anotherjesse/controlnet-inpaint-test – Run with an API on Replicate

anotherjesse / controlnet-inpaint-test

controlnet_v11p_sd15_inpainting demo

Cold

Public
97.1K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

control_image

file

Preview

Optional Image to use for guidance based on inpainting

mask

file

Preview

Mask to use for control inpainting

prompt

string

Shift + Return to add a new line

Input prompt

Default: "photo of cjw person"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

num_outputs

integer

(minimum: 1, maximum: 10)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

disable_safety_check

boolean

Disable safety check. Use at your own risk!

Default: false

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=anotherjesse/controlnet-inpaint-test

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

const output = await replicate.run(
  "anotherjesse/controlnet-inpaint-test:3a294336beb5dcaba6c5baf1418058171298d559e4eef8dafed1e0a8c3594984",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/J70YfPyVE2xFVDHK0kdmMhiuaNrKxOBnDbMzvC6SfbCv2iWs/mask.png",
      width: 512,
      height: 512,
      prompt: "a handsome man with ray-ban sunglasses",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      control_image: "https://replicate.delivery/pbxt/J70YfER9vhcJsFsJ2Jw5MAdC97mB97bNrh7eU84t7XEkaCpa/control.png",
      guidance_scale: 7.5,
      num_inference_steps: 50,
      disable_safety_check: false
    }
  }
);
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 anotherjesse/controlnet-inpaint-test using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/controlnet-inpaint-test:3a294336beb5dcaba6c5baf1418058171298d559e4eef8dafed1e0a8c3594984",
    input={
        "mask": "https://replicate.delivery/pbxt/J70YfPyVE2xFVDHK0kdmMhiuaNrKxOBnDbMzvC6SfbCv2iWs/mask.png",
        "width": 512,
        "height": 512,
        "prompt": "a handsome man with ray-ban sunglasses",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "control_image": "https://replicate.delivery/pbxt/J70YfER9vhcJsFsJ2Jw5MAdC97mB97bNrh7eU84t7XEkaCpa/control.png",
        "guidance_scale": 7.5,
        "num_inference_steps": 50,
        "disable_safety_check": False
    }
)

# The anotherjesse/controlnet-inpaint-test model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/anotherjesse/controlnet-inpaint-test/api#output-schema
    print(item)

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 anotherjesse/controlnet-inpaint-test 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": "3a294336beb5dcaba6c5baf1418058171298d559e4eef8dafed1e0a8c3594984",
    "input": {
      "mask": "https://replicate.delivery/pbxt/J70YfPyVE2xFVDHK0kdmMhiuaNrKxOBnDbMzvC6SfbCv2iWs/mask.png",
      "width": 512,
      "height": 512,
      "prompt": "a handsome man with ray-ban sunglasses",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/J70YfER9vhcJsFsJ2Jw5MAdC97mB97bNrh7eU84t7XEkaCpa/control.png",
      "guidance_scale": 7.5,
      "num_inference_steps": 50,
      "disable_safety_check": false
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-07-04T04:03:55.972789Z",
  "created_at": "2023-07-04T04:01:58.017394Z",
  "data_removed": false,
  "error": null,
  "id": "sqp5j2tbvaxp4ddbmgemctdrpa",
  "input": {
    "mask": "https://replicate.delivery/pbxt/J70YfPyVE2xFVDHK0kdmMhiuaNrKxOBnDbMzvC6SfbCv2iWs/mask.png",
    "width": 512,
    "height": 512,
    "prompt": "a handsome man with ray-ban sunglasses",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "control_image": "https://replicate.delivery/pbxt/J70YfER9vhcJsFsJ2Jw5MAdC97mB97bNrh7eU84t7XEkaCpa/control.png",
    "guidance_scale": 7.5,
    "num_inference_steps": 50
  },
  "logs": "Using ControlNet inpaint\n(512, 512, 3)\n(512, 512)\nUsing seed: 8466\n/root/.pyenv/versions/3.11.4/lib/python3.11/site-packages/diffusers/configuration_utils.py:135: FutureWarning: Accessing config attribute `use_karras_sigmas` directly via 'HeunDiscreteScheduler' object attribute is deprecated. Please access 'use_karras_sigmas' over 'HeunDiscreteScheduler's config object instead, e.g. 'scheduler.config.use_karras_sigmas'.\ndeprecate(\"direct config name access\", \"1.0.0\", deprecation_message, standard_warn=False)\nparsed prompt: Conjunction:[FlattenedPrompt:[Fragment:'a handsome man with ray-ban sunglasses'@1.0]] | type AND | weights [1.0] | loras []\n/root/.pyenv/versions/3.11.4/lib/python3.11/site-packages/diffusers/image_processor.py:204: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:07,  6.25it/s]\n  8%|▊         | 4/50 [00:00<00:02, 15.66it/s]\n 14%|█▍        | 7/50 [00:00<00:02, 19.33it/s]\n 20%|██        | 10/50 [00:00<00:01, 21.16it/s]\n 26%|██▌       | 13/50 [00:00<00:01, 22.23it/s]\n 32%|███▏      | 16/50 [00:00<00:01, 22.89it/s]\n 38%|███▊      | 19/50 [00:00<00:01, 23.32it/s]\n 44%|████▍     | 22/50 [00:01<00:01, 23.60it/s]\n 50%|█████     | 25/50 [00:01<00:01, 23.79it/s]\n 56%|█████▌    | 28/50 [00:01<00:00, 23.91it/s]\n 62%|██████▏   | 31/50 [00:01<00:00, 24.00it/s]\n 68%|██████▊   | 34/50 [00:01<00:00, 24.06it/s]\n 74%|███████▍  | 37/50 [00:01<00:00, 24.11it/s]\n 80%|████████  | 40/50 [00:01<00:00, 24.13it/s]\n 86%|████████▌ | 43/50 [00:01<00:00, 24.13it/s]\n 92%|█████████▏| 46/50 [00:02<00:00, 24.14it/s]\n 98%|█████████▊| 49/50 [00:02<00:00, 24.14it/s]\n100%|██████████| 50/50 [00:02<00:00, 22.87it/s]",
  "metrics": {
    "predict_time": 5.72184,
    "total_time": 117.955395
  },
  "output": [
    "https://replicate.delivery/pbxt/4tjRIiRkYTqGNBS2fFVsDFxOh62LfmODwyCMKekTGcrUhpYiA/seed-8466.png"
  ],
  "started_at": "2023-07-04T04:03:50.250949Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sqp5j2tbvaxp4ddbmgemctdrpa",
    "cancel": "https://api.replicate.com/v1/predictions/sqp5j2tbvaxp4ddbmgemctdrpa/cancel"
  },
  "version": "3a294336beb5dcaba6c5baf1418058171298d559e4eef8dafed1e0a8c3594984"
}

