yan-ops/ai_face_swap – Run with an API on Replicate

yan-ops / ai_face_swap

Cold

Public
595.7K runs
L40S

Run with an API

Playground API Examples README Versions

Input

source_image

file

source image

request_id

string

Shift + Return to add a new line

request_id

Default: ""

det_thresh

number

det_thresh default 0.1

Default: 0.1

local_source

file

local source image

prompt

*string

Shift + Return to add a new line

prompt

negative_prompt

string

Shift + Return to add a new line

negative_prompt

Default: ""

batch_size

integer

batch_size, default 1

Default: 1

width

integer

width, default 640

Default: 640

height

integer

width, default 800

Default: 800

sampling_steps

integer

sampling_steps, default 7

Default: 7

cfg_scale

number

cfg_scale default 1.8

Default: 1.8

sampling_method

string

sampling_method, default Euler A

Default: "Euler A"

disable_safety_checker

boolean

prompt

Default: true

seed

integer

generator seed

model

string

Shift + Return to add a new line

model, default control_v11p_sd15_openpose

Default: "control_v11p_sd15_openpose"

local_control_image

file

local_control_image

control_image

string

Shift + Return to add a new line

control_image

control_guidance_start

number

control_guidance_start

Default: 0

control_guidance_end

number

control_guidance_start

Default: 1

controlnet_conditioning_scale

number

controlnet_conditioning_scale default 0.3

Default: 0.3

token_merging_ratio

number

token_merging_ratio default 0.5

Default: 0.5

denoising_strength

number

denoising strength default 0.6

Default: 0.6

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

npx create-replicate --model=yan-ops/ai_face_swap

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

const output = await replicate.run(
  "yan-ops/ai_face_swap:39a5f139b5fe7539e46551b54d4fc566656a0acb4c98d6c78fc75f7d4cc61d2a",
  {
    input: {
      model: "control_v11p_sd15_openpose",
      width: 640,
      height: 800,
      cfg_scale: 1.8,
      batch_size: 1,
      det_thresh: 0.1,
      request_id: "",
      sampling_steps: 7,
      negative_prompt: "",
      sampling_method: "Euler A",
      denoising_strength: 0.6,
      token_merging_ratio: 0.5,
      control_guidance_end: 1,
      control_guidance_start: 0,
      controlnet_conditioning_scale: 0.3
    }
  }
);
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 yan-ops/ai_face_swap using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "yan-ops/ai_face_swap:39a5f139b5fe7539e46551b54d4fc566656a0acb4c98d6c78fc75f7d4cc61d2a",
    input={
        "model": "control_v11p_sd15_openpose",
        "width": 640,
        "height": 800,
        "cfg_scale": 1.8,
        "batch_size": 1,
        "det_thresh": 0.1,
        "request_id": "",
        "sampling_steps": 7,
        "negative_prompt": "",
        "sampling_method": "Euler A",
        "denoising_strength": 0.6,
        "token_merging_ratio": 0.5,
        "control_guidance_end": 1,
        "control_guidance_start": 0,
        "controlnet_conditioning_scale": 0.3
    }
)
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 yan-ops/ai_face_swap 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": "39a5f139b5fe7539e46551b54d4fc566656a0acb4c98d6c78fc75f7d4cc61d2a",
    "input": {
      "model": "control_v11p_sd15_openpose",
      "width": 640,
      "height": 800,
      "cfg_scale": 1.8,
      "batch_size": 1,
      "det_thresh": 0.1,
      "request_id": "",
      "sampling_steps": 7,
      "negative_prompt": "",
      "sampling_method": "Euler A",
      "denoising_strength": 0.6,
      "token_merging_ratio": 0.5,
      "control_guidance_end": 1,
      "control_guidance_start": 0,
      "controlnet_conditioning_scale": 0.3
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

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

Pull and run yan-ops/ai_face_swap using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/yan-ops/ai_face_swap@sha256:39a5f139b5fe7539e46551b54d4fc566656a0acb4c98d6c78fc75f7d4cc61d2a \
  -i 'model="control_v11p_sd15_openpose"' \
  -i 'width=640' \
  -i 'height=800' \
  -i 'cfg_scale=1.8' \
  -i 'batch_size=1' \
  -i 'det_thresh=0.1' \
  -i 'request_id=""' \
  -i 'sampling_steps=7' \
  -i 'negative_prompt=""' \
  -i 'sampling_method="Euler A"' \
  -i 'denoising_strength=0.6' \
  -i 'token_merging_ratio=0.5' \
  -i 'control_guidance_end=1' \
  -i 'control_guidance_start=0' \
  -i 'controlnet_conditioning_scale=0.3'

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

Pull and run yan-ops/ai_face_swap using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/yan-ops/ai_face_swap@sha256:39a5f139b5fe7539e46551b54d4fc566656a0acb4c98d6c78fc75f7d4cc61d2a
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "model": "control_v11p_sd15_openpose",
      "width": 640,
      "height": 800,
      "cfg_scale": 1.8,
      "batch_size": 1,
      "det_thresh": 0.1,
      "request_id": "",
      "sampling_steps": 7,
      "negative_prompt": "",
      "sampling_method": "Euler A",
      "denoising_strength": 0.6,
      "token_merging_ratio": 0.5,
      "control_guidance_end": 1,
      "control_guidance_start": 0,
      "controlnet_conditioning_scale": 0.3
    }
  }' \
  http://localhost:5000/predictions

Output

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

Run time and cost

This model costs approximately $0.025 to run on Replicate, or 40 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 L40S GPU hardware. Predictions typically complete within 27 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.