mohamad1998630/controlnet | Run with an API on Replicate

mohamad1998630 / controlnet

Cold

Public
84 runs
T4

Run with an API

Playground API Examples README Versions

Input

input_image_path

*file

Image to process

prompt

*string

Shift + Return to add a new line

prompt

a_prompt

string

Shift + Return to add a new line

added prompt

Default: "best quality, extremely detailed"

n_prompt

string

Shift + Return to add a new line

longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low qualitylongbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality

negative prompt

Default: "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality"

num_samples

integer

num_samples

Default: 1

image_resolution

integer

Image resolution

Default: 512

detect_resolution

integer

detect_resolution

Default: 512

ddim_steps

integer

ddim steps

Default: 20

guess_mode

boolean

guess mode

Default: false

strength

number

strength

Default: 1

scale

number

scale

Default: 9

seed

number

seed

Default: 3.5

eta

number

eta

Default: 0

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

npx create-replicate --model=mohamad1998630/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 mohamad1998630/controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "mohamad1998630/controlnet:905298f5d96cb992b6133132b151d4029122599cfd57d7ceb4c4e447b2390855",
  {
    input: {
      eta: 0,
      seed: 3.5,
      scale: 9,
      prompt: "Put furniture",
      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",
      strength: 1,
      ddim_steps: 20,
      guess_mode: false,
      num_samples: 1,
      image_resolution: 512,
      input_image_path: "https://replicate.delivery/pbxt/KSbEAl9T5UeDInRBNViM9xIpyYR2XNcRVqXC8gKJeWSfNe1y/point3d-commercial-imaging-ltd-nQlVMCHPysY-unsplash.jpg",
      detect_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 mohamad1998630/controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "mohamad1998630/controlnet:905298f5d96cb992b6133132b151d4029122599cfd57d7ceb4c4e447b2390855",
    input={
        "eta": 0,
        "seed": 3.5,
        "scale": 9,
        "prompt": "Put furniture",
        "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",
        "strength": 1,
        "ddim_steps": 20,
        "guess_mode": False,
        "num_samples": 1,
        "image_resolution": 512,
        "input_image_path": "https://replicate.delivery/pbxt/KSbEAl9T5UeDInRBNViM9xIpyYR2XNcRVqXC8gKJeWSfNe1y/point3d-commercial-imaging-ltd-nQlVMCHPysY-unsplash.jpg",
        "detect_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 mohamad1998630/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": "mohamad1998630/controlnet:905298f5d96cb992b6133132b151d4029122599cfd57d7ceb4c4e447b2390855",
    "input": {
      "eta": 0,
      "seed": 3.5,
      "scale": 9,
      "prompt": "Put furniture",
      "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",
      "strength": 1,
      "ddim_steps": 20,
      "guess_mode": false,
      "num_samples": 1,
      "image_resolution": 512,
      "input_image_path": "https://replicate.delivery/pbxt/KSbEAl9T5UeDInRBNViM9xIpyYR2XNcRVqXC8gKJeWSfNe1y/point3d-commercial-imaging-ltd-nQlVMCHPysY-unsplash.jpg",
      "detect_resolution": 512
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

[ "https://storage.googleapis.com/replicate-files/PWpGmEAwYp50OddPlMXlUXKnekgZE78oqSucrfA7nFRqY8ZSA/out-0.png" ]

