fal

Image generation service implementation using fal’s fast SDXL models

Overview

FalImageGenService provides high-speed image generation capabilities using fal’s optimized Stable Diffusion XL models. It supports various image sizes, formats, and generation parameters with a focus on fast inference and low-latency image creation.

Fal Image Gen API Reference

Pipecat’s API methods for fal image generation integration

Example Implementation

Browse examples using fal image generation

fal Documentation

Official fal API documentation and model guides

fal Platform

Access fast SDXL models and manage API keys

Installation

To use fal image generation services, install the required dependencies:

pip install "pipecat-ai[fal]"

Prerequisites

fal Account Setup

Before using fal image generation services, you need:

1. fal Account: Sign up at fal Platform
2. API Key: Generate an API key from your account dashboard
3. Model Selection: Choose from available fast SDXL models
4. HTTP Session: Configure aiohttp session for image downloading

Required Environment Variables

• FAL_KEY: Your fal API key for authentication

Configuration

params · InputParams · required

Input parameters for image generation configuration. See InputParams below.

aiohttp_session · aiohttp.ClientSession · required

HTTP client session for downloading generated images.

model · str · default: "fal-ai/fast-sdxl"

The fal model to use for image generation.

key · str · default: "None"

Optional API key for fal. If provided, sets the FAL_KEY environment variable.

InputParams

Parameter	Type	Default	Description
seed	int	None	Random seed for reproducible generation. If None, uses a random seed.
num_inference_steps	int	8	Number of inference steps for generation.
num_images	int	1	Number of images to generate.
image_size	str | dict	"square_hd"	Image dimensions as a string preset or dict with width/height keys.
expand_prompt	bool	False	Whether to automatically expand/enhance the prompt.
enable_safety_checker	bool	True	Whether to enable content safety filtering.
format	str	"png"	Output image format.

Usage

Basic Setup

import aiohttp
from pipecat.services.fal import FalImageGenService

async with aiohttp.ClientSession() as session:
    image_gen = FalImageGenService(
        params=FalImageGenService.InputParams(
            image_size="landscape_16_9",
        ),
        aiohttp_session=session,
        key=os.getenv("FAL_KEY"),
    )

With Custom Parameters

image_gen = FalImageGenService(
    params=FalImageGenService.InputParams(
        image_size={"width": 1024, "height": 768},
        num_inference_steps=12,
        seed=42,
        enable_safety_checker=True,
    ),
    aiohttp_session=session,
    model="fal-ai/fast-sdxl",
)

Notes

• Environment variable: If the key constructor parameter is provided, it sets the FAL_KEY environment variable automatically.
• HTTP session required: You must provide an aiohttp.ClientSession for downloading the generated images from fal’s URLs.
• Image size presets: The image_size parameter accepts string presets (e.g., "square_hd", "landscape_16_9") or a dictionary with explicit width and height values.