mlscade/face_swap_lab – Run with an API on Replicate

mlscade / face_swap_lab

face_swap_lab

Cold

Public
6 runs
A100 (80GB)

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

image

file

Input image [img2img or postprocessing modes only]

face_1_source_img

file

reference image

face_1_blend_faces

boolean

Will blend faces if True

Default: true

face_1_same_gender

boolean

Use same gender filtering

Default: false

face_1_sort_by_size

boolean

Sort Faces by size

Default: false

face_1_check_similarity

boolean

If True, discard images with low similarity

Default: false

face_1_compute_similarity

boolean

If True will compute similarity and add it to the image info

Default: false

face_1_min_sim

number

(minimum: 0, maximum: 1)

Minimum similarity against the used face

Default: 0

face_1_min_ref_sim

number

(minimum: 0, maximum: 1)

Minimum similarity against the reference

Default: 0

face_1_faces_index

string

Shift + Return to add a new line

The face index to use for swapping, comma separated list of face numbers starting from 0

Default: "0"

face_1_reference_face_index

integer

The face index to use to extract face from reference

Default: 0

face_1_improved_mask

boolean

Use Improved Mask

Default: false

face_1_color_corrections

boolean

Use Color Correction

Default: false

face_1_sharpen

boolean

Sharpen Image

Default: false

face_1_erosion_factor

number

(minimum: 0, maximum: 10)

Erosion Factor

Default: 1

face_2_enable

boolean

Enable face 2

Default: false

face_2_source_img

file

reference image

face_2_blend_faces

boolean

Will blend faces if True

Default: true

face_2_same_gender

boolean

Use same gender filtering

Default: false

face_2_sort_by_size

boolean

Sort Faces by size

Default: false

face_2_check_similarity

boolean

If True, discard images with low similarity

Default: false

face_2_compute_similarity

boolean

If True will compute similarity and add it to the image info

Default: false

face_2_min_sim

number

(minimum: 0, maximum: 1)

Minimum similarity against the used face

Default: 0

face_2_min_ref_sim

number

(minimum: 0, maximum: 1)

Minimum similarity against the reference

Default: 0

face_2_faces_index

string

Shift + Return to add a new line

The face index to use for swapping, comma separated list of face numbers starting from 0

Default: "0"

face_2_reference_face_index

integer

The face index to use to extract face from reference

Default: 0

face_2_improved_mask

boolean

Use Improved Mask

Default: false

face_2_color_corrections

boolean

Use Color Correction

Default: false

face_2_sharpen

boolean

Sharpen Image

Default: false

face_2_erosion_factor

number

(minimum: 0, maximum: 10)

Erosion Factor

Default: 1

face_restorer_name

string

face restorer name

Default: "CodeFormer"

restorer_visibility

number

(minimum: 0, maximum: 1)

face restorer visibility

Default: 1

codeformer_weight

number

(minimum: 0, maximum: 1)

face restorer codeformer weight

Default: 1

upscaler_name

string

upscaler name

Default: "4x-UltraSharp"

scale

number

(minimum: 0, maximum: 10)

upscaling scale

Default: 1

upscaler_visibility

number

(minimum: 0, maximum: 1)

upscaler visibility

Default: 1

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

npx create-replicate --model=mlscade/face_swap_lab

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

const output = await replicate.run(
  "mlscade/face_swap_lab:5329af124a2b7120c673285a58bc128833f2b720a5e75dc932e10c82d247ede9",
  {
    input: {
      scale: 1,
      face_2_enable: false,
      upscaler_name: "4x-UltraSharp",
      face_1_min_sim: 0,
      face_1_sharpen: false,
      face_2_min_sim: 0,
      face_2_sharpen: false,
      codeformer_weight: 1,
      face_1_blend_faces: true,
      face_1_faces_index: "0",
      face_1_min_ref_sim: 0,
      face_1_same_gender: false,
      face_2_blend_faces: true,
      face_2_faces_index: "0",
      face_2_min_ref_sim: 0,
      face_2_same_gender: false,
      face_restorer_name: "CodeFormer",
      face_1_sort_by_size: false,
      face_2_sort_by_size: false,
      restorer_visibility: 1,
      upscaler_visibility: 1,
      face_1_improved_mask: false,
      face_2_improved_mask: false,
      face_1_erosion_factor: 1,
      face_2_erosion_factor: 1,
      face_1_check_similarity: false,
      face_2_check_similarity: false,
      face_1_color_corrections: false,
      face_2_color_corrections: false,
      face_1_compute_similarity: false,
      face_2_compute_similarity: false,
      face_1_reference_face_index: 0,
      face_2_reference_face_index: 0
    }
  }
);

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

output = replicate.run(
    "mlscade/face_swap_lab:5329af124a2b7120c673285a58bc128833f2b720a5e75dc932e10c82d247ede9",
    input={
        "scale": 1,
        "face_2_enable": False,
        "upscaler_name": "4x-UltraSharp",
        "face_1_min_sim": 0,
        "face_1_sharpen": False,
        "face_2_min_sim": 0,
        "face_2_sharpen": False,
        "codeformer_weight": 1,
        "face_1_blend_faces": True,
        "face_1_faces_index": "0",
        "face_1_min_ref_sim": 0,
        "face_1_same_gender": False,
        "face_2_blend_faces": True,
        "face_2_faces_index": "0",
        "face_2_min_ref_sim": 0,
        "face_2_same_gender": False,
        "face_restorer_name": "CodeFormer",
        "face_1_sort_by_size": False,
        "face_2_sort_by_size": False,
        "restorer_visibility": 1,
        "upscaler_visibility": 1,
        "face_1_improved_mask": False,
        "face_2_improved_mask": False,
        "face_1_erosion_factor": 1,
        "face_2_erosion_factor": 1,
        "face_1_check_similarity": False,
        "face_2_check_similarity": False,
        "face_1_color_corrections": False,
        "face_2_color_corrections": False,
        "face_1_compute_similarity": False,
        "face_2_compute_similarity": False,
        "face_1_reference_face_index": 0,
        "face_2_reference_face_index": 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 mlscade/face_swap_lab 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": "mlscade/face_swap_lab:5329af124a2b7120c673285a58bc128833f2b720a5e75dc932e10c82d247ede9",
    "input": {
      "scale": 1,
      "face_2_enable": false,
      "upscaler_name": "4x-UltraSharp",
      "face_1_min_sim": 0,
      "face_1_sharpen": false,
      "face_2_min_sim": 0,
      "face_2_sharpen": false,
      "codeformer_weight": 1,
      "face_1_blend_faces": true,
      "face_1_faces_index": "0",
      "face_1_min_ref_sim": 0,
      "face_1_same_gender": false,
      "face_2_blend_faces": true,
      "face_2_faces_index": "0",
      "face_2_min_ref_sim": 0,
      "face_2_same_gender": false,
      "face_restorer_name": "CodeFormer",
      "face_1_sort_by_size": false,
      "face_2_sort_by_size": false,
      "restorer_visibility": 1,
      "upscaler_visibility": 1,
      "face_1_improved_mask": false,
      "face_2_improved_mask": false,
      "face_1_erosion_factor": 1,
      "face_2_erosion_factor": 1,
      "face_1_check_similarity": false,
      "face_2_check_similarity": false,
      "face_1_color_corrections": false,
      "face_2_color_corrections": false,
      "face_1_compute_similarity": false,
      "face_2_compute_similarity": false,
      "face_1_reference_face_index": 0,
      "face_2_reference_face_index": 0
    }
  }' \
  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.