Generated in

5.7 seconds

Tweak itReport

Using ControlNet inpaint
(512, 512, 3)
(512, 512)
Using seed: 8466
/root/.pyenv/versions/3.11.4/lib/python3.11/site-packages/diffusers/configuration_utils.py:135: FutureWarning: Accessing config attribute `use_karras_sigmas` directly via 'HeunDiscreteScheduler' object attribute is deprecated. Please access 'use_karras_sigmas' over 'HeunDiscreteScheduler's config object instead, e.g. 'scheduler.config.use_karras_sigmas'.
deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False)
parsed prompt: Conjunction:[FlattenedPrompt:[Fragment:'a handsome man with ray-ban sunglasses'@1.0]] | type AND | weights [1.0] | loras []
/root/.pyenv/versions/3.11.4/lib/python3.11/site-packages/diffusers/image_processor.py:204: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]
warnings.warn(
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:07,  6.25it/s]
  8%|▊         | 4/50 [00:00<00:02, 15.66it/s]
 14%|█▍        | 7/50 [00:00<00:02, 19.33it/s]
 20%|██        | 10/50 [00:00<00:01, 21.16it/s]
 26%|██▌       | 13/50 [00:00<00:01, 22.23it/s]
 32%|███▏      | 16/50 [00:00<00:01, 22.89it/s]
 38%|███▊      | 19/50 [00:00<00:01, 23.32it/s]
 44%|████▍     | 22/50 [00:01<00:01, 23.60it/s]
 50%|█████     | 25/50 [00:01<00:01, 23.79it/s]
 56%|█████▌    | 28/50 [00:01<00:00, 23.91it/s]
 62%|██████▏   | 31/50 [00:01<00:00, 24.00it/s]
 68%|██████▊   | 34/50 [00:01<00:00, 24.06it/s]
 74%|███████▍  | 37/50 [00:01<00:00, 24.11it/s]
 80%|████████  | 40/50 [00:01<00:00, 24.13it/s]
 86%|████████▌ | 43/50 [00:01<00:00, 24.13it/s]
 92%|█████████▏| 46/50 [00:02<00:00, 24.14it/s]
 98%|█████████▊| 49/50 [00:02<00:00, 24.14it/s]
100%|██████████| 50/50 [00:02<00:00, 22.87it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.029 to run on Replicate, or 34 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 A100 (80GB) GPU hardware. Predictions typically complete within 21 seconds.

Readme

This model doesn't have a readme.