threshold": 200,
  "value_threshold": 0.1,
  "image_resolution": "512",
  "detect_resolution": 512,
  "distance_threshold": 0.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "jagilley/controlnet:8ebda4c70b3ea2a2bf86e44595afb562a2cdf85525c620f1671a78113c9f325b",
  {
    input: {
      image: "https://replicate.delivery/pbxt/IMpV0c2SLNPxcnFxJzNrYymUxrzOd9UoQzdLxV1Ew3jAzXRW/doge.png",
      scale: 9,
      prompt: "a cute dog",
      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,
      model_type: "canny",
      num_samples: "1",
      low_threshold: 100,
      high_threshold: 200,
      value_threshold: 0.1,
      image_resolution: "512",
      detect_resolution: 512,
      distance_threshold: 0.1
    }
  }
);

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

output = replicate.run(
    "jagilley/controlnet:8ebda4c70b3ea2a2bf86e44595afb562a2cdf85525c620f1671a78113c9f325b",
    input={
        "image": "https://replicate.delivery/pbxt/IMpV0c2SLNPxcnFxJzNrYymUxrzOd9UoQzdLxV1Ew3jAzXRW/doge.png",
        "scale": 9,
        "prompt": "a cute dog",
        "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,
        "model_type": "canny",
        "num_samples": "1",
        "low_threshold": 100,
        "high_threshold": 200,
        "value_threshold": 0.1,
        "image_resolution": "512",
        "detect_resolution": 512,
        "distance_threshold": 0.1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run jagilley/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": "8ebda4c70b3ea2a2bf86e44595afb562a2cdf85525c620f1671a78113c9f325b",
    "input": {
      "image": "https://replicate.delivery/pbxt/IMpV0c2SLNPxcnFxJzNrYymUxrzOd9UoQzdLxV1Ew3jAzXRW/doge.png",
      "scale": 9,
      "prompt": "a cute dog",
      "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,
      "model_type": "canny",
      "num_samples": "1",
      "low_threshold": 100,
      "high_threshold": 200,
      "value_threshold": 0.1,
      "image_resolution": "512",
      "detect_resolution": 512,
      "distance_threshold": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-02-24T01:58:28.347866Z",
  "created_at": "2023-02-24T01:43:51.210346Z",
  "data_removed": false,
  "error": null,
  "id": "gcynsad625ezjpcpqtnnhyfxrq",
  "input": {
    "image": "https://replicate.delivery/pbxt/IMpV0c2SLNPxcnFxJzNrYymUxrzOd9UoQzdLxV1Ew3jAzXRW/doge.png",
    "scale": 9,
    "prompt": "a cute dog",
    "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,
    "model_type": "canny",
    "num_samples": "1",
    "low_threshold": 100,
    "high_threshold": 200,
    "value_threshold": 0.1,
    "image_resolution": "512",
    "detect_resolution": 512,
    "distance_threshold": 0.1
  },
  "logs": "Loading state dict for model...\nLoaded state_dict from [./models/control_sd15_canny.pth]\nDone!\nGlobal seed set to 599616\nData shape for DDIM sampling is (1, 4, 64, 72), 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<00:37,  2.00s/it]\nDDIM Sampler:  10%|█         | 2/20 [00:02<00:16,  1.07it/s]\nDDIM Sampler:  15%|█▌        | 3/20 [00:02<00:10,  1.69it/s]\nDDIM Sampler:  20%|██        | 4/20 [00:02<00:06,  2.32it/s]\nDDIM Sampler:  25%|██▌       | 5/20 [00:02<00:05,  2.93it/s]\nDDIM Sampler:  30%|███       | 6/20 [00:02<00:04,  3.47it/s]\nDDIM Sampler:  35%|███▌      | 7/20 [00:03<00:03,  3.94it/s]\nDDIM Sampler:  40%|████      | 8/20 [00:03<00:02,  4.33it/s]\nDDIM Sampler:  45%|████▌     | 9/20 [00:03<00:02,  4.63it/s]\nDDIM Sampler:  50%|█████     | 10/20 [00:03<00:02,  4.86it/s]\nDDIM Sampler:  55%|█████▌    | 11/20 [00:03<00:01,  5.03it/s]\nDDIM Sampler:  60%|██████    | 12/20 [00:04<00:01,  5.16it/s]\nDDIM Sampler:  65%|██████▌   | 13/20 [00:04<00:01,  5.25it/s]\nDDIM Sampler:  70%|███████   | 14/20 [00:04<00:01,  5.32it/s]\nDDIM Sampler:  75%|███████▌  | 15/20 [00:04<00:00,  5.36it/s]\nDDIM Sampler:  80%|████████  | 16/20 [00:04<00:00,  5.37it/s]\nDDIM Sampler:  85%|████████▌ | 17/20 [00:04<00:00,  5.41it/s]\nDDIM Sampler:  90%|█████████ | 18/20 [00:05<00:00,  5.43it/s]\nDDIM Sampler:  95%|█████████▌| 19/20 [00:05<00:00,  5.45it/s]\nDDIM Sampler: 100%|██████████| 20/20 [00:05<00:00,  5.47it/s]\nDDIM Sampler: 100%|██████████| 20/20 [00:05<00:00,  3.65it/s]",
  "metrics": {
    "predict_time": 25.202505,
    "total_time": 877.13752
  },
  "output": [
    "https://replicate.delivery/pbxt/94lHvFrTYlKkCVk9vEPqP5URvdGCIIMAQeOLetu412hDvchQA/output_0.png",
    "https://replicate.delivery/pbxt/lpIREB3qXpY7LFfEytmPDac26VgA8hXncVspk3F2Z7qhXuQIA/output_1.png"
  ],
  "started_at": "2023-02-24T01:58:03.145361Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/gcynsad625ezjpcpqtnnhyfxrq",
    "cancel": "https://api.replicate.com/v1/predictions/gcynsad625ezjpcpqtnnhyfxrq/cancel"
  },
  "version": "8ebda4c70b3ea2a2bf86e44595afb562a2cdf85525c620f1671a78113c9f325b"
}

Generated in

25.2 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model