Latent Consistency (SDXL & SDv1.5) | Text to Image | API Documentation

fal-ai/lcm

Produce high-quality images with minimal inference steps.

Inference

Commercial use

About

Generates an image using the given prompt and model.

If only the prompt is given, the model will generate an image from scratch, this process is also known as "text-to-image".

If an image is given (via image_url parameter), the model will generate an image that's similar to the given image depending on the strength parameter. This process is also known as "image-to-image".

If an image and a mask are given (via image_url and mask_url parameters), the model will generate an image that fills the mask area with the most relevant content from the given image. This process is also known as "inpainting".

1. Calling the API#

Install the client#

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

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

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 { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/lcm", {
  input: {
    prompt: "a black cat with glowing eyes, cute, adorable, disney, pixar, highly detailed, 8k"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

Real-time via WebSockets#

This model has a real-time mode via websockets, this is supported via the fal.realtime client.

import { fal } from "@fal-ai/client";

const connection = fal.realtime.connect("fal-ai/lcm", {
  onResult: (result) => {
    console.log(result);
  },
  onError: (error) => {
    console.error(error);
  }
});

connection.send({
  prompt: "a black cat with glowing eyes, cute, adorable, disney, pixar, highly detailed, 8k"
});

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 { fal } from "@fal-ai/client";

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

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/lcm", {
  input: {
    prompt: "a black cat with glowing eyes, cute, adorable, disney, pixar, highly detailed, 8k"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/lcm", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/lcm", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. 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 { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

model ModelEnum

The model to use for generating the image. Default value: "sdv1-5"

Possible enum values: sdxl, sdv1-5

prompt string* required

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

image_url string

The base image to use for guiding the image generation on image-to-image generations. If the either width or height of the image is larger than 1024 pixels, the image will be resized to 1024 pixels while keeping the aspect ratio.

mask_url string

The mask to use for guiding the image generation on image inpainting. The model will focus on the mask area and try to fill it with the most relevant content.

The mask must be a black and white image where the white area is the area that needs to be filled and the black area is the area that should be ignored.

The mask must have the same dimensions as the image passed as image_url.

strength float

The strength of the image that is passed as image_url. The strength determines how much the generated image will be similar to the image passed as image_url. The higher the strength the more model gets "creative" and generates an image that's different from the initial image. A strength of 1.0 means that the initial image is more or less ignored and the model will try to generate an image that's as close as possible to the prompt. Default value: 0.8

negative_prompt string

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: ""

seed integer

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

guidance_scale float

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: 1

num_inference_steps integer

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: 4

image_size ImageSize | Enum

The size of the generated image. You can choose between some presets or custom height and width that must be multiples of 8.

If not provided:

For text-to-image generations, the default size is 512x512.
For image-to-image generations, the default size is the same as the input image.
For inpainting generations, the default size is the same as the input image.

Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}

sync_mode boolean

If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN.

num_images integer

The number of images to generate. The function will return a list of images with the same prompt and negative prompt but different seeds. Default value: 1

enable_safety_checks boolean

If set to true, the resulting image will be checked whether it includes any potentially unsafe content. If it does, it will be replaced with a black image. Default value: true

request_id string

An id bound to a request, can be used with response to identify the request itself. Default value: ""

inpaint_mask_only boolean

If set to true, the inpainting pipeline will only inpaint the provided mask area. Only effective for inpainting pipelines.

controlnet_inpaint boolean

If set to true, the inpainting pipeline will use controlnet inpainting. Only effective for inpainting pipelines.

lora_url string

The url of the lora server to use for image generation.

lora_scale float

The scale of the lora server to use for image generation. Default value: 1

{
  "model": "sdv1-5",
  "prompt": "a black cat with glowing eyes, cute, adorable, disney, pixar, highly detailed, 8k",
  "image_url": "https://storage.googleapis.com/falserverless/model_tests/lcm/inpaint_image.png",
  "mask_url": "https://storage.googleapis.com/falserverless/model_tests/lcm/inpaint_mask.png",
  "strength": 0.8,
  "negative_prompt": "cartoon, illustration, animation. face. male, female",
  "seed": 42,
  "guidance_scale": 1,
  "num_inference_steps": 4,
  "num_images": 1,
  "enable_safety_checks": true,
  "lora_scale": 1
}

Output#

images list<Image>* required

The generated image files info.

timings Timings* required

seed integer* required

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.

num_inference_steps integer

Number of inference steps used to generate the image. It will be the same value of the one passed in the input or the default one in case none was passed. Default value: 4

request_id string

An id bound to a request, can be used with response to identify the request itself. Default value: ""

nsfw_content_detected list<boolean>* required

A list of booleans indicating whether the generated image contains any potentially unsafe content. If the safety check is disabled, this field will all will be false.

{
  "images": [
    {
      "url": "",
      "content_type": "image/jpeg"
    }
  ],
  "num_inference_steps": 4
}

Other types#

ImageSize#

width integer

The width of the generated image. Default value: 512

height integer

The height of the generated image. Default value: 512

Image#

url string* required

width integer* required

height integer* required

content_type string

Default value: "image/jpeg"

Related Models

fal-ai/stable-diffusion-v35-large

text-to-image

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

diffusion

fal-ai/stable-diffusion-v3-medium

text-to-image

Stable Diffusion 3 Medium (Text to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

diffusion

style

Latent Consistency (SDXL & SDv1.5) Text to Image

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

Real-time via WebSockets#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

ImageSize#

Image#

Related Models