/fal-ai

name: fal-ai
description: Generate images, videos, and audio with fal.ai serverless AI. Use when building AI image generation, video generation, image editing, or real-time AI features. Triggers on fal.ai, fal, AI image generation, Flux, SDXL, real-time AI, serverless AI.

fal.ai - Serverless AI Platform

Generate images, videos, and audio with fal.ai's fast serverless inference.

Quick Start

npm install @fal-ai/serverless-client

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

fal.config({
  credentials: process.env.FAL_KEY,
});

// Generate image with Flux
const result = await fal.subscribe('fal-ai/flux/dev', {
  input: {
    prompt: 'A serene Japanese garden with cherry blossoms',
    image_size: 'landscape_16_9',
    num_images: 1,
  },
});

console.log(result.images[0].url);

Authentication

// Option 1: Environment variable (recommended)
// Set FAL_KEY in .env
fal.config({ credentials: process.env.FAL_KEY });

// Option 2: Direct config
fal.config({ credentials: 'your-api-key' });

// Option 3: Proxy (for client-side apps)
// Use fal.config({ proxyUrl: '/api/fal/proxy' }) on client

Image Generation Models

Flux (Fastest, High Quality)

// Flux Dev - Best quality
const result = await fal.subscribe('fal-ai/flux/dev', {
  input: {
    prompt: 'Professional headshot of a business executive',
    image_size: 'square_hd',  // 1024x1024
    num_inference_steps: 28,
    guidance_scale: 3.5,
    num_images: 1,
    enable_safety_checker: true,
  },
});

// Flux Schnell - Ultra fast (~0.5s)
const fast = await fal.subscribe('fal-ai/flux/schnell', {
  input: {
    prompt: 'A cute robot',
    image_size: 'square',
    num_inference_steps: 4,  // Schnell needs fewer steps
  },
});

// Flux Pro - Highest quality
const pro = await fal.subscribe('fal-ai/flux-pro', {
  input: {
    prompt: 'Hyperrealistic portrait',
    image_size: 'portrait_4_3',
    safety_tolerance: '2',
  },
});

Image Sizes

type ImageSize = 
  | 'square_hd'      // 1024x1024
  | 'square'         // 512x512
  | 'portrait_4_3'   // 768x1024
  | 'portrait_16_9'  // 576x1024
  | 'landscape_4_3'  // 1024x768
  | 'landscape_16_9' // 1024x576
  | { width: number; height: number };  // Custom

SDXL & Stable Diffusion

// SDXL
const sdxl = await fal.subscribe('fal-ai/fast-sdxl', {
  input: {
    prompt: 'Fantasy landscape',
    negative_prompt: 'blurry, low quality',
    image_size: 'landscape_16_9',
    num_inference_steps: 25,
    guidance_scale: 7.5,
    scheduler: 'DPM++ 2M Karras',
  },
});

// Stable Diffusion 3
const sd3 = await fal.subscribe('fal-ai/stable-diffusion-v3-medium', {
  input: {
    prompt: 'A mountain lake at sunset',
    negative_prompt: 'ugly, deformed',
    image_size: 'landscape_16_9',
  },
});

Image-to-Image

Image Editing with Flux

// Image to image
const result = await fal.subscribe('fal-ai/flux/dev/image-to-image', {
  input: {
    prompt: 'Transform to watercolor painting style',
    image_url: 'https://example.com/photo.jpg',
    strength: 0.75,  // How much to change (0-1)
    num_inference_steps: 28,
  },
});

// Inpainting (edit specific areas)
const inpaint = await fal.subscribe('fal-ai/flux/dev/inpainting', {
  input: {
    prompt: 'A red sports car',
    image_url: 'https://example.com/street.jpg',
    mask_url: 'https://example.com/mask.png',  // White = edit area
  },
});

ControlNet

// Generate with pose/edge control
const controlled = await fal.subscribe('fal-ai/flux-controlnet', {
  input: {
    prompt: 'A professional dancer',
    control_image_url: 'https://example.com/pose.jpg',
    controlnet_conditioning_scale: 0.8,
  },
});

Video Generation

Kling Video

const video = await fal.subscribe('fal-ai/kling-video/v1/standard/text-to-video', {
  input: {
    prompt: 'A golden retriever running through a field of flowers',
    duration: '5',  // seconds
    aspect_ratio: '16:9',
  },
});

console.log(video.video.url);

Image to Video

const i2v = await fal.subscribe('fal-ai/kling-video/v1/standard/image-to-video', {
  input: {
    prompt: 'The person starts walking forward',
    image_url: 'https://example.com/person.jpg',
    duration: '5',
  },
});

Luma Dream Machine

const luma = await fal.subscribe('fal-ai/luma-dream-machine', {
  input: {
    prompt: 'A timelapse of clouds moving over mountains',
    aspect_ratio: '16:9',
  },
});

Real-Time Generation

WebSocket Streaming

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

// Real-time image generation with streaming
const stream = await fal.stream('fal-ai/flux/dev', {
  input: {
    prompt: 'A beautiful sunset',
    image_size: 'landscape_16_9',
  },
});

for await (const event of stream) {
  if (event.images) {
    console.log('Generated:', event.images[0].url);
  }
}

Real-Time SDXL (Low Latency)

// Ultra-low latency for interactive apps
const realtime = await fal.subscribe('fal-ai/fast-lcm-diffusion', {
  input: {
    prompt: 'Abstract art',
    image_size: 'square',
    num_inference_steps: 4,  // LCM needs very few steps
  },
});

Background Removal & Editing

// Remove background
const nobg = await fal.subscribe('fal-ai/birefnet', {
  input: {
    image_url: 'https://example.com/photo.jpg',
  },
});

// Upscale image
const upscaled = await fal.subscribe('fal-ai/creative-upscaler', {
  input: {
    image_url: 'https://example.com/small.jpg',
    scale: 2,
    creativity: 0.5,
    prompt: 'High quality, detailed',
  },
});

// Face swap
const swapped = await fal.subscribe('fal-ai/face-swap', {
  input: {
    base_image_url: 'https://example.com/target.jpg',
    swap_image_url: 'https://example.com/face.jpg',
  },
});

Next.js Integration

API Route (App Router)

// app/api/generate/route.ts
import * as fa