qwaezrx/ipadapter-faceid-faceswap-upscale:5ce588c1

Version

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

qwaezrx /ipadapter-faceid-faceswap-upscale:5ce588c1

Input

positive_prompt

string

Shift + Return to add a new line

photo of a man, fashion model, simple clothes

high quality, highly detailed, 4k, highresphoto of a man, fashion model, simple clothes

high quality, highly detailed, 4k, highres

Positive Prompt

Default: "photo of a man, fashion model, simple clothes\n\nhigh quality, highly detailed, 4k, highres"

negative_prompt

string

Shift + Return to add a new line

blurry, distorted, low quality, bad handsblurry, distorted, low quality, bad hands

Negative Prompt

Default: "blurry, distorted, low quality, bad hands"

face_image

*file

Source image of the face

checkpoint

string

SD 1.5 model checkpoint

Default: "beautifulRealistic_v7.safetensors"

num_inference_steps

integer

Steps

Default: 30

batch_size

integer

Number of images to generate in batch

Default: 1

repeat

integer

Repeat running this request (2 batch size, 2 repeat -> 2 * 2 images)

Default: 1

width

integer

Default: 512

height

integer

Default: 768

cfg

number

Default: 8

seed

integer

Sampling seed, leave Empty for Random

vae

string

An enumeration.

Default: "vae-ft-mse-840000-ema-pruned.safetensors"

sampler

string

An enumeration.

Default: "euler"

scheduler

string

An enumeration.

Default: "normal"

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

npx create-replicate --model=qwaezrx/ipadapter-faceid-faceswap-upscale

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 qwaezrx/ipadapter-faceid-faceswap-upscale using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "qwaezrx/ipadapter-faceid-faceswap-upscale:5ce588c1966bfac3c2f9cd2d25fe573dbed41b284cf0fdab891c699a966eea37",
  {
    input: {
      cfg: 8,
      vae: "vae-ft-mse-840000-ema-pruned.safetensors",
      width: 512,
      height: 768,
      repeat: 1,
      sampler: "euler",
      scheduler: "normal",
      batch_size: 1,
      checkpoint: "beautifulRealistic_v7.safetensors",
      negative_prompt: "blurry, distorted, low quality, bad hands",
      positive_prompt: "photo of a man, fashion model, simple clothes\n\nhigh quality, highly detailed, 4k, highres",
      num_inference_steps: 30
    }
  }
);

// 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 qwaezrx/ipadapter-faceid-faceswap-upscale using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "qwaezrx/ipadapter-faceid-faceswap-upscale:5ce588c1966bfac3c2f9cd2d25fe573dbed41b284cf0fdab891c699a966eea37",
    input={
        "cfg": 8,
        "vae": "vae-ft-mse-840000-ema-pruned.safetensors",
        "width": 512,
        "height": 768,
        "repeat": 1,
        "sampler": "euler",
        "scheduler": "normal",
        "batch_size": 1,
        "checkpoint": "beautifulRealistic_v7.safetensors",
        "negative_prompt": "blurry, distorted, low quality, bad hands",
        "positive_prompt": "photo of a man, fashion model, simple clothes\n\nhigh quality, highly detailed, 4k, highres",
        "num_inference_steps": 30
    }
)
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 qwaezrx/ipadapter-faceid-faceswap-upscale 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": "qwaezrx/ipadapter-faceid-faceswap-upscale:5ce588c1966bfac3c2f9cd2d25fe573dbed41b284cf0fdab891c699a966eea37",
    "input": {
      "cfg": 8,
      "vae": "vae-ft-mse-840000-ema-pruned.safetensors",
      "width": 512,
      "height": 768,
      "repeat": 1,
      "sampler": "euler",
      "scheduler": "normal",
      "batch_size": 1,
      "checkpoint": "beautifulRealistic_v7.safetensors",
      "negative_prompt": "blurry, distorted, low quality, bad hands",
      "positive_prompt": "photo of a man, fashion model, simple clothes\\n\\nhigh quality, highly detailed, 4k, highres",
      "num_inference_steps": 30
    }
  }' \
  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.