fenglinglwb/large-hole-image-inpainting:4b52aba4

Version

You're looking at a specific version of this model. Jump to the model overview.

fenglinglwb /large-hole-image-inpainting:4b52aba4

Input

image

*file

Input image to inpaint; must be 512x512 in size. You can crop your image to size here: https://www.iloveimg.com/crop-image

mask

file

Optional mask (also 512x512) that overlays image. Should be black in areas that you wish to inpaint. If left blank, a random mask will be generated over the image.

model

string

Select which model to use: Places or CelebA-HQ-512

Default: "places"

truncation_psi

number

Truncation psi. Improve image quality at the cost of output diversity/variation; truncation psi ψ = 1 means no truncation, ψ = 0 means no diversity.

Default: 1

noise_mode

string

Noise mode

Default: "const"

seed

integer

(minimum: -1, maximum: 4294967295)

Seed for random number generator to encourage diverse results. If -1, a random seed will be chosen. (minimum: -1; maximum: 4294967295)

Default: -1

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

npx create-replicate --model=fenglinglwb/large-hole-image-inpainting

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 fenglinglwb/large-hole-image-inpainting using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fenglinglwb/large-hole-image-inpainting:4b52aba43c7acdf89dd71429921a60f3696c2bb9c9242f10f1a6c212c0e596eb",
  {
    input: {
      seed: -1,
      model: "places",
      noise_mode: "const",
      truncation_psi: 1
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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 fenglinglwb/large-hole-image-inpainting using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fenglinglwb/large-hole-image-inpainting:4b52aba43c7acdf89dd71429921a60f3696c2bb9c9242f10f1a6c212c0e596eb",
    input={
        "seed": -1,
        "model": "places",
        "noise_mode": "const",
        "truncation_psi": 1
    }
)
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 fenglinglwb/large-hole-image-inpainting 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": "4b52aba43c7acdf89dd71429921a60f3696c2bb9c9242f10f1a6c212c0e596eb",
    "input": {
      "seed": -1,
      "model": "places",
      "noise_mode": "const",
      "truncation_psi": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/fenglinglwb/large-hole-image-inpainting@sha256:4b52aba43c7acdf89dd71429921a60f3696c2bb9c9242f10f1a6c212c0e596eb \
  -i 'seed=-1' \
  -i 'model="places"' \
  -i 'noise_mode="const"' \
  -i 'truncation_psi=1'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/fenglinglwb/large-hole-image-inpainting@sha256:4b52aba43c7acdf89dd71429921a60f3696c2bb9c9242f10f1a6c212c0e596eb
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "model": "places",
      "noise_mode": "const",
      "truncation_psi": 1
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

No output yet! Press "Submit" to start a prediction.