juanfranem/ip-adapter-full-face | Run with an API on Replicate

Input

image

file

Input face image

model

string

Model

Default: "realistic"

prompt

string

Shift + Return to add a new line

a girl who looks like unmasked spiderman in a big citya girl who looks like unmasked spiderman in a big city

Prompt

Default: "photo of a beautiful girl wearing casual shirt in a garden"

negative_prompt

string

Shift + Return to add a new line

simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurrysimple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurry

Negative Prompt

Default: "(deformed), text"

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

seed

integer

Random seed. Leave blank to randomize the seed

width

integer

Image width

Default: 512

height

integer

Image height

Default: 704

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

npx create-replicate --model=juanfranem/ip-adapter-full-face

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";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run juanfranem/ip-adapter-full-face using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "juanfranem/ip-adapter-full-face:18fd619984b344195d4f9f45a849ecc514475ec7e07f8966b0dc679676cc4960",
  {
    input: {
      image: "https://replicate.delivery/pbxt/LgUjhXQTCzFMriy3nojzfOTw47qbfGl6YXId51Mx6Omoj7yH/input.jpg",
      model: "realistic",
      width: 512,
      height: 704,
      prompt: "a girl who looks like unmasked spiderman in a big city",
      num_outputs: 1,
      negative_prompt: "simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurry",
      num_inference_steps: 50
    }
  }
);

// 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 juanfranem/ip-adapter-full-face using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "juanfranem/ip-adapter-full-face:18fd619984b344195d4f9f45a849ecc514475ec7e07f8966b0dc679676cc4960",
    input={
        "image": "https://replicate.delivery/pbxt/LgUjhXQTCzFMriy3nojzfOTw47qbfGl6YXId51Mx6Omoj7yH/input.jpg",
        "model": "realistic",
        "width": 512,
        "height": 704,
        "prompt": "a girl who looks like unmasked spiderman in a big city",
        "num_outputs": 1,
        "negative_prompt": "simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurry",
        "num_inference_steps": 50
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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 juanfranem/ip-adapter-full-face 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": "juanfranem/ip-adapter-full-face:18fd619984b344195d4f9f45a849ecc514475ec7e07f8966b0dc679676cc4960",
    "input": {
      "image": "https://replicate.delivery/pbxt/LgUjhXQTCzFMriy3nojzfOTw47qbfGl6YXId51Mx6Omoj7yH/input.jpg",
      "model": "realistic",
      "width": 512,
      "height": 704,
      "prompt": "a girl who looks like unmasked spiderman in a big city",
      "num_outputs": 1,
      "negative_prompt": "simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurry",
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-09-25T11:36:42.383352Z",
  "created_at": "2024-09-25T11:33:43.770000Z",
  "data_removed": false,
  "error": null,
  "id": "fksmvkk4v9rgg0cj53ttj44dh0",
  "input": {
    "image": "https://replicate.delivery/pbxt/LgUjhXQTCzFMriy3nojzfOTw47qbfGl6YXId51Mx6Omoj7yH/input.jpg",
    "model": "realistic",
    "width": 512,
    "height": 704,
    "prompt": "a girl who looks like unmasked spiderman in a big city",
    "num_outputs": 1,
    "negative_prompt": "simple background, duplicate, retro style, low quality, lowest quality, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013, bad anatomy, bad proportions, extra digits, lowres, username, artist name, error, duplicate, watermark, signature, text, extra digit, fewer digits, worst quality, jpeg artifacts, blurry",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 50684\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:07,  6.36it/s]\n  6%|▌         | 3/50 [00:00<00:03, 12.19it/s]\n 10%|█         | 5/50 [00:00<00:03, 14.58it/s]\n 14%|█▍        | 7/50 [00:00<00:02, 15.82it/s]\n 18%|█▊        | 9/50 [00:00<00:02, 16.55it/s]\n 22%|██▏       | 11/50 [00:00<00:02, 17.00it/s]\n 26%|██▌       | 13/50 [00:00<00:02, 17.29it/s]\n 30%|███       | 15/50 [00:00<00:02, 17.44it/s]\n 34%|███▍      | 17/50 [00:01<00:01, 17.57it/s]\n 38%|███▊      | 19/50 [00:01<00:01, 17.61it/s]\n 42%|████▏     | 21/50 [00:01<00:01, 17.62it/s]\n 46%|████▌     | 23/50 [00:01<00:01, 17.67it/s]\n 50%|█████     | 25/50 [00:01<00:01, 17.69it/s]\n 54%|█████▍    | 27/50 [00:01<00:01, 17.71it/s]\n 58%|█████▊    | 29/50 [00:01<00:01, 17.73it/s]\n 62%|██████▏   | 31/50 [00:01<00:01, 17.73it/s]\n 66%|██████▌   | 33/50 [00:01<00:00, 17.74it/s]\n 70%|███████   | 35/50 [00:02<00:00, 17.73it/s]\n 74%|███████▍  | 37/50 [00:02<00:00, 17.71it/s]\n 78%|███████▊  | 39/50 [00:02<00:00, 17.72it/s]\n 82%|████████▏ | 41/50 [00:02<00:00, 17.73it/s]\n 86%|████████▌ | 43/50 [00:02<00:00, 17.73it/s]\n 90%|█████████ | 45/50 [00:02<00:00, 17.75it/s]\n 94%|█████████▍| 47/50 [00:02<00:00, 17.74it/s]\n 98%|█████████▊| 49/50 [00:02<00:00, 17.75it/s]\n100%|██████████| 50/50 [00:02<00:00, 17.17it/s]",
  "metrics": {
    "predict_time": 8.863272431,
    "total_time": 178.613352
  },
  "output": [
    "https://replicate.delivery/pbxt/3JBMfWo8zei49006xsKzCBfKsX4Z2S5YqeuHfTZsldEO5TDcC/out-0.png"
  ],
  "started_at": "2024-09-25T11:36:33.520080Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/fksmvkk4v9rgg0cj53ttj44dh0",
    "cancel": "https://api.replicate.com/v1/predictions/fksmvkk4v9rgg0cj53ttj44dh0/cancel"
  },
  "version": "18fd619984b344195d4f9f45a849ecc514475ec7e07f8966b0dc679676cc4960"
}

Generated in

8.9 seconds

Tweak it Iterate in playground ShareReport View full prediction

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.