IP Adapter Face ID

fal-ai/ip-adapter-face-id
Inference
Research only

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/serverless-client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import * as fal from "@fal-ai/serverless-client";

const result = await fal.subscribe("fal-ai/ip-adapter-face-id", {
  input: {
    prompt: "Man cyberpunk, synthwave night city, futuristic, high quality, highly detailed, high resolution, sharp, hyper realistic, extremely detailed"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
import * as fal from "@fal-ai/serverless-client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import * as fal from "@fal-ai/serverless-client";

// Upload a file (you can get a file reference from an input element or a drag-and-drop event)
const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

// Use the URL in your request
const result = await fal.subscribe("fal-ai/ip-adapter-face-id", { image_url: url });

Read more about file handling in our file upload guide.

4. Schema#

Input#

model_typeModelTypeEnum

The model type to use. 1_5 is the default and is recommended for most use cases. Default value: "1_5-v1"

Possible values: "1_5-v1", "1_5-v1-plus", "1_5-v2-plus", "SDXL-v1", "SDXL-v2-plus"

prompt*string

The prompt to use for generating the image. Be as descriptive as possible for best results.

face_image_urlstring

An image of a face to match. If an image with a size of 640x640 is not provided, it will be scaled and cropped to that size.

face_images_data_urlstring

URL to zip archive with images of faces. The images embedding will be averaged to create a more accurate face id.

negative_promptstring

The negative prompt to use.Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). Default value: "blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy"

seedinteger

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

guidance_scalefloat

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Default value: 7.5

num_inference_stepsinteger

The number of inference steps to use for generating the image. The more steps the better the image will be but it will also take longer to generate. Default value: 50

num_samplesinteger

The number of samples for face id. The more samples the better the image will be but it will also take longer to generate. Default is 4. Default value: 4

widthinteger

The width of the generated image. Default value: 512

heightinteger

The height of the generated image. Default value: 512

face_id_det_sizeinteger

The size of the face detection model. The higher the number the more accurate the detection will be but it will also take longer to run. The higher the number the more likely it will fail to find a face as well. Lower it if you are having trouble finding a face in the image. Default value: 640

base_1_5_model_repostring

The URL to the base 1.5 model. Default is SG161222/Realistic_Vision_V4.0_noVAE Default value: "SG161222/Realistic_Vision_V4.0_noVAE"

base_sdxl_model_repostring

The URL to the base SDXL model. Default is SG161222/RealVisXL_V3.0 Default value: "SG161222/RealVisXL_V3.0"

{
  "model_type": "1_5-v1",
  "prompt": "Man cyberpunk, synthwave night city, futuristic, high quality, highly detailed, high resolution, sharp, hyper realistic, extremely detailed",
  "face_image_url": "https://storage.googleapis.com/falserverless/model_tests/upscale/image%20(8).png",
  "negative_prompt": "blurry, low resolution, bad, ugly, low quality, pixelated, interpolated, compression artifacts, noisey, grainy",
  "seed": 42,
  "guidance_scale": 7.5,
  "num_inference_steps": 50,
  "num_samples": 4,
  "width": 512,
  "height": 512,
  "face_id_det_size": 640,
  "base_1_5_model_repo": "SG161222/Realistic_Vision_V4.0_noVAE",
  "base_sdxl_model_repo": "SG161222/RealVisXL_V3.0"
}

Output#

image*Image

The generated image file info.

seed*integer

Seed of the generated Image. It will be the same value of the one passed in the input or the randomly generated that was used in case none was passed.

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019,
    "width": 1024,
    "height": 1024
  }
}