image

Fal’s image generation service implementation.

This module provides integration with Fal’s image generation API for creating images from text prompts using various AI models.

Bases: ImageGenSettings

Settings for the Fal image generation service.

Parameters:

model – Fal.ai model identifier.
seed – Random seed for reproducible generation. None uses a random seed.
num_inference_steps – Number of inference steps for generation.
num_images – Number of images to generate.
image_size – Image dimensions as a string preset or dict with width/height.
expand_prompt – Whether to automatically expand/enhance the prompt.
enable_safety_checker – Whether to enable content safety filtering.
format – Output image format.

seed: int | None | _NotGiven

num_inference_steps: int | _NotGiven

num_images: int | _NotGiven

image_size: str | dict[str, int] | _NotGiven

expand_prompt: bool | _NotGiven

enable_safety_checker: bool | _NotGiven

format: str | _NotGiven

to_api_arguments() → dict[str, Any][source]: Build the Fal API arguments dict from settings, excluding None values.

class pipecat.services.fal.image.FalImageGenService(*, params: InputParams | None = None, aiohttp_session: ClientSession, model: str | None = None, key: str | None = None, settings: FalImageGenSettings | None = None, **kwargs)[source]

Bases: ImageGenService

Fal’s image generation service.

Provides text-to-image generation using Fal.ai’s API with configurable parameters for image quality, safety, and format options.

Settings: alias of FalImageGenSettings

class InputParams(*, seed: int | None = None, num_inference_steps: int = 8, num_images: int = 1, image_size: str | dict[str, int] = 'square_hd', expand_prompt: bool = False, enable_safety_checker: bool = True, format: str = 'png')[source]

Bases: BaseModel

Input parameters for Fal.ai image generation.

Deprecated since version 0.0.105: Use settings=FalImageGenService.Settings(...) instead.

Parameters:

seed – Random seed for reproducible generation. If None, uses random seed.
num_inference_steps – Number of inference steps for generation. Defaults to 8.
num_images – Number of images to generate. Defaults to 1.
image_size – Image dimensions as string preset or dict with width/height. Defaults to “square_hd”.
expand_prompt – Whether to automatically expand/enhance the prompt. Defaults to False.
enable_safety_checker – Whether to enable content safety filtering. Defaults to True.
format – Output image format. Defaults to “png”.

seed: int | None

num_inference_steps: int

num_images: int

image_size: str | dict[str, int]

expand_prompt: bool

enable_safety_checker: bool

format: str

__init__(*, params: InputParams | None = None, aiohttp_session: ClientSession, model: str | None = None, key: str | None = None, settings: FalImageGenSettings | None = None, **kwargs)[source]

Initialize the FalImageGenService.

Parameters:

params –
Input parameters for image generation configuration.

Deprecated since version 0.0.105: Use settings=FalImageGenService.Settings(...) instead.
aiohttp_session – HTTP client session for downloading generated images.
model –
The Fal.ai model to use for generation. Defaults to “fal-ai/fast-sdxl”.

Deprecated since version 0.0.105: Use settings=FalImageGenService.Settings(model=...) instead.
key – Optional API key for Fal.ai. If provided, sets FAL_KEY environment variable.
settings – Runtime-updatable settings. When provided alongside deprecated parameters, settings values take precedence.
**kwargs – Additional arguments passed to parent ImageGenService.

async run_image_gen(prompt: str) → AsyncGenerator[Frame, None][source]

Generate an image from a text prompt.

Parameters:: prompt – The text prompt to generate an image from.
Yields:: URLImageRawFrame – Frame containing the generated image data and metadata. ErrorFrame: If image generation fails.