jagilley / controlnet-scribble

Generate detailed images from scribbled drawings

Cold

Public
38.2M runs
A100 (80GB)
GitHub
License

Run with an API

Playground API Examples README Versions

Prediction

jagilley/controlnet-scribble:435061a1

Model

jagilley/controlnet-scribble:435061a1

yz7xq2yxgzgp3d3d7pgxkmcad4

Status

Succeeded

Source

Web

Hardware

–

Total duration

2m 48s

Created

about 2 years ago by @jagilley

Input

image
scale: 9
prompt: a photo of a brightly colored turtle
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
image_resolution: 512

{
  "image": "https://replicate.delivery/pbxt/IJE6zP4jtdwxe7SffC7te9DPHWHW99dMXED5AWamlBNcvxn0/user_1.png",
  "scale": 9,
  "prompt": "a photo of a brightly colored turtle",
  "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",
  "image_resolution": "512"
}

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

const output = await replicate.run(
  "jagilley/controlnet-scribble:435061a1b5a4c1e26740464bf786efdfa9cb3a3ac488595a2de23e143fdb0117",
  {
    input: {
      image: "https://replicate.delivery/pbxt/IJE6zP4jtdwxe7SffC7te9DPHWHW99dMXED5AWamlBNcvxn0/user_1.png",
      scale: 9,
      prompt: "a photo of a brightly colored turtle",
      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",
      image_resolution: "512"
    }
  }
);
console.log(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 jagilley/controlnet-scribble using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jagilley/controlnet-scribble:435061a1b5a4c1e26740464bf786efdfa9cb3a3ac488595a2de23e143fdb0117",
    input={
        "image": "https://replicate.delivery/pbxt/IJE6zP4jtdwxe7SffC7te9DPHWHW99dMXED5AWamlBNcvxn0/user_1.png",
        "scale": 9,
        "prompt": "a photo of a brightly colored turtle",
        "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",
        "image_resolution": "512"
    }
)
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 jagilley/controlnet-scribble 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": "435061a1b5a4c1e26740464bf786efdfa9cb3a3ac488595a2de23e143fdb0117",
    "input": {
      "image": "https://replicate.delivery/pbxt/IJE6zP4jtdwxe7SffC7te9DPHWHW99dMXED5AWamlBNcvxn0/user_1.png",
      "scale": 9,
      "prompt": "a photo of a brightly colored turtle",
      "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",
      "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": "2023-02-13T22:09:46.520767Z",
  "created_at": "2023-02-13T22:06:58.326782Z",
  "data_removed": false,
  "error": null,
  "id": "yz7xq2yxgzgp3d3d7pgxkmcad4",
  "input": {
    "image": "https://replicate.delivery/pbxt/IJE6zP4jtdwxe7SffC7te9DPHWHW99dMXED5AWamlBNcvxn0/user_1.png",
    "scale": 9,
    "prompt": "a photo of a brightly colored turtle",
    "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",
    "image_resolution": "512"
  },
  "logs": "Global seed set to 422584\nData shape for DDIM sampling is (1, 4, 64, 64), eta 0.0\nRunning DDIM Sampling with 20 timesteps\nDDIM Sampler:   0%|          | 0/20 [00:00<?, ?it/s]\nDDIM Sampler:   5%|▌         | 1/20 [00:02<00:52,  2.77s/it]\nDDIM Sampler:  10%|█         | 2/20 [00:03<00:28,  1.57s/it]\nDDIM Sampler:  15%|█▌        | 3/20 [00:04<00:20,  1.18s/it]\nDDIM Sampler:  20%|██        | 4/20 [00:04<00:15,  1.00it/s]\nDDIM Sampler:  25%|██▌       | 5/20 [00:05<00:13,  1.11it/s]\nDDIM Sampler:  30%|███       | 6/20 [00:06<00:11,  1.19it/s]\nDDIM Sampler:  35%|███▌      | 7/20 [00:07<00:10,  1.24it/s]\nDDIM Sampler:  40%|████      | 8/20 [00:07<00:09,  1.29it/s]\nDDIM Sampler:  45%|████▌     | 9/20 [00:08<00:08,  1.32it/s]\nDDIM Sampler:  50%|█████     | 10/20 [00:09<00:07,  1.34it/s]\nDDIM Sampler:  55%|█████▌    | 11/20 [00:10<00:06,  1.35it/s]\nDDIM Sampler:  60%|██████    | 12/20 [00:10<00:05,  1.36it/s]\nDDIM Sampler:  65%|██████▌   | 13/20 [00:11<00:05,  1.36it/s]\nDDIM Sampler:  70%|███████   | 14/20 [00:12<00:04,  1.36it/s]\nDDIM Sampler:  75%|███████▌  | 15/20 [00:12<00:03,  1.37it/s]\nDDIM Sampler:  80%|████████  | 16/20 [00:13<00:02,  1.37it/s]\nDDIM Sampler:  85%|████████▌ | 17/20 [00:14<00:02,  1.37it/s]\nDDIM Sampler:  90%|█████████ | 18/20 [00:15<00:01,  1.37it/s]\nDDIM Sampler:  95%|█████████▌| 19/20 [00:15<00:00,  1.37it/s]\nDDIM Sampler: 100%|██████████| 20/20 [00:16<00:00,  1.37it/s]\nDDIM Sampler: 100%|██████████| 20/20 [00:16<00:00,  1.21it/s]",
  "metrics": {
    "predict_time": 20.510561,
    "total_time": 168.193985
  },
  "output": [
    "https://replicate.delivery/pbxt/aNV6gZDqqiJiPddvDfV9jkATVcE6ckTl7hmweE7Z8DbpcGegA/output_0.png",
    "https://replicate.delivery/pbxt/3dbPD8n9bqbDLBZ6PwLbB23NFnmSLV3vhe6XLWpGEcvUODPIA/output_1.png"
  ],
  "started_at": "2023-02-13T22:09:26.010206Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/yz7xq2yxgzgp3d3d7pgxkmcad4",
    "cancel": "https://api.replicate.com/v1/predictions/yz7xq2yxgzgp3d3d7pgxkmcad4/cancel"
  },
  "version": "435061a1b5a4c1e26740464bf786efdfa9cb3a3ac488595a2de23e143fdb0117"
}

Generated in

20.5 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model