{
  "completed_at": "2024-02-24T16:07:06.767767Z",
  "created_at": "2024-02-24T15:58:54.438733Z",
  "data_removed": false,
  "error": null,
  "id": "elsb22zbvrv5nxstfzbzfrstpy",
  "input": {
    "eta": 0,
    "seed": 3.5,
    "scale": 9,
    "prompt": "Put furniture",
    "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",
    "strength": 1,
    "ddim_steps": 20,
    "guess_mode": false,
    "num_samples": 1,
    "image_resolution": 512,
    "input_image_path": "https://replicate.delivery/pbxt/KSbEAl9T5UeDInRBNViM9xIpyYR2XNcRVqXC8gKJeWSfNe1y/point3d-commercial-imaging-ltd-nQlVMCHPysY-unsplash.jpg",
    "detect_resolution": 512
  },
  "logs": "Image shape: (4480, 6720, 3)\n/src/annotator/uniformer/mmseg/models/segmentors/base.py:271: UserWarning: show==False and out_file is not specified, only result image will be returned\nwarnings.warn('show==False and out_file is not specified, only '\nGlobal seed set to 3\nData shape for DDIM sampling is (1, 4, 64, 96), 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<00:30,  1.59s/it]\nDDIM Sampler:  10%|█         | 2/20 [00:02<00:26,  1.47s/it]\nDDIM Sampler:  15%|█▌        | 3/20 [00:04<00:24,  1.43s/it]\nDDIM Sampler:  20%|██        | 4/20 [00:05<00:22,  1.42s/it]\nDDIM Sampler:  25%|██▌       | 5/20 [00:07<00:21,  1.41s/it]\nDDIM Sampler:  30%|███       | 6/20 [00:08<00:19,  1.41s/it]\nDDIM Sampler:  35%|███▌      | 7/20 [00:09<00:18,  1.41s/it]\nDDIM Sampler:  40%|████      | 8/20 [00:11<00:16,  1.41s/it]\nDDIM Sampler:  45%|████▌     | 9/20 [00:12<00:15,  1.42s/it]\nDDIM Sampler:  50%|█████     | 10/20 [00:14<00:14,  1.42s/it]\nDDIM Sampler:  55%|█████▌    | 11/20 [00:15<00:12,  1.42s/it]\nDDIM Sampler:  60%|██████    | 12/20 [00:17<00:11,  1.43s/it]\nDDIM Sampler:  65%|██████▌   | 13/20 [00:18<00:10,  1.43s/it]\nDDIM Sampler:  70%|███████   | 14/20 [00:19<00:08,  1.43s/it]\nDDIM Sampler:  75%|███████▌  | 15/20 [00:21<00:07,  1.43s/it]\nDDIM Sampler:  80%|████████  | 16/20 [00:22<00:05,  1.43s/it]\nDDIM Sampler:  85%|████████▌ | 17/20 [00:24<00:04,  1.44s/it]\nDDIM Sampler:  90%|█████████ | 18/20 [00:25<00:02,  1.44s/it]\nDDIM Sampler:  95%|█████████▌| 19/20 [00:27<00:01,  1.45s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:28<00:00,  1.45s/it]\nDDIM Sampler: 100%|██████████| 20/20 [00:28<00:00,  1.43s/it]\n<class 'numpy.ndarray'>\n(512, 768, 3)",
  "metrics": {
    "predict_time": 35.301674,
    "total_time": 492.329034
  },
  "output": [
    "https://storage.googleapis.com/replicate-files/PWpGmEAwYp50OddPlMXlUXKnekgZE78oqSucrfA7nFRqY8ZSA/out-0.png"
  ],
  "started_at": "2024-02-24T16:06:31.466093Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/elsb22zbvrv5nxstfzbzfrstpy",
    "cancel": "https://api.replicate.com/v1/predictions/elsb22zbvrv5nxstfzbzfrstpy/cancel"
  },
  "version": "905298f5d96cb992b6133132b151d4029122599cfd57d7ceb4c4e447b2390855"
}

Generated in

35.3 seconds

Tweak it Report View full prediction

Image shape: (4480, 6720, 3)
/src/annotator/uniformer/mmseg/models/segmentors/base.py:271: UserWarning: show==False and out_file is not specified, only result image will be returned
warnings.warn('show==False and out_file is not specified, only '
Global seed set to 3
Data shape for DDIM sampling is (1, 4, 64, 96), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler:   0%|          | 0/20 [00:00<?, ?it/s]
DDIM Sampler:   5%|▌         | 1/20 [00:01<00:30,  1.59s/it]
DDIM Sampler:  10%|█         | 2/20 [00:02<00:26,  1.47s/it]
DDIM Sampler:  15%|█▌        | 3/20 [00:04<00:24,  1.43s/it]
DDIM Sampler:  20%|██        | 4/20 [00:05<00:22,  1.42s/it]
DDIM Sampler:  25%|██▌       | 5/20 [00:07<00:21,  1.41s/it]
DDIM Sampler:  30%|███       | 6/20 [00:08<00:19,  1.41s/it]
DDIM Sampler:  35%|███▌      | 7/20 [00:09<00:18,  1.41s/it]
DDIM Sampler:  40%|████      | 8/20 [00:11<00:16,  1.41s/it]
DDIM Sampler:  45%|████▌     | 9/20 [00:12<00:15,  1.42s/it]
DDIM Sampler:  50%|█████     | 10/20 [00:14<00:14,  1.42s/it]
DDIM Sampler:  55%|█████▌    | 11/20 [00:15<00:12,  1.42s/it]
DDIM Sampler:  60%|██████    | 12/20 [00:17<00:11,  1.43s/it]
DDIM Sampler:  65%|██████▌   | 13/20 [00:18<00:10,  1.43s/it]
DDIM Sampler:  70%|███████   | 14/20 [00:19<00:08,  1.43s/it]
DDIM Sampler:  75%|███████▌  | 15/20 [00:21<00:07,  1.43s/it]
DDIM Sampler:  80%|████████  | 16/20 [00:22<00:05,  1.43s/it]
DDIM Sampler:  85%|████████▌ | 17/20 [00:24<00:04,  1.44s/it]
DDIM Sampler:  90%|█████████ | 18/20 [00:25<00:02,  1.44s/it]
DDIM Sampler:  95%|█████████▌| 19/20 [00:27<00:01,  1.45s/it]
DDIM Sampler: 100%|██████████| 20/20 [00:28<00:00,  1.45s/it]
DDIM Sampler: 100%|██████████| 20/20 [00:28<00:00,  1.43s/it]
<class 'numpy.ndarray'>
(512, 768, 3)

Run time and cost

This model costs approximately $0.085 to run on Replicate, or 11 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 T4 GPU hardware. Predictions typically complete within 7 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.