lightweight-ai/op_flux – Run with an API on Replicate

lightweight-ai / op_flux

Warm

Public
3.7K runs
A100 (80GB)

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Prompt for generated image

Default: "High quailty, 4K, UHD"

image

file

Upload an image for inpainting. This will be the base image that will be partially modified.

num_inference_steps

integer

The number of interfence steps

Default: 28

guidance

number

Default: 30

seed

integer

Random seed. Set for reproducible generation

width

integer

Default: 1408

height

integer

Default: 784

margin_x

integer

Horizontal margin from left edge of canvas

Default: 0

margin_y

integer

Vertical margin from top edge of canvas

Default: 0

overlap_percentage

integer

Overlap percentage

Default: 10

overlap_left

boolean

Activation Outpaint left overlap

Default: true

overlap_right

boolean

Activation Outpaint right overlap

Default: true

overlap_top

boolean

Activation Outpaint top overlap

Default: true

overlap_bottom

boolean

Activation Outpaint bottom overlap

Default: true

version

number

API version number. Different versions may produce different results.

Default: 0

fast_mode

boolean

Fast response mode - skip actual generation if true

Default: false

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

npx create-replicate --model=lightweight-ai/op_flux

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

const output = await replicate.run(
  "lightweight-ai/op_flux:1efeec559373fec9d972a77c512b0cb5643cc7a7b2bc28414ecfec18a2317aad",
  {
    input: {
      width: 1408,
      height: 784,
      prompt: "High quailty, 4K, UHD",
      version: 0,
      guidance: 30,
      margin_x: 0,
      margin_y: 0,
      fast_mode: false,
      overlap_top: true,
      overlap_left: true,
      overlap_right: true,
      overlap_bottom: true,
      overlap_percentage: 10,
      num_inference_steps: 28
    }
  }
);

// 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

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

output = replicate.run(
    "lightweight-ai/op_flux:1efeec559373fec9d972a77c512b0cb5643cc7a7b2bc28414ecfec18a2317aad",
    input={
        "width": 1408,
        "height": 784,
        "prompt": "High quailty, 4K, UHD",
        "version": 0,
        "guidance": 30,
        "margin_x": 0,
        "margin_y": 0,
        "fast_mode": False,
        "overlap_top": True,
        "overlap_left": True,
        "overlap_right": True,
        "overlap_bottom": True,
        "overlap_percentage": 10,
        "num_inference_steps": 28
    }
)
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 lightweight-ai/op_flux 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": "lightweight-ai/op_flux:1efeec559373fec9d972a77c512b0cb5643cc7a7b2bc28414ecfec18a2317aad",
    "input": {
      "width": 1408,
      "height": 784,
      "prompt": "High quailty, 4K, UHD",
      "version": 0,
      "guidance": 30,
      "margin_x": 0,
      "margin_y": 0,
      "fast_mode": false,
      "overlap_top": true,
      "overlap_left": true,
      "overlap_right": true,
      "overlap_bottom": true,
      "overlap_percentage": 10,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

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

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.