lightweight-ai/model2_9 – Run with an API on Replicate

lightweight-ai / model2_9

Warm

Public
93K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A bohemian-style female travel blogger with sun-kissed skin and messy beach wavesA bohemian-style female travel blogger with sun-kissed skin and messy beach waves

Prompt for generated image

Default: "A bohemian-style female travel blogger with sun-kissed skin and messy beach waves"

image

file

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

guidance_scale

number

Default: 3.5

inpaint

boolean

Default: false

controlnet

boolean

Default: false

mask

file

Upload a mask image for inpainting. White areas (255) indicate regions to be inpainted, while black areas (0) will be preserved from the original image.

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.

Default: 0.8

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of inference steps

Default: 28

loras

string[]

Lora list (Realism, Karina, IU)

Default: []

lora_scales

number[]

Enter a string of numbers separated by commas

Lora scales

Default: []

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

Default: "png"

output_quality

integer

(minimum: 0, maximum: 100)

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 100

control_strength

number

(minimum: 0, maximum: 1)

ControlNet strength, depth works best at 0.2, canny works best at 0.4. Recommended range is 0.3-0.8

Default: 0.65

control_image

file

Control image

low_threshold

integer

Default: 100

high_threshold

integer

Default: 200

sketch_image

file

Control image

nsfw_chekcer

boolean

Default: false

brightness

number

Default: 1

annotator

string

An enumeration.

Default: "canny"

control_guidance_start

number

(minimum: 0, maximum: 1)

control_guidance_start

Default: 0

control_guidance_end

number

(minimum: 0, maximum: 1)

control_guidance_end

Default: 0.8

version

number

API version number. Different versions may produce different results.

Default: 0

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

npx create-replicate --model=lightweight-ai/model2_9

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/model2_9 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lightweight-ai/model2_9:1626a5fdbf7cd41ec52a04db3b9c72d52fcad4e81af18789a008121374bc0eac",
  {
    input: {
      loras: [],
      width: 1024,
      height: 1024,
      prompt: "A bohemian-style female travel blogger with sun-kissed skin and messy beach waves",
      inpaint: false,
      version: 0,
      annotator: "canny",
      brightness: 1,
      controlnet: false,
      lora_scales: [],
      num_outputs: 1,
      nsfw_chekcer: false,
      low_threshold: 100,
      output_format: "png",
      guidance_scale: 3.5,
      high_threshold: 200,
      output_quality: 100,
      prompt_strength: 0.8,
      control_strength: 0.65,
      num_inference_steps: 28,
      control_guidance_end: 0.8,
      control_guidance_start: 0
    }
  }
);

// 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/model2_9 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lightweight-ai/model2_9:1626a5fdbf7cd41ec52a04db3b9c72d52fcad4e81af18789a008121374bc0eac",
    input={
        "loras": [],
        "width": 1024,
        "height": 1024,
        "prompt": "A bohemian-style female travel blogger with sun-kissed skin and messy beach waves",
        "inpaint": False,
        "version": 0,
        "annotator": "canny",
        "brightness": 1,
        "controlnet": False,
        "lora_scales": [],
        "num_outputs": 1,
        "nsfw_chekcer": False,
        "low_threshold": 100,
        "output_format": "png",
        "guidance_scale": 3.5,
        "high_threshold": 200,
        "output_quality": 100,
        "prompt_strength": 0.8,
        "control_strength": 0.65,
        "num_inference_steps": 28,
        "control_guidance_end": 0.8,
        "control_guidance_start": 0
    }
)
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/model2_9 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": "1626a5fdbf7cd41ec52a04db3b9c72d52fcad4e81af18789a008121374bc0eac",
    "input": {
      "loras": [],
      "width": 1024,
      "height": 1024,
      "prompt": "A bohemian-style female travel blogger with sun-kissed skin and messy beach waves",
      "inpaint": false,
      "version": 0,
      "annotator": "canny",
      "brightness": 1,
      "controlnet": false,
      "lora_scales": [],
      "num_outputs": 1,
      "nsfw_chekcer": false,
      "low_threshold": 100,
      "output_format": "png",
      "guidance_scale": 3.5,
      "high_threshold": 200,
      "output_quality": 100,
      "prompt_strength": 0.8,
      "control_strength": 0.65,
      "num_inference_steps": 28,
      "control_guidance_end": 0.8,
      "control_guidance_start": 0
    }
  }' \
  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/lightweight-ai/model2_9@sha256:1626a5fdbf7cd41ec52a04db3b9c72d52fcad4e81af18789a008121374bc0eac \
  -i 'loras=[]' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A bohemian-style female travel blogger with sun-kissed skin and messy beach waves"' \
  -i 'inpaint=false' \
  -i 'version=0' \
  -i 'annotator="canny"' \
  -i 'brightness=1' \
  -i 'controlnet=false' \
  -i 'lora_scales=[]' \
  -i 'num_outputs=1' \
  -i 'nsfw_chekcer=false' \
  -i 'low_threshold=100' \
  -i 'output_format="png"' \
  -i 'guidance_scale=3.5' \
  -i 'high_threshold=200' \
  -i 'output_quality=100' \
  -i 'prompt_strength=0.8' \
  -i 'control_strength=0.65' \
  -i 'num_inference_steps=28' \
  -i 'control_guidance_end=0.8' \
  -i 'control_guidance_start=0'

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/lightweight-ai/model2_9@sha256:1626a5fdbf7cd41ec52a04db3b9c72d52fcad4e81af18789a008121374bc0eac
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "loras": [],
      "width": 1024,
      "height": 1024,
      "prompt": "A bohemian-style female travel blogger with sun-kissed skin and messy beach waves",
      "inpaint": false,
      "version": 0,
      "annotator": "canny",
      "brightness": 1,
      "controlnet": false,
      "lora_scales": [],
      "num_outputs": 1,
      "nsfw_chekcer": false,
      "low_threshold": 100,
      "output_format": "png",
      "guidance_scale": 3.5,
      "high_threshold": 200,
      "output_quality": 100,
      "prompt_strength": 0.8,
      "control_strength": 0.65,
      "num_inference_steps": 28,
      "control_guidance_end": 0.8,
      "control_guidance_start": 0
    }
  }' \
  http://localhost:5000/predictions

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

Output

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

Run time and cost

This model costs approximately $0.0014 to run on Replicate, or 714 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 1 seconds.

Readme

This model doesn't have a readme.